diff --git a/147127/neon-cluster-meta-runner-nvidia/divOperator.json b/147127/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..436df0b --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "283210", "standardDeviation": "3004.45", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "283567", "standardDeviation": "6020.53", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547051", "standardDeviation": "4682.98", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "266469", "standardDeviation": "5150.22", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05423e+06", "standardDeviation": "2327.34", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "290512", "standardDeviation": "4505.66", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.29226e+06", "standardDeviation": "51588.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "300211", "standardDeviation": "4811.92", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.25737e+06", "standardDeviation": "29203.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "325207", "standardDeviation": "6341.84", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/147127/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..3bc4ed8 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/147127/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..f7b3813 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/divOperator_time.png b/147127/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..f95cb55 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/field.json b/147127/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..e3c805b --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "432745", "standardDeviation": "2839.05", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32844.8", "standardDeviation": "926.797", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "461058", "standardDeviation": "7944.81", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32863.1", "standardDeviation": "1129.47", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "952404", "standardDeviation": "173772", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36994.8", "standardDeviation": "4516.25", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.86752e+06", "standardDeviation": "251769", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42824.1", "standardDeviation": "1048.94", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66571e+06", "standardDeviation": "53057.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "711311", "standardDeviation": "58780.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "319861", "standardDeviation": "38932.4", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27288.2", "standardDeviation": "728.163", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631735", "standardDeviation": "2326.6", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27239.9", "standardDeviation": "624.959", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25866e+06", "standardDeviation": "2775.69", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31366.6", "standardDeviation": "3937.11", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.53192e+06", "standardDeviation": "201571", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35582.2", "standardDeviation": "743.289", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.02408e+06", "standardDeviation": "55187.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "708698", "standardDeviation": "58238.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/field_fvops.png b/147127/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..ac0729f Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/field_relative.png b/147127/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..f4741b0 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/field_time.png b/147127/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..c496444 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/linear.json b/147127/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..5674e4c --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100709", "standardDeviation": "991.475", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "150227", "standardDeviation": "1572.72", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2672.17", "standardDeviation": "83.3287", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200615", "standardDeviation": "1946.93", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299572", "standardDeviation": "1653.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2655.76", "standardDeviation": "123.617", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "413398", "standardDeviation": "123002", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597596", "standardDeviation": "2040.58", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2682.54", "standardDeviation": "61.0053", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "801246", "standardDeviation": "13643.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19321e+06", "standardDeviation": "2071.46", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2731.41", "standardDeviation": "329.204", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57964e+06", "standardDeviation": "59893.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38402e+06", "standardDeviation": "4952.17", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2666.64", "standardDeviation": "109.719", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130321", "standardDeviation": "2188.13", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139207", "standardDeviation": "1683.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2347.91", "standardDeviation": "57.8588", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "259905", "standardDeviation": "2166.23", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "295292", "standardDeviation": "2296.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2332.2", "standardDeviation": "71.6547", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "553319", "standardDeviation": "3078.79", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "585278", "standardDeviation": "2771.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2351.66", "standardDeviation": "200.721", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.04405e+06", "standardDeviation": "3573.23", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.16724e+06", "standardDeviation": "3831.97", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2425.22", "standardDeviation": "199.873", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.55543e+06", "standardDeviation": "18812.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.66081e+06", "standardDeviation": "17033.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2386.02", "standardDeviation": "128.739", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/linear_fvops.png b/147127/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..4988547 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/linear_relative.png b/147127/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..f28e3a4 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/linear_time.png b/147127/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..14b69fe Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/lscpu.log b/147127/neon-cluster-meta-runner-nvidia/lscpu.log new file mode 100644 index 0000000..0a2e791 --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/lscpu.log @@ -0,0 +1,38 @@ +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected diff --git a/147127/neon-cluster-meta-runner-nvidia/main/divOperator.json b/147127/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..190de5d --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "548530", "standardDeviation": "43684.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "384372", "standardDeviation": "5738.75", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "541787", "standardDeviation": "13103.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "247767", "standardDeviation": "3444.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05419e+06", "standardDeviation": "25147.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "252298", "standardDeviation": "3497.46", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.13096e+06", "standardDeviation": "405265", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "263028", "standardDeviation": "20708.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.73624e+06", "standardDeviation": "67615.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284269", "standardDeviation": "3298.06", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/main/field.json b/147127/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..2ee341b --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "216129", "standardDeviation": "3161.78", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29440.1", "standardDeviation": "783.535", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "886140", "standardDeviation": "32841", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47693.2", "standardDeviation": "1594.79", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79998e+06", "standardDeviation": "6538.91", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35021", "standardDeviation": "2403.15", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82849e+06", "standardDeviation": "24960.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "44521", "standardDeviation": "1531.69", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.70665e+06", "standardDeviation": "59141.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "712164", "standardDeviation": "57176.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "317142", "standardDeviation": "2180.03", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24194.2", "standardDeviation": "1049.69", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "630903", "standardDeviation": "8309.74", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25733.4", "standardDeviation": "3218.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25888e+06", "standardDeviation": "8188.63", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36075.6", "standardDeviation": "12860.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.51668e+06", "standardDeviation": "22213.7", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32948.5", "standardDeviation": "994.267", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.16382e+06", "standardDeviation": "380140", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "701625", "standardDeviation": "40106.2", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/main/linear.json b/147127/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..1f8ae2b --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100393", "standardDeviation": "2234.43", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149597", "standardDeviation": "1447.21", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2375.4", "standardDeviation": "460.933", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200492", "standardDeviation": "3726.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "306646", "standardDeviation": "76078.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2342.06", "standardDeviation": "151.704", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "426932", "standardDeviation": "211910", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597428", "standardDeviation": "3073.68", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2392.29", "standardDeviation": "119.655", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "814642", "standardDeviation": "47171.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19462e+06", "standardDeviation": "5797.98", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2469.42", "standardDeviation": "657.793", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57563e+06", "standardDeviation": "81017.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.396e+06", "standardDeviation": "18882", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2364.7", "standardDeviation": "180.917", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130044", "standardDeviation": "7971.08", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "140591", "standardDeviation": "7990.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2326.16", "standardDeviation": "154.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "263480", "standardDeviation": "21108.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "280858", "standardDeviation": "19203.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2363.07", "standardDeviation": "128.102", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "524631", "standardDeviation": "43536.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "557181", "standardDeviation": "41155.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2379.14", "standardDeviation": "177.898", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10628e+06", "standardDeviation": "95084.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.20801e+06", "standardDeviation": "96307.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2325.78", "standardDeviation": "229.207", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.23808e+06", "standardDeviation": "128109", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.28412e+06", "standardDeviation": "115972", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2361.12", "standardDeviation": "296.413", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/main/lscpu.log b/147127/neon-cluster-meta-runner-nvidia/main/lscpu.log new file mode 100644 index 0000000..0a2e791 --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/main/lscpu.log @@ -0,0 +1,38 @@ +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected diff --git a/147127/neon-cluster-meta-runner-nvidia/main/upwind.json b/147127/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..4e25f20 --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83331.4", "standardDeviation": "1521.28", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133501", "standardDeviation": "1631.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2518.99", "standardDeviation": "127.75", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167066", "standardDeviation": "4016.74", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266570", "standardDeviation": "2374.06", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2473.11", "standardDeviation": "151.275", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "334572", "standardDeviation": "9912.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531842", "standardDeviation": "4014.45", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2451.02", "standardDeviation": "127.192", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "669482", "standardDeviation": "24591.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06323e+06", "standardDeviation": "8578.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2468.94", "standardDeviation": "189.274", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.38618e+06", "standardDeviation": "91873.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.13092e+06", "standardDeviation": "20067.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2444.25", "standardDeviation": "199.667", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "119941", "standardDeviation": "8255.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136850", "standardDeviation": "6212.18", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2456.73", "standardDeviation": "133.059", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "243860", "standardDeviation": "113153", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272513", "standardDeviation": "17658.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2398.64", "standardDeviation": "168.977", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "487421", "standardDeviation": "47414.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "553140", "standardDeviation": "44250.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2457.28", "standardDeviation": "190.059", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00119e+06", "standardDeviation": "97254.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12597e+06", "standardDeviation": "229826", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2473.25", "standardDeviation": "168.699", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.2814e+06", "standardDeviation": "140038", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.32655e+06", "standardDeviation": "126775", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2486.28", "standardDeviation": "241.401", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/upwind.json b/147127/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..27fbadb --- /dev/null +++ b/147127/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83393.5", "standardDeviation": "919.525", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133378", "standardDeviation": "1022.31", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2593.48", "standardDeviation": "437.505", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166701", "standardDeviation": "1391.93", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266985", "standardDeviation": "5212.66", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2465.35", "standardDeviation": "87.7688", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "347398", "standardDeviation": "128655", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "532236", "standardDeviation": "1981.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2769.05", "standardDeviation": "56.1916", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "668731", "standardDeviation": "4096.43", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06185e+06", "standardDeviation": "1721.79", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2795.53", "standardDeviation": "272.557", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33618e+06", "standardDeviation": "10244.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12289e+06", "standardDeviation": "3323.83", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2759.85", "standardDeviation": "352.578", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172916", "standardDeviation": "5030.61", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "172328", "standardDeviation": "60805.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2816.84", "standardDeviation": "180.095", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "327345", "standardDeviation": "19111", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278912", "standardDeviation": "5217.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2801.78", "standardDeviation": "205.168", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "598902", "standardDeviation": "56032.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "609268", "standardDeviation": "44429.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2749.83", "standardDeviation": "73.8336", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.08726e+06", "standardDeviation": "291195", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.14264e+06", "standardDeviation": "82605.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2791.16", "standardDeviation": "161.304", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.4324e+06", "standardDeviation": "225773", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.99819e+06", "standardDeviation": "174405", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2789.36", "standardDeviation": "196.964", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147127/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/147127/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..5c94212 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/upwind_relative.png b/147127/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..c9639ec Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/147127/neon-cluster-meta-runner-nvidia/upwind_time.png b/147127/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..17f5ff2 Binary files /dev/null and b/147127/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/147150/divOperator.json b/147150/divOperator.json new file mode 100644 index 0000000..617bf15 --- /dev/null +++ b/147150/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "277054", "standardDeviation": "3051.15", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "263693", "standardDeviation": "5095.73", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "579177", "standardDeviation": "23465.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "268529", "standardDeviation": "3602.61", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.09122e+06", "standardDeviation": "46903.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272578", "standardDeviation": "4379.87", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.13321e+06", "standardDeviation": "375228", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272015", "standardDeviation": "3731.97", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.16321e+06", "standardDeviation": "120681", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "311523", "standardDeviation": "4030.12", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147150/field.json b/147150/field.json new file mode 100644 index 0000000..d7e50ab --- /dev/null +++ b/147150/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "432567", "standardDeviation": "4970.37", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31095.8", "standardDeviation": "801.567", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "455815", "standardDeviation": "5081.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32428.3", "standardDeviation": "639.824", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "930091", "standardDeviation": "13950.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36246.3", "standardDeviation": "4037.97", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.86246e+06", "standardDeviation": "248974", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40628.2", "standardDeviation": "1011.48", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66441e+06", "standardDeviation": "47202.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "709169", "standardDeviation": "58707.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "320183", "standardDeviation": "36841.1", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26874.5", "standardDeviation": "527.879", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "633039", "standardDeviation": "4546.99", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26809.5", "standardDeviation": "473.094", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.2575e+06", "standardDeviation": "2677.58", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32634.6", "standardDeviation": "3769.67", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.52564e+06", "standardDeviation": "161543", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35849.4", "standardDeviation": "1074.73", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.01497e+06", "standardDeviation": "5528.76", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "708861", "standardDeviation": "58663.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147150/linear.json b/147150/linear.json new file mode 100644 index 0000000..efafac9 --- /dev/null +++ b/147150/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100734", "standardDeviation": "1153.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149498", "standardDeviation": "875.987", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2638.21", "standardDeviation": "51.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "201323", "standardDeviation": "1412.99", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299381", "standardDeviation": "1812.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2690.87", "standardDeviation": "61.423", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "416455", "standardDeviation": "146165", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597932", "standardDeviation": "2559.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2741.26", "standardDeviation": "214.21", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "799124", "standardDeviation": "9892.32", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.1939e+06", "standardDeviation": "2226.33", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2699.33", "standardDeviation": "111.991", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58829e+06", "standardDeviation": "44614.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38342e+06", "standardDeviation": "3361.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2679.36", "standardDeviation": "136.733", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "180089", "standardDeviation": "5989.66", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "179564", "standardDeviation": "8748.15", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2652", "standardDeviation": "45.1129", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "285669", "standardDeviation": "11357.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "341182", "standardDeviation": "20138.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2600.92", "standardDeviation": "59.8236", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "628030", "standardDeviation": "65906.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "636564", "standardDeviation": "57085.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2667.9", "standardDeviation": "113.698", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.23242e+06", "standardDeviation": "253556", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.24001e+06", "standardDeviation": "95210.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2781.23", "standardDeviation": "533.67", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.65318e+06", "standardDeviation": "199797", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.1418e+06", "standardDeviation": "134982", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2734.93", "standardDeviation": "211.275", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147150/main/divOperator.json b/147150/main/divOperator.json new file mode 100644 index 0000000..eebbcec --- /dev/null +++ b/147150/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "288814", "standardDeviation": "4268.88", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "268763", "standardDeviation": "5758.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "576792", "standardDeviation": "23610.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "263269", "standardDeviation": "4551.18", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.09333e+06", "standardDeviation": "46670", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "274222", "standardDeviation": "3598.32", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.21621e+06", "standardDeviation": "1.11338e+06", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284010", "standardDeviation": "3256.42", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.48314e+06", "standardDeviation": "176626", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "307916", "standardDeviation": "3438.35", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147150/main/field.json b/147150/main/field.json new file mode 100644 index 0000000..8e450f3 --- /dev/null +++ b/147150/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "220996", "standardDeviation": "20364.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33099.1", "standardDeviation": "4740.53", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "453382", "standardDeviation": "4767.62", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33694.2", "standardDeviation": "8979.16", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "929498", "standardDeviation": "13530.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39380.7", "standardDeviation": "3112.36", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83836e+06", "standardDeviation": "24205.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41996.5", "standardDeviation": "1390.07", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.65828e+06", "standardDeviation": "40697.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "710157", "standardDeviation": "59373.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "317400", "standardDeviation": "1442.97", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26792.9", "standardDeviation": "501.851", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631622", "standardDeviation": "2201.77", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26928.7", "standardDeviation": "832.537", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.2585e+06", "standardDeviation": "2704.28", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31606.2", "standardDeviation": "3938.21", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.5824e+06", "standardDeviation": "411206", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35297.2", "standardDeviation": "983.313", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.01544e+06", "standardDeviation": "18990.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "708411", "standardDeviation": "58301.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147150/main/linear.json b/147150/main/linear.json new file mode 100644 index 0000000..ca0e612 --- /dev/null +++ b/147150/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100633", "standardDeviation": "796.168", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "150304", "standardDeviation": "1351.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2724.45", "standardDeviation": "392.801", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200831", "standardDeviation": "2989.93", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "305783", "standardDeviation": "66189.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2676.95", "standardDeviation": "174.877", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "400267", "standardDeviation": "5616.99", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597129", "standardDeviation": "2022.42", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2672.45", "standardDeviation": "91.6254", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "800707", "standardDeviation": "5520.53", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19159e+06", "standardDeviation": "1682.67", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2845.17", "standardDeviation": "1871.31", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57886e+06", "standardDeviation": "51261", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38301e+06", "standardDeviation": "2770.71", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2686.89", "standardDeviation": "125.388", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "156249", "standardDeviation": "3339.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "161690", "standardDeviation": "4974.17", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2648.54", "standardDeviation": "206.038", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "313157", "standardDeviation": "16577.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "317284", "standardDeviation": "14581.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2597.64", "standardDeviation": "108.319", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "592727", "standardDeviation": "47335.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "611344", "standardDeviation": "35487.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2632.59", "standardDeviation": "84.4494", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12083e+06", "standardDeviation": "91142.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.20248e+06", "standardDeviation": "48718.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2689.73", "standardDeviation": "138.451", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.69567e+06", "standardDeviation": "170211", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.91134e+06", "standardDeviation": "146544", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2764.11", "standardDeviation": "347.252", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147150/main/upwind.json b/147150/main/upwind.json new file mode 100644 index 0000000..eeaeb54 --- /dev/null +++ b/147150/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83681.8", "standardDeviation": "1158.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133257", "standardDeviation": "779.112", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2865.45", "standardDeviation": "184.338", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168249", "standardDeviation": "1836.22", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "267122", "standardDeviation": "2426.11", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2849.8", "standardDeviation": "118.764", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340830", "standardDeviation": "55756.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "532364", "standardDeviation": "1992.93", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2750.91", "standardDeviation": "63.9389", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "673175", "standardDeviation": "3836.01", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06332e+06", "standardDeviation": "1737.61", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2803.74", "standardDeviation": "271.773", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33572e+06", "standardDeviation": "6551.65", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12301e+06", "standardDeviation": "4039.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2782.33", "standardDeviation": "99.9989", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "160741", "standardDeviation": "4384.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "157056", "standardDeviation": "3820.04", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2772.75", "standardDeviation": "91.5528", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "299896", "standardDeviation": "15535.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "302825", "standardDeviation": "63735.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2735.13", "standardDeviation": "177.77", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "562728", "standardDeviation": "48483.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "575385", "standardDeviation": "31221.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2694.74", "standardDeviation": "81.7546", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "969699", "standardDeviation": "48585.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.10046e+06", "standardDeviation": "46416.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2722.59", "standardDeviation": "97.7675", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.27597e+06", "standardDeviation": "212687", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.87235e+06", "standardDeviation": "141003", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2699.61", "standardDeviation": "194.486", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147150/system-info.log b/147150/system-info.log new file mode 100644 index 0000000..0764dd3 --- /dev/null +++ b/147150/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA L40S, 46068 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/147150/upwind.json b/147150/upwind.json new file mode 100644 index 0000000..594d58c --- /dev/null +++ b/147150/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83699.8", "standardDeviation": "1080.26", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133558", "standardDeviation": "897.358", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2914.3", "standardDeviation": "361.523", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169278", "standardDeviation": "1579.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266855", "standardDeviation": "1529.29", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2823.95", "standardDeviation": "223.559", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "350303", "standardDeviation": "132232", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "532938", "standardDeviation": "2099.22", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2863.36", "standardDeviation": "199.393", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "673038", "standardDeviation": "12956.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06309e+06", "standardDeviation": "2972.78", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2787.2", "standardDeviation": "87.9863", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34383e+06", "standardDeviation": "14340.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12237e+06", "standardDeviation": "3672.23", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2900.87", "standardDeviation": "408.874", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170068", "standardDeviation": "5537.28", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "165986", "standardDeviation": "5852.85", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2878.46", "standardDeviation": "69.7942", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "331133", "standardDeviation": "18627.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "330123", "standardDeviation": "87326.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2793.73", "standardDeviation": "71.2078", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "608255", "standardDeviation": "62763.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "605602", "standardDeviation": "44703.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2708.15", "standardDeviation": "104.643", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09111e+06", "standardDeviation": "141017", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.15298e+06", "standardDeviation": "101284", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2813.09", "standardDeviation": "84.4176", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.42801e+06", "standardDeviation": "222295", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.51347e+06", "standardDeviation": "166086", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2779.99", "standardDeviation": "130.503", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/divOperator.json b/147162/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..e929862 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "276293", "standardDeviation": "4001.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "260738", "standardDeviation": "5632.89", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "544809", "standardDeviation": "13763.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262994", "standardDeviation": "5274.59", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.06046e+06", "standardDeviation": "22848.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "270252", "standardDeviation": "6015.79", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.07789e+06", "standardDeviation": "52002", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "282684", "standardDeviation": "6660.94", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.43561e+06", "standardDeviation": "141877", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "302780", "standardDeviation": "5732.17", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/147162/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..c67b9d9 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/147162/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..07a21fe Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/divOperator_time.png b/147162/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..993ae54 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/field.json b/147162/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..9eb1932 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "434674", "standardDeviation": "2983.69", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50257.7", "standardDeviation": "864.077", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "919082", "standardDeviation": "4958.66", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32643.4", "standardDeviation": "1120.09", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "937750", "standardDeviation": "17827.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38640.9", "standardDeviation": "634.503", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.85471e+06", "standardDeviation": "270539", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42173.1", "standardDeviation": "1060.41", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.64854e+06", "standardDeviation": "27253", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699657", "standardDeviation": "57763.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "319128", "standardDeviation": "34629.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24536.5", "standardDeviation": "935.122", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "637095", "standardDeviation": "26189", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25488.4", "standardDeviation": "2182.64", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25825e+06", "standardDeviation": "2525.39", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32881.8", "standardDeviation": "785.599", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.52592e+06", "standardDeviation": "144462", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32467.8", "standardDeviation": "634.066", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.08442e+06", "standardDeviation": "320786", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699680", "standardDeviation": "59124.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/field_fvops.png b/147162/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..622f9b7 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/field_relative.png b/147162/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..e59181a Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/field_time.png b/147162/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..785f850 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/linear.json b/147162/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..3ff3a32 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100265", "standardDeviation": "1602.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "300731", "standardDeviation": "12016.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2588.26", "standardDeviation": "2619.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "216396", "standardDeviation": "55398.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "302360", "standardDeviation": "1730.06", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2329.06", "standardDeviation": "139.762", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "399012", "standardDeviation": "1607.24", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596683", "standardDeviation": "1210.22", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2335.27", "standardDeviation": "89.6307", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "799201", "standardDeviation": "1774.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19071e+06", "standardDeviation": "1159.93", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2357.31", "standardDeviation": "144.121", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58388e+06", "standardDeviation": "52342.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38179e+06", "standardDeviation": "1897.73", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2366.84", "standardDeviation": "235.943", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "128326", "standardDeviation": "1565.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138545", "standardDeviation": "1284.49", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2374.08", "standardDeviation": "134.689", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "257242", "standardDeviation": "2533.62", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278431", "standardDeviation": "2300.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2351.08", "standardDeviation": "76.41", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "513829", "standardDeviation": "3224.67", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "555687", "standardDeviation": "2676.17", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2346.27", "standardDeviation": "201.982", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12358e+06", "standardDeviation": "3923.28", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.13265e+06", "standardDeviation": "11479.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2415.38", "standardDeviation": "288.634", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.9626e+06", "standardDeviation": "71835.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.11443e+06", "standardDeviation": "64668", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2420.89", "standardDeviation": "349.706", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/linear_fvops.png b/147162/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..c34ddfe Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/linear_relative.png b/147162/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..5bb0a35 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/linear_time.png b/147162/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..dbc4886 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/main/divOperator.json b/147162/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..08ca75f --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "275813", "standardDeviation": "2282.77", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "260390", "standardDeviation": "5513.79", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "542016", "standardDeviation": "2843.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262672", "standardDeviation": "5073.26", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05635e+06", "standardDeviation": "17726.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "266612", "standardDeviation": "7120.74", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.07231e+06", "standardDeviation": "36728.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278922", "standardDeviation": "6160.48", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.40679e+06", "standardDeviation": "163943", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "304196", "standardDeviation": "4810.53", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/main/field.json b/147162/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..5d38c35 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "215495", "standardDeviation": "1967.53", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31945.7", "standardDeviation": "1939.79", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "446624", "standardDeviation": "5104.68", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32328.7", "standardDeviation": "2380.58", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "917166", "standardDeviation": "13289.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40748.5", "standardDeviation": "858.546", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.8508e+06", "standardDeviation": "251151", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41624.6", "standardDeviation": "960.171", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.64813e+06", "standardDeviation": "23317.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "708937", "standardDeviation": "54472.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "320282", "standardDeviation": "37429.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26663.8", "standardDeviation": "979.069", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631140", "standardDeviation": "4133.76", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28191.2", "standardDeviation": "3233.02", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25835e+06", "standardDeviation": "8660.46", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34647.3", "standardDeviation": "1479.67", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.53537e+06", "standardDeviation": "161201", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35107.8", "standardDeviation": "1183.78", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.08868e+06", "standardDeviation": "310038", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "707848", "standardDeviation": "56309.2", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/main/linear.json b/147162/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..a811b18 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100151", "standardDeviation": "1258.42", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149684", "standardDeviation": "930.537", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2433.14", "standardDeviation": "403.656", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199743", "standardDeviation": "1132.02", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304492", "standardDeviation": "60507", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2401.61", "standardDeviation": "130.971", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "422718", "standardDeviation": "245464", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597313", "standardDeviation": "1219.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2430.52", "standardDeviation": "340.197", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "799795", "standardDeviation": "1717.04", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19343e+06", "standardDeviation": "1411.15", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2452.31", "standardDeviation": "109.207", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.60789e+06", "standardDeviation": "2482.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.43843e+06", "standardDeviation": "223416", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2459.61", "standardDeviation": "190.488", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "128755", "standardDeviation": "1824.14", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139677", "standardDeviation": "1533.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2410.55", "standardDeviation": "67.0751", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "258155", "standardDeviation": "3046.42", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "276587", "standardDeviation": "2498.24", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2429.13", "standardDeviation": "81.0802", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "520191", "standardDeviation": "3458", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "555698", "standardDeviation": "11673.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2395.5", "standardDeviation": "151.331", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.05997e+06", "standardDeviation": "5932.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11019e+06", "standardDeviation": "3466.22", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2482.97", "standardDeviation": "116.015", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.71125e+06", "standardDeviation": "68969.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.99132e+06", "standardDeviation": "88115.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2456.46", "standardDeviation": "332.78", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/main/upwind.json b/147162/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..b229760 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83411.8", "standardDeviation": "658.132", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133188", "standardDeviation": "1064.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2796.97", "standardDeviation": "141.039", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167267", "standardDeviation": "4207.88", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266325", "standardDeviation": "1771.85", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2899.32", "standardDeviation": "1263.81", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "335781", "standardDeviation": "11187.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531061", "standardDeviation": "1320.66", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2760.79", "standardDeviation": "176.634", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "666487", "standardDeviation": "2407.87", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06182e+06", "standardDeviation": "9281.58", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2725.93", "standardDeviation": "171.602", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33815e+06", "standardDeviation": "46553.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12306e+06", "standardDeviation": "14827.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2725.26", "standardDeviation": "497.219", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122328", "standardDeviation": "8608.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137489", "standardDeviation": "15477.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2797.84", "standardDeviation": "171.714", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "243274", "standardDeviation": "19444.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275727", "standardDeviation": "3917.33", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2716.76", "standardDeviation": "223.612", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "480873", "standardDeviation": "45717.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "543290", "standardDeviation": "21005.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2686.22", "standardDeviation": "225.876", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "976152", "standardDeviation": "63053.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09457e+06", "standardDeviation": "82816.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2703.34", "standardDeviation": "233.96", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.0813e+06", "standardDeviation": "84990.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.05008e+06", "standardDeviation": "179934", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2650.36", "standardDeviation": "330.23", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/system-info.log b/147162/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..0764dd3 --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA L40S, 46068 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/147162/neon-cluster-meta-runner-nvidia/upwind.json b/147162/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..b9c5aea --- /dev/null +++ b/147162/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83163.5", "standardDeviation": "989.885", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133181", "standardDeviation": "1118.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2549.8", "standardDeviation": "467.618", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166621", "standardDeviation": "1703.52", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266424", "standardDeviation": "1773.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2450.48", "standardDeviation": "139.198", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "344153", "standardDeviation": "111253", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "532216", "standardDeviation": "2152.93", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2425.09", "standardDeviation": "147.92", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "665699", "standardDeviation": "2078.86", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06194e+06", "standardDeviation": "1209.81", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2423.03", "standardDeviation": "96.9685", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33281e+06", "standardDeviation": "2337.17", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.14057e+06", "standardDeviation": "73069.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2499.76", "standardDeviation": "277.698", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "118490", "standardDeviation": "1584.01", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "142403", "standardDeviation": "61789.6", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2449.04", "standardDeviation": "147.064", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "227223", "standardDeviation": "3406.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "270365", "standardDeviation": "2093.44", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2455.84", "standardDeviation": "79.2342", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "482771", "standardDeviation": "25665.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "542140", "standardDeviation": "2451.59", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2434.81", "standardDeviation": "155.81", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "977087", "standardDeviation": "205080", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0779e+06", "standardDeviation": "4733.58", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2497.95", "standardDeviation": "381.214", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.53949e+06", "standardDeviation": "101315", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.65115e+06", "standardDeviation": "135515", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2449.31", "standardDeviation": "246.184", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147162/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/147162/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..9c2ff22 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/upwind_relative.png b/147162/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..f46c7a7 Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/147162/neon-cluster-meta-runner-nvidia/upwind_time.png b/147162/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..47075ea Binary files /dev/null and b/147162/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/divOperator.json b/147163/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..3e967a5 --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "280655", "standardDeviation": "2363.54", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262779", "standardDeviation": "3742.72", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "561003", "standardDeviation": "9695.25", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262411", "standardDeviation": "3823.04", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.11174e+06", "standardDeviation": "269932", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "268833", "standardDeviation": "3944.96", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.18044e+06", "standardDeviation": "432729", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280287", "standardDeviation": "4030.93", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.24734e+06", "standardDeviation": "15995.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "303821", "standardDeviation": "3922.84", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/147163/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..eeada9d Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/147163/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..afc49ee Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/divOperator_time.png b/147163/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..db1d6a0 Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/field.json b/147163/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..a02e6e5 --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "427766", "standardDeviation": "2558.44", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45061.2", "standardDeviation": "1377.83", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "888083", "standardDeviation": "14376.4", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31196.8", "standardDeviation": "1203.14", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "919366", "standardDeviation": "2161.36", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40038.9", "standardDeviation": "1656.08", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.85546e+06", "standardDeviation": "219671", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40669.1", "standardDeviation": "1057.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.65739e+06", "standardDeviation": "4491.67", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "701398", "standardDeviation": "58576", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "320775", "standardDeviation": "35567.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26298.9", "standardDeviation": "384.746", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631245", "standardDeviation": "2209.87", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27220.8", "standardDeviation": "2044.81", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25748e+06", "standardDeviation": "1884.08", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35079.9", "standardDeviation": "1378.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.52742e+06", "standardDeviation": "180771", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34818.4", "standardDeviation": "498.031", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.01313e+06", "standardDeviation": "3075.46", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700901", "standardDeviation": "58124.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/field_fvops.png b/147163/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..58fa769 Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/field_relative.png b/147163/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..e959a6c Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/field_time.png b/147163/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..5b9156e Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/linear.json b/147163/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..81bd405 --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100551", "standardDeviation": "840.346", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149492", "standardDeviation": "954.924", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2598.78", "standardDeviation": "408.078", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199681", "standardDeviation": "1081.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304988", "standardDeviation": "64147.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2554.86", "standardDeviation": "132.561", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "426148", "standardDeviation": "233615", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596348", "standardDeviation": "1381.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2569.76", "standardDeviation": "50.9774", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "798150", "standardDeviation": "15644.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19158e+06", "standardDeviation": "1925.56", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2564.06", "standardDeviation": "83.2718", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.59852e+06", "standardDeviation": "1729.22", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38222e+06", "standardDeviation": "6925.06", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2555.21", "standardDeviation": "116.869", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "131365", "standardDeviation": "1406.96", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "140520", "standardDeviation": "1328.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2582.56", "standardDeviation": "142.297", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "256653", "standardDeviation": "2588.15", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "284050", "standardDeviation": "2410.12", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2570.86", "standardDeviation": "172.113", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "520529", "standardDeviation": "3344.59", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "557857", "standardDeviation": "2552.73", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2531.78", "standardDeviation": "102.983", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07527e+06", "standardDeviation": "3895.41", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.17445e+06", "standardDeviation": "3424.75", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2567.74", "standardDeviation": "88.0796", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.61405e+06", "standardDeviation": "18968.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.78604e+06", "standardDeviation": "24543.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2559.34", "standardDeviation": "244.001", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/linear_fvops.png b/147163/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..46251cb Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/linear_relative.png b/147163/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..568c770 Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/linear_time.png b/147163/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..ad0f84c Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/main/divOperator.json b/147163/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..d99c142 --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "297126", "standardDeviation": "5612.18", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281967", "standardDeviation": "6376.04", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "601709", "standardDeviation": "27646.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285660", "standardDeviation": "5300.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.1163e+06", "standardDeviation": "63133.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "290820", "standardDeviation": "7394.12", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.12629e+06", "standardDeviation": "99776.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "317712", "standardDeviation": "5155.41", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.20364e+06", "standardDeviation": "161870", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "313020", "standardDeviation": "5405.87", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/main/field.json b/147163/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..320e66b --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "217956", "standardDeviation": "3031.47", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34953.1", "standardDeviation": "1567.94", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "457021", "standardDeviation": "5147.34", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34907.6", "standardDeviation": "1301.15", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "935808", "standardDeviation": "18044.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36486.9", "standardDeviation": "2649.79", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.84616e+06", "standardDeviation": "31508.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "44429.3", "standardDeviation": "1067.98", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66649e+06", "standardDeviation": "50066.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "709366", "standardDeviation": "57467.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "319385", "standardDeviation": "22317.1", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29385", "standardDeviation": "1277.08", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631714", "standardDeviation": "2294.14", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29578.2", "standardDeviation": "984.461", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25855e+06", "standardDeviation": "2640.48", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31719.4", "standardDeviation": "3243.59", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.52999e+06", "standardDeviation": "188198", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38201.8", "standardDeviation": "1079.28", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.01771e+06", "standardDeviation": "4370.58", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "706797", "standardDeviation": "58641.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/main/linear.json b/147163/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..407a6ad --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100854", "standardDeviation": "1338.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149751", "standardDeviation": "930.558", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2997.37", "standardDeviation": "97.1519", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "201709", "standardDeviation": "1561.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299229", "standardDeviation": "1594.93", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3059.84", "standardDeviation": "187.918", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "410168", "standardDeviation": "103044", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597653", "standardDeviation": "2393.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3016.72", "standardDeviation": "102.499", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "799713", "standardDeviation": "5202.09", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19225e+06", "standardDeviation": "1953.55", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3042.67", "standardDeviation": "378.52", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57993e+06", "standardDeviation": "50911.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38304e+06", "standardDeviation": "4478.67", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2996.93", "standardDeviation": "113.02", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "175173", "standardDeviation": "6494.45", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "182225", "standardDeviation": "77789.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2834.19", "standardDeviation": "76.6943", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "336767", "standardDeviation": "20707.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "347635", "standardDeviation": "13208.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3071.76", "standardDeviation": "83.1758", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "633177", "standardDeviation": "60055", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "632248", "standardDeviation": "54162", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2968.94", "standardDeviation": "85.0218", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.17247e+06", "standardDeviation": "139395", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.25449e+06", "standardDeviation": "83537.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3024.01", "standardDeviation": "211.029", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.74686e+06", "standardDeviation": "204514", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.95626e+06", "standardDeviation": "175559", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2903.46", "standardDeviation": "203.852", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/main/upwind.json b/147163/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..d1c7d5b --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84660.8", "standardDeviation": "1047.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133487", "standardDeviation": "770.349", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3173.86", "standardDeviation": "60.0737", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198469", "standardDeviation": "4080.59", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "267360", "standardDeviation": "1975.02", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3053.57", "standardDeviation": "57.7522", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "363864", "standardDeviation": "12540.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "532577", "standardDeviation": "2476.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3121.86", "standardDeviation": "94.4689", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "727347", "standardDeviation": "42187.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08986e+06", "standardDeviation": "180433", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3126.07", "standardDeviation": "271.703", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.41854e+06", "standardDeviation": "87506.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12743e+06", "standardDeviation": "11568.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2983.57", "standardDeviation": "163.963", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200622", "standardDeviation": "6377.34", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "205535", "standardDeviation": "6366.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3199.01", "standardDeviation": "190.908", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "374722", "standardDeviation": "24496.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "394633", "standardDeviation": "23579.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3003.46", "standardDeviation": "197.119", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "710391", "standardDeviation": "75553.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "727800", "standardDeviation": "68333.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3071.94", "standardDeviation": "361.473", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.25524e+06", "standardDeviation": "187279", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.25342e+06", "standardDeviation": "104398", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2988.97", "standardDeviation": "209.606", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.5942e+06", "standardDeviation": "287486", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.75401e+06", "standardDeviation": "227527", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3047.43", "standardDeviation": "512.169", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/system-info.log b/147163/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..0764dd3 --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA L40S, 46068 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/147163/neon-cluster-meta-runner-nvidia/upwind.json b/147163/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..597c94f --- /dev/null +++ b/147163/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83268.3", "standardDeviation": "565.789", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133285", "standardDeviation": "893.205", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2781.54", "standardDeviation": "127.696", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166934", "standardDeviation": "1075.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266053", "standardDeviation": "1263.05", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2760.39", "standardDeviation": "105.481", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340199", "standardDeviation": "21575.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531565", "standardDeviation": "1727.69", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2674.55", "standardDeviation": "122.987", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "666960", "standardDeviation": "1595.29", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06128e+06", "standardDeviation": "1349.92", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2698.76", "standardDeviation": "159.123", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33021e+06", "standardDeviation": "3527.86", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12239e+06", "standardDeviation": "2504.93", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2645.3", "standardDeviation": "96.7837", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121151", "standardDeviation": "1541.69", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136676", "standardDeviation": "1206.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2763.3", "standardDeviation": "70.8767", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "238626", "standardDeviation": "3123.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "284147", "standardDeviation": "128531", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2671.91", "standardDeviation": "147.626", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "472846", "standardDeviation": "3677.15", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "542086", "standardDeviation": "2753.15", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2655.03", "standardDeviation": "104.582", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "963149", "standardDeviation": "5953.03", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07763e+06", "standardDeviation": "1517.66", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2630.92", "standardDeviation": "68.4092", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.42118e+06", "standardDeviation": "21124.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.57333e+06", "standardDeviation": "18521.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2607.98", "standardDeviation": "127.472", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147163/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/147163/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..bac9af5 Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/upwind_relative.png b/147163/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..389ab1e Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/147163/neon-cluster-meta-runner-nvidia/upwind_time.png b/147163/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..df754bb Binary files /dev/null and b/147163/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/divOperator.json b/147233/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..c365e87 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "280701", "standardDeviation": "23152.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "242989", "standardDeviation": "4039.16", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547835", "standardDeviation": "2929.55", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "244586", "standardDeviation": "4174.84", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05474e+06", "standardDeviation": "5578.91", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "249988", "standardDeviation": "4221.67", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.07538e+06", "standardDeviation": "2920.18", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262323", "standardDeviation": "3899.01", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.18769e+06", "standardDeviation": "18575.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286856", "standardDeviation": "4389.76", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/147233/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..5a5c14e Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/147233/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..866e0d8 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/divOperator_time.png b/147233/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..4f40f1f Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/field.json b/147233/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..1c82ad1 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "427095", "standardDeviation": "2191.85", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29786", "standardDeviation": "759.411", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445929", "standardDeviation": "4137.15", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29945.8", "standardDeviation": "1290.95", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "932026", "standardDeviation": "158152", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38906.7", "standardDeviation": "602.625", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.84965e+06", "standardDeviation": "158964", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39296.6", "standardDeviation": "1167.43", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.64676e+06", "standardDeviation": "2967.01", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700125", "standardDeviation": "58885", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "315660", "standardDeviation": "1500.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24763.4", "standardDeviation": "716.755", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "629914", "standardDeviation": "1700.24", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25662.1", "standardDeviation": "1968.13", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.25661e+06", "standardDeviation": "5401.04", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33025.4", "standardDeviation": "964.875", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.51294e+06", "standardDeviation": "1999.34", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32995.5", "standardDeviation": "836.716", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.01915e+06", "standardDeviation": "1630.37", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699946", "standardDeviation": "59179.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/field_fvops.png b/147233/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..caaa7ac Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/field_relative.png b/147233/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..cd65940 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/field_time.png b/147233/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..d9e3590 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/linear.json b/147233/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..f07fdd1 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100031", "standardDeviation": "988.891", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149647", "standardDeviation": "1322.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2317.48", "standardDeviation": "91.3291", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199919", "standardDeviation": "1435.91", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "298671", "standardDeviation": "1751.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2316.4", "standardDeviation": "71.3999", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "412872", "standardDeviation": "129046", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596733", "standardDeviation": "1736.64", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2348.54", "standardDeviation": "146.139", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "800650", "standardDeviation": "1824.88", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19226e+06", "standardDeviation": "1376.51", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2396.73", "standardDeviation": "229.348", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58899e+06", "standardDeviation": "42913", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38334e+06", "standardDeviation": "3305.27", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2377.89", "standardDeviation": "74.0149", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138824", "standardDeviation": "2304.44", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "151998", "standardDeviation": "70207.3", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2348.18", "standardDeviation": "137.062", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "271446", "standardDeviation": "4301.49", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "280153", "standardDeviation": "3021.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2339.26", "standardDeviation": "71.6799", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "565668", "standardDeviation": "6285.34", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "563811", "standardDeviation": "4354.47", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2408.47", "standardDeviation": "232.46", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.14511e+06", "standardDeviation": "199278", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.15728e+06", "standardDeviation": "4977.45", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2393.93", "standardDeviation": "143.39", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.80212e+06", "standardDeviation": "18454.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.93935e+06", "standardDeviation": "21447.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2371.48", "standardDeviation": "111.859", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/linear_fvops.png b/147233/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..f48f17f Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/linear_relative.png b/147233/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..bc8cee1 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/linear_time.png b/147233/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..157fc77 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/main/divOperator.json b/147233/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..434022b --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "277826", "standardDeviation": "2452.63", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "241483", "standardDeviation": "4128.58", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "541800", "standardDeviation": "2726.04", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "247001", "standardDeviation": "24995.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05112e+06", "standardDeviation": "2268.26", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "250006", "standardDeviation": "2459.26", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.09208e+06", "standardDeviation": "305456", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262134", "standardDeviation": "3996.69", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.35585e+06", "standardDeviation": "108000", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286861", "standardDeviation": "2469.35", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/main/field.json b/147233/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..0a61df8 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "215212", "standardDeviation": "2894.08", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30174.3", "standardDeviation": "1661.59", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "456488", "standardDeviation": "5829.71", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29488.5", "standardDeviation": "2004.08", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "938364", "standardDeviation": "148615", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38619.2", "standardDeviation": "1458.89", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83493e+06", "standardDeviation": "5304.14", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39824.9", "standardDeviation": "780.389", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.6681e+06", "standardDeviation": "5405.07", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700656", "standardDeviation": "58487.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "317281", "standardDeviation": "3217.68", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24225", "standardDeviation": "814.243", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "632275", "standardDeviation": "3428.73", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25788.8", "standardDeviation": "2951.83", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.26181e+06", "standardDeviation": "4794.07", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33051.9", "standardDeviation": "1009.67", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.53694e+06", "standardDeviation": "140551", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32794.6", "standardDeviation": "947.225", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.03338e+06", "standardDeviation": "5549.15", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700197", "standardDeviation": "58299.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/main/linear.json b/147233/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..cfc9cd5 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100481", "standardDeviation": "1107.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149725", "standardDeviation": "1252.4", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2388.03", "standardDeviation": "391.624", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200611", "standardDeviation": "1651.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304805", "standardDeviation": "57717.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2333.47", "standardDeviation": "69.5155", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "400339", "standardDeviation": "8624.04", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596417", "standardDeviation": "1745.64", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2467.03", "standardDeviation": "264.108", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "788719", "standardDeviation": "35175.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19576e+06", "standardDeviation": "4139.59", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2411.05", "standardDeviation": "136.76", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58959e+06", "standardDeviation": "51808.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38488e+06", "standardDeviation": "5478.56", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2407.72", "standardDeviation": "150.662", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147321", "standardDeviation": "4594.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159394", "standardDeviation": "4131.89", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2351.28", "standardDeviation": "120.434", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "297636", "standardDeviation": "7016.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "316207", "standardDeviation": "6129.39", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2367.11", "standardDeviation": "136.255", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "595562", "standardDeviation": "10757.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "628671", "standardDeviation": "9534.56", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.35", "standardDeviation": "241.267", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.18865e+06", "standardDeviation": "11279.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.26468e+06", "standardDeviation": "22722.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2346.35", "standardDeviation": "178.535", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.87031e+06", "standardDeviation": "25305.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.98126e+06", "standardDeviation": "22905.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2436.98", "standardDeviation": "171.537", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/main/upwind.json b/147233/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..a93f33c --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "85947.6", "standardDeviation": "23017.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133827", "standardDeviation": "1291.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2530.12", "standardDeviation": "63.2827", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166985", "standardDeviation": "1351.53", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266131", "standardDeviation": "1458.68", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2448.95", "standardDeviation": "123.204", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332561", "standardDeviation": "1735.91", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "530989", "standardDeviation": "1796.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2477.11", "standardDeviation": "132.58", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "666994", "standardDeviation": "2124.25", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08645e+06", "standardDeviation": "214455", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2496.43", "standardDeviation": "89.295", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33378e+06", "standardDeviation": "45260.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.12217e+06", "standardDeviation": "2232.73", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2461.32", "standardDeviation": "86.6302", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "119920", "standardDeviation": "1931.91", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135809", "standardDeviation": "1302.94", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2470.73", "standardDeviation": "57.1007", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "243283", "standardDeviation": "11323.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "284764", "standardDeviation": "129923", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2469", "standardDeviation": "150.619", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "474071", "standardDeviation": "4641.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "540029", "standardDeviation": "2170.42", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2472.12", "standardDeviation": "223.256", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "974000", "standardDeviation": "6298.68", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09596e+06", "standardDeviation": "2238.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2471.15", "standardDeviation": "131.774", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.35702e+06", "standardDeviation": "21072.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.34923e+06", "standardDeviation": "13054", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2523.24", "standardDeviation": "336.808", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/system-info.log b/147233/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..0764dd3 --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA L40S, 46068 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/147233/neon-cluster-meta-runner-nvidia/upwind.json b/147233/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..a919bab --- /dev/null +++ b/147233/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83381.8", "standardDeviation": "1108.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133093", "standardDeviation": "1158.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2564.9", "standardDeviation": "411.957", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167524", "standardDeviation": "1365.74", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266358", "standardDeviation": "1572.38", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2463.4", "standardDeviation": "77.1786", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "339334", "standardDeviation": "60798.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531353", "standardDeviation": "1796.78", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2470.18", "standardDeviation": "86.828", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "667498", "standardDeviation": "2054.43", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06177e+06", "standardDeviation": "1365.35", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2458.73", "standardDeviation": "174.296", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33009e+06", "standardDeviation": "1598.08", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.122e+06", "standardDeviation": "1873.57", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2498.29", "standardDeviation": "63.5411", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "127871", "standardDeviation": "1571.76", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139264", "standardDeviation": "1594.37", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2445.95", "standardDeviation": "97.942", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "259761", "standardDeviation": "4838.46", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "287172", "standardDeviation": "112462", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2432.13", "standardDeviation": "63.9097", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "518917", "standardDeviation": "8578.82", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "553541", "standardDeviation": "2481.95", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2408.53", "standardDeviation": "200.737", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.04135e+06", "standardDeviation": "28227.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11496e+06", "standardDeviation": "6419.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2436.7", "standardDeviation": "158.005", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34285e+06", "standardDeviation": "13843.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.57352e+06", "standardDeviation": "30729", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2436.57", "standardDeviation": "174.067", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/147233/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/147233/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..fbdd567 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/upwind_relative.png b/147233/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..96ce8b0 Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/147233/neon-cluster-meta-runner-nvidia/upwind_time.png b/147233/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..8bbf8ea Binary files /dev/null and b/147233/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..b735b55 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "389283", "standardDeviation": "3327.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "322077", "standardDeviation": "3249.92", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "764042", "standardDeviation": "3938.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "324233", "standardDeviation": "2762.48", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.48263e+06", "standardDeviation": "4715.83", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "327148", "standardDeviation": "2957.17", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.99815e+06", "standardDeviation": "11595.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286941", "standardDeviation": "2007.77", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.20457e+06", "standardDeviation": "660221", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "312961", "standardDeviation": "2741.68", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..c42f156 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..08c7fc7 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..f838b3b Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..7e7946f --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306131", "standardDeviation": "2280.12", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43689.8", "standardDeviation": "1056.54", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "654317", "standardDeviation": "11406.8", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49026.7", "standardDeviation": "1916.73", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.32951e+06", "standardDeviation": "7107.37", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49033.3", "standardDeviation": "2209.04", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.81723e+06", "standardDeviation": "41088.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45378.5", "standardDeviation": "1052.14", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.57265e+06", "standardDeviation": "12929.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145358", "standardDeviation": "3299.65", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "308508", "standardDeviation": "1624.45", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34017.4", "standardDeviation": "3792.07", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "615807", "standardDeviation": "1991.34", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39023.6", "standardDeviation": "814.84", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22699e+06", "standardDeviation": "1649.86", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38923.9", "standardDeviation": "9388.42", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.45058e+06", "standardDeviation": "2953.95", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39358.9", "standardDeviation": "743.762", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.89398e+06", "standardDeviation": "3388.34", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131027", "standardDeviation": "2584.29", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..32003a7 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..e863186 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..4bf3ca9 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..f54882a --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "97620.4", "standardDeviation": "787.217", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "146019", "standardDeviation": "907.311", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2473.35", "standardDeviation": "63.6409", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194458", "standardDeviation": "3170.59", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "294316", "standardDeviation": "5974.27", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2486.46", "standardDeviation": "115.437", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "395799", "standardDeviation": "8245.97", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588518", "standardDeviation": "11260.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2492.72", "standardDeviation": "142.694", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "785787", "standardDeviation": "21343.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.186e+06", "standardDeviation": "98984.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2490.88", "standardDeviation": "170.421", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.55972e+06", "standardDeviation": "69810.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35131e+06", "standardDeviation": "20317.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2499.47", "standardDeviation": "136.989", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "124749", "standardDeviation": "2619.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138441", "standardDeviation": "2947.96", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2550.44", "standardDeviation": "118.846", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "249624", "standardDeviation": "5168.91", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "273989", "standardDeviation": "5342.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2404.27", "standardDeviation": "96.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "509936", "standardDeviation": "4696.82", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "548596", "standardDeviation": "9759.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2486.76", "standardDeviation": "80.0519", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00156e+06", "standardDeviation": "14958.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11201e+06", "standardDeviation": "15641", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2550.53", "standardDeviation": "92.0892", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.56014e+06", "standardDeviation": "25231.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.74232e+06", "standardDeviation": "22469", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2541.39", "standardDeviation": "226.945", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..f6053e8 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..2586f8b Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..7aff3a4 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..2ba3b15 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "274484", "standardDeviation": "2802.77", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277177", "standardDeviation": "6331.29", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540318", "standardDeviation": "5133.68", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281068", "standardDeviation": "4271.44", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.04796e+06", "standardDeviation": "6656.95", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284426", "standardDeviation": "22691.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.06136e+06", "standardDeviation": "33154.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "288955", "standardDeviation": "3638.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.51553e+06", "standardDeviation": "235418", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "314508", "standardDeviation": "4388.58", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..e8145d2 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306677", "standardDeviation": "1539.76", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41354", "standardDeviation": "2462.19", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "631958", "standardDeviation": "1796.09", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42644.8", "standardDeviation": "799.688", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "884689", "standardDeviation": "1205.39", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42163.5", "standardDeviation": "695.01", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.76576e+06", "standardDeviation": "1563.16", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42906.7", "standardDeviation": "643.458", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.52681e+06", "standardDeviation": "4175.74", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130910", "standardDeviation": "16464.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "307633", "standardDeviation": "1339.23", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35951.5", "standardDeviation": "814.851", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "613835", "standardDeviation": "2149.97", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36021.8", "standardDeviation": "762.965", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22587e+06", "standardDeviation": "1164.04", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37037.2", "standardDeviation": "11028.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.4658e+06", "standardDeviation": "4977.66", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39627.2", "standardDeviation": "3843.94", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.92618e+06", "standardDeviation": "6113.89", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121901", "standardDeviation": "3428.85", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..5fd638a --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99075.3", "standardDeviation": "2408.33", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147829", "standardDeviation": "3081.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2599.1", "standardDeviation": "598.163", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198699", "standardDeviation": "7719.26", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "302080", "standardDeviation": "75821.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2543.78", "standardDeviation": "129.497", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394425", "standardDeviation": "8914.75", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588227", "standardDeviation": "10431", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2630.91", "standardDeviation": "121.115", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "793225", "standardDeviation": "36114.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.1739e+06", "standardDeviation": "14558.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2769.35", "standardDeviation": "2343", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57497e+06", "standardDeviation": "62022.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35005e+06", "standardDeviation": "26970.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2499.45", "standardDeviation": "181.909", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137651", "standardDeviation": "5415.08", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137915", "standardDeviation": "4714.55", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2513.38", "standardDeviation": "125.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "271365", "standardDeviation": "11257.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "295871", "standardDeviation": "12550.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2473.19", "standardDeviation": "90.1385", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "543982", "standardDeviation": "43492.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "592968", "standardDeviation": "35575.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2582.25", "standardDeviation": "192.773", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10757e+06", "standardDeviation": "129727", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.20257e+06", "standardDeviation": "122733", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2488.82", "standardDeviation": "119.327", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.9176e+06", "standardDeviation": "266472", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.28187e+06", "standardDeviation": "187730", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2552.24", "standardDeviation": "347.486", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..85d6ab5 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82302.1", "standardDeviation": "2175.42", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130591", "standardDeviation": "1430.05", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2690.71", "standardDeviation": "78.9534", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "165365", "standardDeviation": "3907.38", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262796", "standardDeviation": "5362.97", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2573.5", "standardDeviation": "86.6413", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "342236", "standardDeviation": "127573", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525234", "standardDeviation": "10343.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2630.05", "standardDeviation": "171.853", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "670245", "standardDeviation": "28178.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05049e+06", "standardDeviation": "17083.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2567.38", "standardDeviation": "200.222", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33708e+06", "standardDeviation": "67133.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.10082e+06", "standardDeviation": "31217.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2594.43", "standardDeviation": "127.488", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "126765", "standardDeviation": "26646", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136009", "standardDeviation": "4904.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2592.93", "standardDeviation": "132.039", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "234761", "standardDeviation": "13674.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "281506", "standardDeviation": "138117", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2505.5", "standardDeviation": "104.748", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "494604", "standardDeviation": "40929.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536451", "standardDeviation": "36022", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2535.37", "standardDeviation": "209.822", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01252e+06", "standardDeviation": "128230", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12212e+06", "standardDeviation": "116247", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2543.08", "standardDeviation": "133.727", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.55705e+06", "standardDeviation": "272847", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.72115e+06", "standardDeviation": "237490", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2553.88", "standardDeviation": "178.702", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/149699/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..1969d75 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA H100 NVL, 95830 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..17e26d8 --- /dev/null +++ b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82689.6", "standardDeviation": "2581.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131237", "standardDeviation": "2800.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2650.23", "standardDeviation": "77.6873", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164612", "standardDeviation": "3067.41", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263003", "standardDeviation": "4534.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3326.85", "standardDeviation": "110.188", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "366267", "standardDeviation": "133266", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "527131", "standardDeviation": "8960.25", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3326.22", "standardDeviation": "126.306", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "735812", "standardDeviation": "38815", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05263e+06", "standardDeviation": "16571.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3299.74", "standardDeviation": "159.612", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.40177e+06", "standardDeviation": "94316.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09699e+06", "standardDeviation": "22817.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3254.86", "standardDeviation": "124.047", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "203388", "standardDeviation": "6530.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "202476", "standardDeviation": "7165.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3136.18", "standardDeviation": "256.689", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "372889", "standardDeviation": "25921.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "390485", "standardDeviation": "117575", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3237.9", "standardDeviation": "386.16", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "701382", "standardDeviation": "75620.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "686953", "standardDeviation": "81030", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3215.8", "standardDeviation": "335.72", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.23959e+06", "standardDeviation": "202805", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28397e+06", "standardDeviation": "173170", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3205.24", "standardDeviation": "165.431", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.82988e+06", "standardDeviation": "294400", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.96063e+06", "standardDeviation": "49152.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2566.89", "standardDeviation": "160.506", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..e987434 Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..d5d2d0a Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..a5cd8ed Binary files /dev/null and b/149699/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..3559a55 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "401275", "standardDeviation": "6356.48", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "297082", "standardDeviation": "7492.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "624009", "standardDeviation": "31255.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "305683", "standardDeviation": "4063.04", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.18132e+06", "standardDeviation": "105450", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "309043", "standardDeviation": "4622.05", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.19015e+06", "standardDeviation": "188985", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "313738", "standardDeviation": "8287.92", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.47587e+06", "standardDeviation": "471113", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "335785", "standardDeviation": "7879.07", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..6179c10 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..bd3d51d Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..454c2fa Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..c28b696 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "313684", "standardDeviation": "3865.44", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49793.9", "standardDeviation": "1111.54", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "673932", "standardDeviation": "19937.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50086.4", "standardDeviation": "2055.5", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.38225e+06", "standardDeviation": "243543", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50401.7", "standardDeviation": "2232.46", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.6958e+06", "standardDeviation": "39631.8", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58773.6", "standardDeviation": "2011.49", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.42665e+06", "standardDeviation": "41585.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "135722", "standardDeviation": "1776.93", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "307666", "standardDeviation": "1361.52", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35755.1", "standardDeviation": "740.934", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "617300", "standardDeviation": "7532.85", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36322.3", "standardDeviation": "868.039", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23167e+06", "standardDeviation": "13232", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36081.3", "standardDeviation": "744.548", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.49319e+06", "standardDeviation": "152186", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39559.7", "standardDeviation": "3674.37", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.89255e+06", "standardDeviation": "1783.26", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131591", "standardDeviation": "3756.43", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..c2a9f25 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..e3a3798 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..c24c6a2 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..bfc04cc --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "143356", "standardDeviation": "2196.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "148901", "standardDeviation": "3907.51", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2513.45", "standardDeviation": "145.074", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "212068", "standardDeviation": "69777.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "296482", "standardDeviation": "7009.69", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3339.79", "standardDeviation": "230.132", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "404178", "standardDeviation": "8706.38", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "591611", "standardDeviation": "11764", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3241.73", "standardDeviation": "127.914", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "797069", "standardDeviation": "16752.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.20305e+06", "standardDeviation": "238909", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3085.89", "standardDeviation": "248.749", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57305e+06", "standardDeviation": "52526.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35428e+06", "standardDeviation": "20772.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3049.15", "standardDeviation": "324.127", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194386", "standardDeviation": "6228.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "184628", "standardDeviation": "4663.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2974.27", "standardDeviation": "111.584", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "337255", "standardDeviation": "20839", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "340406", "standardDeviation": "146021", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2962.3", "standardDeviation": "89.2468", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "680411", "standardDeviation": "73257", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "668505", "standardDeviation": "51130.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2890.02", "standardDeviation": "197.793", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.19326e+06", "standardDeviation": "174516", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.26565e+06", "standardDeviation": "141401", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2885.5", "standardDeviation": "102.308", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.83431e+06", "standardDeviation": "209712", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.95582e+06", "standardDeviation": "231539", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2943.21", "standardDeviation": "218.667", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..4d80857 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..6bfa2ca Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..e02d712 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..b8c034b --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "277448", "standardDeviation": "23408.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276451", "standardDeviation": "2679.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "539489", "standardDeviation": "4514.11", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279199", "standardDeviation": "2338.32", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05177e+06", "standardDeviation": "5766.83", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281952", "standardDeviation": "3304.19", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.07772e+06", "standardDeviation": "19990.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "289198", "standardDeviation": "2835.41", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.27074e+06", "standardDeviation": "57473.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "314832", "standardDeviation": "4931.51", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..4ea5695 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "318956", "standardDeviation": "4771.99", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48948.2", "standardDeviation": "1795.06", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "691493", "standardDeviation": "15027.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49394", "standardDeviation": "1572.62", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.38737e+06", "standardDeviation": "57708.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "52473.2", "standardDeviation": "16989.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.74938e+06", "standardDeviation": "75136.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50687.6", "standardDeviation": "1178.95", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.52774e+06", "standardDeviation": "106784", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139292", "standardDeviation": "15311.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309569", "standardDeviation": "2981.82", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36231.9", "standardDeviation": "961.583", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "617283", "standardDeviation": "4788.71", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37873.8", "standardDeviation": "724.403", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22983e+06", "standardDeviation": "7687.36", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37127.9", "standardDeviation": "8974", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47439e+06", "standardDeviation": "6495.59", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39608.4", "standardDeviation": "3790.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94691e+06", "standardDeviation": "20096.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131668", "standardDeviation": "3827.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..1b54b89 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98918.9", "standardDeviation": "2940.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147628", "standardDeviation": "3191.94", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2590.42", "standardDeviation": "566.522", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197548", "standardDeviation": "4365.11", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "301335", "standardDeviation": "63373.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2490.64", "standardDeviation": "143.846", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394546", "standardDeviation": "7612.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588693", "standardDeviation": "11402.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2458.04", "standardDeviation": "98.9621", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "787658", "standardDeviation": "19546.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17781e+06", "standardDeviation": "17767.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2802.65", "standardDeviation": "2644.95", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.55398e+06", "standardDeviation": "84754", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35981e+06", "standardDeviation": "20844.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2553.47", "standardDeviation": "142.635", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137952", "standardDeviation": "2118.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "144259", "standardDeviation": "62812", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2471.42", "standardDeviation": "84.3075", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "275023", "standardDeviation": "4266.17", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272932", "standardDeviation": "5760.72", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2468.34", "standardDeviation": "85.2866", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "547402", "standardDeviation": "4604.31", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "596741", "standardDeviation": "7866.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2488.89", "standardDeviation": "160.521", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.1399e+06", "standardDeviation": "296311", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.1817e+06", "standardDeviation": "13193.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2488.3", "standardDeviation": "175.974", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.31516e+06", "standardDeviation": "42725.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.05564e+06", "standardDeviation": "102307", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2563.63", "standardDeviation": "321.727", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..84171d6 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82249.5", "standardDeviation": "1877.77", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131337", "standardDeviation": "2515.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2686.9", "standardDeviation": "378.806", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169415", "standardDeviation": "51484.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263041", "standardDeviation": "5512.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2595.98", "standardDeviation": "139.033", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "328035", "standardDeviation": "6571.22", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524980", "standardDeviation": "11548.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2644.57", "standardDeviation": "199.329", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "660543", "standardDeviation": "13990.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.0495e+06", "standardDeviation": "21898.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2634.71", "standardDeviation": "136.266", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33191e+06", "standardDeviation": "24707", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09458e+06", "standardDeviation": "19311.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2670.86", "standardDeviation": "152.532", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113602", "standardDeviation": "2462.58", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135785", "standardDeviation": "2800.75", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2641.82", "standardDeviation": "109.082", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "218953", "standardDeviation": "4115.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272976", "standardDeviation": "53274.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2587.78", "standardDeviation": "89.9872", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "453749", "standardDeviation": "6553.94", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "534275", "standardDeviation": "9733.67", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2441.88", "standardDeviation": "93.8294", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "911109", "standardDeviation": "15092.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07448e+06", "standardDeviation": "40849.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2527.51", "standardDeviation": "286.138", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.33713e+06", "standardDeviation": "131034", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.54033e+06", "standardDeviation": "138321", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2559.73", "standardDeviation": "216.959", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/149720/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..1969d75 --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA H100 NVL, 95830 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..18f661b --- /dev/null +++ b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83302.9", "standardDeviation": "3314.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131854", "standardDeviation": "3057.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3033.52", "standardDeviation": "244.164", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168580", "standardDeviation": "3286.06", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "265249", "standardDeviation": "13538.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2581.24", "standardDeviation": "72.5224", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340582", "standardDeviation": "113637", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524281", "standardDeviation": "9711.47", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2549.37", "standardDeviation": "89.3871", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "659456", "standardDeviation": "11776.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04928e+06", "standardDeviation": "17991.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2604.8", "standardDeviation": "147.809", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32142e+06", "standardDeviation": "17889.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09611e+06", "standardDeviation": "20074.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2678.18", "standardDeviation": "152.608", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "124631", "standardDeviation": "2661.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139435", "standardDeviation": "2793.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2604.2", "standardDeviation": "88.9692", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "232333", "standardDeviation": "2284.04", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "280757", "standardDeviation": "107668", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2619.45", "standardDeviation": "95.716", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "487461", "standardDeviation": "8473.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536088", "standardDeviation": "8899.69", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2717.14", "standardDeviation": "1850.88", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01022e+06", "standardDeviation": "12918.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06345e+06", "standardDeviation": "13399.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2566.32", "standardDeviation": "155.474", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.43643e+06", "standardDeviation": "53416.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.61435e+06", "standardDeviation": "54778.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2543.93", "standardDeviation": "223.839", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..9ef0186 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..45c112a Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..df9ad04 Binary files /dev/null and b/149720/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/divOperator.json b/151570/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..2b0fb9d --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "211188", "standardDeviation": "2579.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "540992", "standardDeviation": "25730.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "477440", "standardDeviation": "4195.45", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "548532", "standardDeviation": "19085", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "942767", "standardDeviation": "7087.86", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "713535", "standardDeviation": "24665.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.20978e+06", "standardDeviation": "22981.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "664630", "standardDeviation": "28348.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.97716e+06", "standardDeviation": "95632.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "706580", "standardDeviation": "21702", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151570/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..feb88bf Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151570/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..015716c Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151570/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..59dab09 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/field.json b/151570/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..25a4ece --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "95197.2", "standardDeviation": "2537.73", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "76196.6", "standardDeviation": "10149.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "134208", "standardDeviation": "1197.75", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "74153.3", "standardDeviation": "8386.15", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "383676", "standardDeviation": "1476.11", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "105152", "standardDeviation": "7122.41", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "764248", "standardDeviation": "1325.23", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117230", "standardDeviation": "7642.09", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.52457e+06", "standardDeviation": "1646.83", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "141024", "standardDeviation": "3132.84", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48183", "standardDeviation": "3381.13", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "56282.2", "standardDeviation": "10455.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "138629", "standardDeviation": "1568.35", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60375.2", "standardDeviation": "9280.49", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "387624", "standardDeviation": "1810.25", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "91426.3", "standardDeviation": "9867", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "775798", "standardDeviation": "1673.66", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103291", "standardDeviation": "7974.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54924e+06", "standardDeviation": "5010.28", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128655", "standardDeviation": "4609.92", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151570/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..beccf7a Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/field_relative.png b/151570/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..213490c Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/field_time.png b/151570/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..91486d2 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/linear.json b/151570/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..3e1d702 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39939.5", "standardDeviation": "1297.06", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51832.8", "standardDeviation": "808.618", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1418.71", "standardDeviation": "1147.53", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "139892", "standardDeviation": "3354.62", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "142497", "standardDeviation": "3074.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1442.5", "standardDeviation": "1484.58", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "286454", "standardDeviation": "10848.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "260646", "standardDeviation": "1310.49", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1428.01", "standardDeviation": "2089.69", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "516004", "standardDeviation": "2169.45", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "533366", "standardDeviation": "22694.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1623.2", "standardDeviation": "2361.14", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.04636e+06", "standardDeviation": "16781.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.06772e+06", "standardDeviation": "56338.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1564.34", "standardDeviation": "1702.06", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "133920", "standardDeviation": "3164.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "142734", "standardDeviation": "2619.96", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1395.98", "standardDeviation": "1320.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "259884", "standardDeviation": "1363.61", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "277584", "standardDeviation": "9915.73", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1433.64", "standardDeviation": "1220.75", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "519080", "standardDeviation": "5109.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "543279", "standardDeviation": "20196.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1636.74", "standardDeviation": "2192.84", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.06012e+06", "standardDeviation": "48388.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06105e+06", "standardDeviation": "16431.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2987.36", "standardDeviation": "4760.17", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.39504e+06", "standardDeviation": "109558", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.60265e+06", "standardDeviation": "81358.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1797.14", "standardDeviation": "2941.69", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151570/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..2783771 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151570/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..4e11ddc Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/linear_time.png b/151570/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..ec57753 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151570/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..a5f6c22 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "217498", "standardDeviation": "3523.97", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "545350", "standardDeviation": "32460.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "461544", "standardDeviation": "15825.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "551181", "standardDeviation": "26525.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "897753", "standardDeviation": "37041.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "635448", "standardDeviation": "38167.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79337e+06", "standardDeviation": "320943", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "758428", "standardDeviation": "31242.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.94897e+06", "standardDeviation": "56000.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "684362", "standardDeviation": "7503.63", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/main/field.json b/151570/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..7528b64 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "46558.7", "standardDeviation": "5874.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72844.1", "standardDeviation": "10395.6", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "132849", "standardDeviation": "1991.35", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78134.9", "standardDeviation": "10352.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "435947", "standardDeviation": "31991.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "112791", "standardDeviation": "15770.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "763897", "standardDeviation": "53538.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128393", "standardDeviation": "44858.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.46724e+06", "standardDeviation": "96358.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151089", "standardDeviation": "47399.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "45567.9", "standardDeviation": "2090.68", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "56579.2", "standardDeviation": "9405.69", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "146681", "standardDeviation": "2466.32", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59923", "standardDeviation": "8939.49", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "409491", "standardDeviation": "22051.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89250.6", "standardDeviation": "3176.28", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "732492", "standardDeviation": "32811.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133533", "standardDeviation": "222972", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.48366e+06", "standardDeviation": "126138", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "141414", "standardDeviation": "53539.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/main/linear.json b/151570/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..1b1dc35 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49173", "standardDeviation": "5048.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51372.1", "standardDeviation": "858.039", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1474.99", "standardDeviation": "1220.52", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155825", "standardDeviation": "3142.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "166123", "standardDeviation": "3588.98", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1512.44", "standardDeviation": "1812.42", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "337886", "standardDeviation": "98449.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304700", "standardDeviation": "12174.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1479.83", "standardDeviation": "1422.59", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "620698", "standardDeviation": "54846.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "624256", "standardDeviation": "55726.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3009.55", "standardDeviation": "4430.62", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24656e+06", "standardDeviation": "212384", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.23269e+06", "standardDeviation": "209001", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1672.88", "standardDeviation": "2878.82", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "209566", "standardDeviation": "7247.35", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "213042", "standardDeviation": "28868", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1588.78", "standardDeviation": "1453.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "397152", "standardDeviation": "26410", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "393527", "standardDeviation": "27884.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1747.43", "standardDeviation": "2072.71", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "721681", "standardDeviation": "83345.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "718085", "standardDeviation": "82479", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2023.8", "standardDeviation": "3454.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.26519e+06", "standardDeviation": "211460", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28611e+06", "standardDeviation": "210554", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2007.79", "standardDeviation": "3285.85", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.66092e+06", "standardDeviation": "301475", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.67681e+06", "standardDeviation": "282085", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1624.01", "standardDeviation": "1308.98", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151570/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..410c6dd --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34439", "standardDeviation": "2126.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "43301.7", "standardDeviation": "572.076", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1555.01", "standardDeviation": "1102.11", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122787", "standardDeviation": "1174.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "129972", "standardDeviation": "1322.51", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1514.4", "standardDeviation": "1207.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "299648", "standardDeviation": "16618", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "269496", "standardDeviation": "13292.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2934.22", "standardDeviation": "6554.98", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "404274", "standardDeviation": "8814.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "556323", "standardDeviation": "59765.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1776.03", "standardDeviation": "2898.68", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "861804", "standardDeviation": "77971", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "876185", "standardDeviation": "114462", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1686.08", "standardDeviation": "2157.04", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "140661", "standardDeviation": "3152.85", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "151834", "standardDeviation": "3873.94", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1573.2", "standardDeviation": "1488.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "303385", "standardDeviation": "10969.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "305220", "standardDeviation": "16208.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1641.06", "standardDeviation": "1486.12", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "538697", "standardDeviation": "32961.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "590827", "standardDeviation": "59872", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1725.24", "standardDeviation": "2338.43", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.06848e+06", "standardDeviation": "114375", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.01842e+06", "standardDeviation": "102555", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1747.9", "standardDeviation": "2279.38", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.4292e+06", "standardDeviation": "142960", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.20781e+06", "standardDeviation": "163728", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1973.98", "standardDeviation": "3334.86", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/system-info.log b/151570/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151570/neon-cluster-meta-runner-neon-amd/upwind.json b/151570/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..8e0e1c3 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49433.8", "standardDeviation": "887.51", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44676.4", "standardDeviation": "989.678", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1448.26", "standardDeviation": "1073.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "120105", "standardDeviation": "3082.13", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "123841", "standardDeviation": "2346.53", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1477.92", "standardDeviation": "1304.25", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "229274", "standardDeviation": "1606.15", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "232316", "standardDeviation": "1416.94", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1502.26", "standardDeviation": "1493.53", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "481472", "standardDeviation": "25533.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "469248", "standardDeviation": "45446", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1638.77", "standardDeviation": "2312.24", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "967810", "standardDeviation": "90345.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "928805", "standardDeviation": "24362.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1616.2", "standardDeviation": "2074.34", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "146220", "standardDeviation": "3079.94", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "144220", "standardDeviation": "1995.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1499.67", "standardDeviation": "1399.73", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "266223", "standardDeviation": "4933.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "259113", "standardDeviation": "6443.74", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1451.28", "standardDeviation": "1172.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "529900", "standardDeviation": "11779.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "508217", "standardDeviation": "1859.04", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1465.01", "standardDeviation": "1941.91", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.06202e+06", "standardDeviation": "49286.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.00886e+06", "standardDeviation": "2154.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1394.17", "standardDeviation": "1557.07", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.47538e+06", "standardDeviation": "102965", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.39954e+06", "standardDeviation": "90523", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1568.32", "standardDeviation": "1912.95", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151570/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..3e3d887 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151570/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..7f053f2 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151570/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..74a9ead Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..83361ea --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "273987", "standardDeviation": "3952.71", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276331", "standardDeviation": "3970.45", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "541128", "standardDeviation": "5333.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279938", "standardDeviation": "4173.24", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05534e+06", "standardDeviation": "8256.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281928", "standardDeviation": "3610.44", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.05701e+06", "standardDeviation": "12030.7", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "288639", "standardDeviation": "3707.88", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.33209e+06", "standardDeviation": "140382", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "313565", "standardDeviation": "3618.05", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..b4860bb Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..1cd4119 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..e656eee Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..7a7a44b --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306882", "standardDeviation": "1673.42", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40323.4", "standardDeviation": "1666.94", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "634764", "standardDeviation": "1789.52", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46781.5", "standardDeviation": "3075.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29078e+06", "standardDeviation": "1807.07", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48561.9", "standardDeviation": "895.107", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.58305e+06", "standardDeviation": "10163.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48758.1", "standardDeviation": "1138.65", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.21378e+06", "standardDeviation": "390407", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161822", "standardDeviation": "2743.42", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "451950", "standardDeviation": "1930.24", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35802.8", "standardDeviation": "1639.76", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "617194", "standardDeviation": "5544.57", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35505.9", "standardDeviation": "708.034", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23066e+06", "standardDeviation": "8733.76", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35674.6", "standardDeviation": "717.507", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47604e+06", "standardDeviation": "6473.17", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40357.5", "standardDeviation": "3981.47", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94839e+06", "standardDeviation": "3621.86", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131879", "standardDeviation": "4061.67", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..3f7f07c Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..fbdb64d Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..6f5d4b6 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..944ca32 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98460.9", "standardDeviation": "2260.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147486", "standardDeviation": "3095.27", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2543.21", "standardDeviation": "140.56", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197664", "standardDeviation": "4555.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "294937", "standardDeviation": "6296.26", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2652.39", "standardDeviation": "186.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "399292", "standardDeviation": "17102.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589381", "standardDeviation": "10684.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2596.24", "standardDeviation": "170.478", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "788745", "standardDeviation": "18230.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17701e+06", "standardDeviation": "15474.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2554.99", "standardDeviation": "97.541", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57952e+06", "standardDeviation": "38364.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.36126e+06", "standardDeviation": "37704.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2498.56", "standardDeviation": "113.681", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129106", "standardDeviation": "2337.85", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136844", "standardDeviation": "2993.13", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2509.47", "standardDeviation": "137.43", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "258496", "standardDeviation": "4276.33", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "270313", "standardDeviation": "5419.25", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2531.21", "standardDeviation": "77.3831", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "529633", "standardDeviation": "82207.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "562955", "standardDeviation": "7868.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2569.42", "standardDeviation": "213.063", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.02315e+06", "standardDeviation": "23141.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12679e+06", "standardDeviation": "16610.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2532.58", "standardDeviation": "351.12", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.9057e+06", "standardDeviation": "72656.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.96178e+06", "standardDeviation": "81971.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2527.03", "standardDeviation": "163.568", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..9601bba Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..2dc09c5 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..c0808c2 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..9371b7e --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "274706", "standardDeviation": "6445.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278034", "standardDeviation": "4331.77", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540187", "standardDeviation": "9308.39", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281532", "standardDeviation": "5169.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05298e+06", "standardDeviation": "8612.46", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285023", "standardDeviation": "5248.71", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.07445e+06", "standardDeviation": "24314.1", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291393", "standardDeviation": "4311.57", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.30519e+06", "standardDeviation": "55070.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "315570", "standardDeviation": "5043.39", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..de156a5 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306546", "standardDeviation": "1628.03", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41015.4", "standardDeviation": "2159.81", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "634631", "standardDeviation": "1774.89", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42465.1", "standardDeviation": "1292.81", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "898227", "standardDeviation": "26376.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42463.3", "standardDeviation": "1213.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79707e+06", "standardDeviation": "50026", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43622.5", "standardDeviation": "762.418", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.6018e+06", "standardDeviation": "58633.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137648", "standardDeviation": "16931.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309270", "standardDeviation": "2762.73", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36466.1", "standardDeviation": "868.564", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616034", "standardDeviation": "4271.44", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36707.4", "standardDeviation": "1817.9", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22975e+06", "standardDeviation": "7243.77", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37400.4", "standardDeviation": "8831.05", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47462e+06", "standardDeviation": "6133.48", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40394.4", "standardDeviation": "3996.16", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.96103e+06", "standardDeviation": "32480.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130017", "standardDeviation": "3985.25", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..468808d --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "143215", "standardDeviation": "5454.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "148137", "standardDeviation": "3456.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2572.59", "standardDeviation": "152.266", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "204864", "standardDeviation": "65339.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295732", "standardDeviation": "7251.33", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2570.61", "standardDeviation": "104.585", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "396303", "standardDeviation": "8058.41", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589439", "standardDeviation": "11036.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2585.64", "standardDeviation": "151.957", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "784706", "standardDeviation": "26961.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17859e+06", "standardDeviation": "18823.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2594.61", "standardDeviation": "308.072", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56797e+06", "standardDeviation": "55493.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35702e+06", "standardDeviation": "26650", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2577.46", "standardDeviation": "195.998", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138482", "standardDeviation": "2006.27", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "149989", "standardDeviation": "2644.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2479.73", "standardDeviation": "121.518", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "245727", "standardDeviation": "3908.01", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "274508", "standardDeviation": "6024.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2509.36", "standardDeviation": "98.5799", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "558325", "standardDeviation": "6406.26", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "596079", "standardDeviation": "7387.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2495.14", "standardDeviation": "112.907", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.1277e+06", "standardDeviation": "181879", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18393e+06", "standardDeviation": "34350.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2482.5", "standardDeviation": "114.425", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.02471e+06", "standardDeviation": "282797", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.97727e+06", "standardDeviation": "27353.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2426.48", "standardDeviation": "216.601", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..d0f78c3 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "81333.9", "standardDeviation": "1076.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130128", "standardDeviation": "1649.08", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2600.36", "standardDeviation": "117.753", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168279", "standardDeviation": "55740.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "259619", "standardDeviation": "1219.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2607.94", "standardDeviation": "81.5976", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "326024", "standardDeviation": "1352.97", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525693", "standardDeviation": "12039.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2549.75", "standardDeviation": "147.183", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "666058", "standardDeviation": "45768.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05416e+06", "standardDeviation": "54912.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2568.9", "standardDeviation": "143.67", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.31774e+06", "standardDeviation": "44940.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09974e+06", "standardDeviation": "21220.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2593.49", "standardDeviation": "90.3309", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113788", "standardDeviation": "5316.21", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "133830", "standardDeviation": "2882.3", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2551.26", "standardDeviation": "176.379", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "225988", "standardDeviation": "3964.52", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "281017", "standardDeviation": "130045", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2507.06", "standardDeviation": "89.4782", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "452532", "standardDeviation": "8427.62", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "549165", "standardDeviation": "73819.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2530.46", "standardDeviation": "117.059", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "914842", "standardDeviation": "16393.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07086e+06", "standardDeviation": "20432.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2519.54", "standardDeviation": "208.759", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.58209e+06", "standardDeviation": "150876", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.80352e+06", "standardDeviation": "88410.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2656.37", "standardDeviation": "818.297", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151570/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..5181276 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,63 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +name, memory.total [MiB], driver_version +NVIDIA H100 NVL, 95830 MiB, 575.51.03 + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..9c93144 --- /dev/null +++ b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82345.3", "standardDeviation": "2775.57", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131308", "standardDeviation": "2809.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2623.11", "standardDeviation": "116.165", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164238", "standardDeviation": "3379.66", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262563", "standardDeviation": "5534.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2612.82", "standardDeviation": "126.703", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340591", "standardDeviation": "117026", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "520584", "standardDeviation": "5436.79", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2580.06", "standardDeviation": "113.622", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "664520", "standardDeviation": "49946.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04872e+06", "standardDeviation": "18051.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2638.82", "standardDeviation": "172.688", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33204e+06", "standardDeviation": "51139", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09522e+06", "standardDeviation": "19405.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2556.22", "standardDeviation": "274.261", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "112855", "standardDeviation": "2807.36", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141861", "standardDeviation": "63590.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2532.47", "standardDeviation": "156.406", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "228289", "standardDeviation": "16110.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "267155", "standardDeviation": "5217.51", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2631.23", "standardDeviation": "206.758", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "458533", "standardDeviation": "32302.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "538809", "standardDeviation": "10111.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2471.41", "standardDeviation": "119.381", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "933140", "standardDeviation": "113742", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08144e+06", "standardDeviation": "16570.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2652.34", "standardDeviation": "351.559", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.59139e+06", "standardDeviation": "74405", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.61091e+06", "standardDeviation": "103775", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2463.07", "standardDeviation": "227.034", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..b4a7787 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..2c17381 Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..79de70a Binary files /dev/null and b/151570/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/divOperator.json b/151609/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..6d04c4a --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "248960", "standardDeviation": "6174.28", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "567735", "standardDeviation": "25768.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "542430", "standardDeviation": "38606.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "577668", "standardDeviation": "32074.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "983033", "standardDeviation": "105292", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "659692", "standardDeviation": "32350", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83271e+06", "standardDeviation": "189855", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "687569", "standardDeviation": "28752.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.77732e+06", "standardDeviation": "264510", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "736467", "standardDeviation": "33758.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151609/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..5457d15 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151609/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..a266a3c Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151609/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..e583d1b Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/field.json b/151609/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..f721162 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100834", "standardDeviation": "31631.7", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93591.4", "standardDeviation": "9294.36", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "144035", "standardDeviation": "3162.41", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "86031.4", "standardDeviation": "8858.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "474080", "standardDeviation": "40132.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123118", "standardDeviation": "9311.81", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "854169", "standardDeviation": "111409", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "135389", "standardDeviation": "11664.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.44716e+06", "standardDeviation": "69186.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "157868", "standardDeviation": "9257.19", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47811.8", "standardDeviation": "2664.08", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61065.2", "standardDeviation": "9106.46", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "123600", "standardDeviation": "6619.04", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63242.3", "standardDeviation": "9866.26", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "379991", "standardDeviation": "14507.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104406", "standardDeviation": "10704.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "749297", "standardDeviation": "48762.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "116141", "standardDeviation": "9440.22", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50349e+06", "standardDeviation": "149821", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137012", "standardDeviation": "7363.65", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151609/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..d009983 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/field_relative.png b/151609/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..d929ae3 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/field_time.png b/151609/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..340687b Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/linear.json b/151609/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..40c5322 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44048.1", "standardDeviation": "3057.89", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52730.5", "standardDeviation": "2408.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1647.48", "standardDeviation": "1470.61", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163428", "standardDeviation": "4967.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "167265", "standardDeviation": "5510.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2234.64", "standardDeviation": "4799.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "309936", "standardDeviation": "17191.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "315295", "standardDeviation": "18444", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1697.3", "standardDeviation": "1764.07", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "573052", "standardDeviation": "57457.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "577157", "standardDeviation": "80365.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2010.71", "standardDeviation": "3023.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.03978e+06", "standardDeviation": "163510", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.02501e+06", "standardDeviation": "143337", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1814.49", "standardDeviation": "2455.29", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "160273", "standardDeviation": "5103.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "163510", "standardDeviation": "5501.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1598.67", "standardDeviation": "1664.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "308060", "standardDeviation": "17685.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "310607", "standardDeviation": "18813.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1606.87", "standardDeviation": "2106.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "566550", "standardDeviation": "55770.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "571482", "standardDeviation": "60784.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2325.43", "standardDeviation": "5162.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03801e+06", "standardDeviation": "120191", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.02701e+06", "standardDeviation": "136456", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1828.93", "standardDeviation": "2190.16", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.47211e+06", "standardDeviation": "218115", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.49718e+06", "standardDeviation": "214182", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2008.31", "standardDeviation": "2883.15", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151609/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..7698f64 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151609/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..7664b03 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/linear_time.png b/151609/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..a890e22 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151609/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..913a396 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "239017", "standardDeviation": "5350.51", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "563519", "standardDeviation": "34109.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "501545", "standardDeviation": "32509.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "571459", "standardDeviation": "35476.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "923516", "standardDeviation": "238792", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "648579", "standardDeviation": "32049.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.78645e+06", "standardDeviation": "137197", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "680365", "standardDeviation": "29680.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.81268e+06", "standardDeviation": "264529", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "725012", "standardDeviation": "33416.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/main/field.json b/151609/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..69b5c53 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50089.6", "standardDeviation": "2026.8", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "74630.5", "standardDeviation": "9176.4", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "162451", "standardDeviation": "6023.71", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "79636.4", "standardDeviation": "8458.77", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "474656", "standardDeviation": "40684.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111178", "standardDeviation": "8863.68", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "856053", "standardDeviation": "112559", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121232", "standardDeviation": "23742.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.5544e+06", "standardDeviation": "218164", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149621", "standardDeviation": "52675.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48095.2", "standardDeviation": "1639.38", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59720.7", "standardDeviation": "9833.46", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "163605", "standardDeviation": "5391.67", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62915.6", "standardDeviation": "9808.84", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "484807", "standardDeviation": "42362.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92688.4", "standardDeviation": "15114.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "867999", "standardDeviation": "118761", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "106471", "standardDeviation": "23032.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55658e+06", "standardDeviation": "224954", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132865", "standardDeviation": "20494.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/main/linear.json b/151609/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..7d9be56 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50266.6", "standardDeviation": "784.284", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51063.1", "standardDeviation": "2584.45", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1789.25", "standardDeviation": "1499.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166375", "standardDeviation": "5818.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "161700", "standardDeviation": "5774.22", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1900.38", "standardDeviation": "3163.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "307867", "standardDeviation": "17575.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "310966", "standardDeviation": "18118.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1713.47", "standardDeviation": "2254.69", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "562144", "standardDeviation": "56337.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "570299", "standardDeviation": "93776.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1945.37", "standardDeviation": "3181.68", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.03136e+06", "standardDeviation": "169772", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.02227e+06", "standardDeviation": "139633", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1855.1", "standardDeviation": "2369.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "160536", "standardDeviation": "4715.41", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "161927", "standardDeviation": "5340.73", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1671.11", "standardDeviation": "1965.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "305347", "standardDeviation": "18134.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "308498", "standardDeviation": "17998.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1650.12", "standardDeviation": "1726.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "564442", "standardDeviation": "55360.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "560608", "standardDeviation": "59572.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1917.14", "standardDeviation": "2859.58", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03989e+06", "standardDeviation": "121148", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.02919e+06", "standardDeviation": "135920", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1716.85", "standardDeviation": "2339.87", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.3221e+06", "standardDeviation": "219579", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.44381e+06", "standardDeviation": "238727", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1975.14", "standardDeviation": "2591.91", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151609/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..e12125c --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "36641.3", "standardDeviation": "5822.03", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45299.4", "standardDeviation": "2260.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1689.12", "standardDeviation": "1352.53", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "145881", "standardDeviation": "2724.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "146223", "standardDeviation": "2966.59", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1659.75", "standardDeviation": "1231.58", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "277733", "standardDeviation": "15355.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "279969", "standardDeviation": "15061.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1722.16", "standardDeviation": "1676.78", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "515656", "standardDeviation": "60457.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "515471", "standardDeviation": "49998.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1807.15", "standardDeviation": "2736.48", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "926544", "standardDeviation": "119592", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "923601", "standardDeviation": "129887", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1890.36", "standardDeviation": "2523.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "165944", "standardDeviation": "3930.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159228", "standardDeviation": "4650.31", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1726.96", "standardDeviation": "1791.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "318980", "standardDeviation": "15465.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "330333", "standardDeviation": "178264", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1682.34", "standardDeviation": "1598.27", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "580015", "standardDeviation": "47393.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "557242", "standardDeviation": "50772.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1819.88", "standardDeviation": "2644.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07644e+06", "standardDeviation": "124581", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.02483e+06", "standardDeviation": "117553", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1845.15", "standardDeviation": "2391.91", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.3177e+06", "standardDeviation": "226902", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.61527e+06", "standardDeviation": "194010", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1924.63", "standardDeviation": "2946.11", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/system-info.log b/151609/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..c793604 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 3 +GPU[0] : GUID: 42924 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151609/neon-cluster-meta-runner-neon-amd/upwind.json b/151609/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..3cf2e6f --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33420.9", "standardDeviation": "2743.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44256.5", "standardDeviation": "2383.94", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1674.03", "standardDeviation": "1298.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "158442", "standardDeviation": "3957.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "160794", "standardDeviation": "4585.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1954.17", "standardDeviation": "3302.65", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "305299", "standardDeviation": "16429.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304255", "standardDeviation": "18372.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1745.74", "standardDeviation": "1924.59", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "560841", "standardDeviation": "57395.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "565218", "standardDeviation": "80197", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1893.44", "standardDeviation": "2742.61", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "882792", "standardDeviation": "92089.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "984929", "standardDeviation": "169538", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1836.66", "standardDeviation": "2566.35", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177189", "standardDeviation": "5128.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "171220", "standardDeviation": "5673.23", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1717.57", "standardDeviation": "1775.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "337633", "standardDeviation": "19247.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "334501", "standardDeviation": "18743.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1694.39", "standardDeviation": "1581.02", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "632105", "standardDeviation": "59257.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "608369", "standardDeviation": "62487.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2176.69", "standardDeviation": "7228.62", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11934e+06", "standardDeviation": "159308", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08219e+06", "standardDeviation": "159824", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1866.33", "standardDeviation": "2352.94", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.71377e+06", "standardDeviation": "227511", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.23401e+06", "standardDeviation": "252838", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1953.36", "standardDeviation": "2729.92", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151609/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..8728b4d Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151609/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..9f71c9f Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151609/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..5684db7 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..ec6a092 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "270801", "standardDeviation": "3093.36", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "289299", "standardDeviation": "15572.9", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "531573", "standardDeviation": "5812.34", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284310", "standardDeviation": "21396.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.02142e+06", "standardDeviation": "8561.94", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291249", "standardDeviation": "3268.72", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.01105e+06", "standardDeviation": "19079.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "290790", "standardDeviation": "3516.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.26034e+06", "standardDeviation": "87509.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "316994", "standardDeviation": "3510.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..516234b Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..2f0809f Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..e8ff264 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..4a00a7a --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "305620", "standardDeviation": "1816.26", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41428.1", "standardDeviation": "2488.66", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "509975", "standardDeviation": "94359", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42463.8", "standardDeviation": "1121.83", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "893294", "standardDeviation": "5696.89", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43244.3", "standardDeviation": "760.151", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.78819e+06", "standardDeviation": "19405.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43579.2", "standardDeviation": "830.419", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.58499e+06", "standardDeviation": "15412", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131326", "standardDeviation": "14363", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309256", "standardDeviation": "2877.43", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36204.5", "standardDeviation": "1169.89", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616445", "standardDeviation": "4632.93", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36263.9", "standardDeviation": "983.463", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22955e+06", "standardDeviation": "7826.75", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37005.9", "standardDeviation": "10355.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47605e+06", "standardDeviation": "7091.92", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41630", "standardDeviation": "3457.85", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94531e+06", "standardDeviation": "2657.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124380", "standardDeviation": "3809.17", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..8c6557f Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..a658d3d Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..a7609d2 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..ae10935 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98486.5", "standardDeviation": "2135.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "146802", "standardDeviation": "1833.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2506.87", "standardDeviation": "500.004", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196652", "standardDeviation": "3952.04", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "296517", "standardDeviation": "43542.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2454.68", "standardDeviation": "137.693", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "393824", "standardDeviation": "7192.86", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "583814", "standardDeviation": "5371.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2480.45", "standardDeviation": "87.9944", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "786714", "standardDeviation": "15596.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17639e+06", "standardDeviation": "13239.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2718.25", "standardDeviation": "2166.51", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.54721e+06", "standardDeviation": "53131.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35002e+06", "standardDeviation": "10961.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2473.01", "standardDeviation": "139.744", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121067", "standardDeviation": "2558.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135978", "standardDeviation": "2788.29", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2401.9", "standardDeviation": "101.895", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "238078", "standardDeviation": "3956.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "273593", "standardDeviation": "4497.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2407.12", "standardDeviation": "85.6361", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "502778", "standardDeviation": "2893.54", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "537398", "standardDeviation": "6451.36", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2492.86", "standardDeviation": "107.144", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "980909", "standardDeviation": "9717.64", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08878e+06", "standardDeviation": "10582.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2474.55", "standardDeviation": "332.431", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.63461e+06", "standardDeviation": "16246.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.83136e+06", "standardDeviation": "17990.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2403.32", "standardDeviation": "138.587", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..a1f42e8 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..a2159ca Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..0ba7733 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..068b43a --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "272837", "standardDeviation": "2836.47", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280649", "standardDeviation": "3300.29", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "531945", "standardDeviation": "4834.88", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "283492", "standardDeviation": "3238.12", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03224e+06", "standardDeviation": "6635", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285991", "standardDeviation": "3255.58", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.02278e+06", "standardDeviation": "17393.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "292299", "standardDeviation": "3335.28", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.27409e+06", "standardDeviation": "73946.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "320638", "standardDeviation": "24669.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..78cb3e3 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306043", "standardDeviation": "2185.27", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40941.4", "standardDeviation": "1711.34", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "635025", "standardDeviation": "2059.51", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48074.7", "standardDeviation": "2363.04", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.1474e+06", "standardDeviation": "187973", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43506.1", "standardDeviation": "956.474", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.77757e+06", "standardDeviation": "2263.57", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43910.1", "standardDeviation": "1065.59", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.54698e+06", "standardDeviation": "2788.33", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131553", "standardDeviation": "15000.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309456", "standardDeviation": "2899.11", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36003.5", "standardDeviation": "716.698", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616263", "standardDeviation": "4511.1", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36080.4", "standardDeviation": "800.682", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22934e+06", "standardDeviation": "7145.19", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37005.6", "standardDeviation": "9575.92", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47374e+06", "standardDeviation": "7559.97", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41475.3", "standardDeviation": "3587.54", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94288e+06", "standardDeviation": "7050.54", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123634", "standardDeviation": "3706.12", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..0ab0dc1 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98766", "standardDeviation": "2297.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147592", "standardDeviation": "3258.13", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2562.9", "standardDeviation": "125.283", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197891", "standardDeviation": "4267.48", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295159", "standardDeviation": "6033.14", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2518.29", "standardDeviation": "100.472", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "408995", "standardDeviation": "129397", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588800", "standardDeviation": "10976.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2485.45", "standardDeviation": "101.505", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "781404", "standardDeviation": "28346", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17836e+06", "standardDeviation": "17462.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2485.14", "standardDeviation": "219.832", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56357e+06", "standardDeviation": "52509.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35355e+06", "standardDeviation": "20554.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2505.53", "standardDeviation": "185.71", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130478", "standardDeviation": "2988.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "143898", "standardDeviation": "59423.8", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2511.74", "standardDeviation": "107.15", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "249573", "standardDeviation": "3094.07", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "276103", "standardDeviation": "5837.19", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2498.42", "standardDeviation": "90.6343", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "493895", "standardDeviation": "8971.95", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "548600", "standardDeviation": "10107.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2501.65", "standardDeviation": "377.391", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03379e+06", "standardDeviation": "258440", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11508e+06", "standardDeviation": "16838.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2428.06", "standardDeviation": "112.121", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.0506e+06", "standardDeviation": "188692", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.82095e+06", "standardDeviation": "96257.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.05", "standardDeviation": "142.243", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..f0807e7 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82524.5", "standardDeviation": "2264.85", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "132799", "standardDeviation": "3375.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2641.38", "standardDeviation": "94.6628", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164799", "standardDeviation": "3811.19", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263323", "standardDeviation": "5779.85", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2584.04", "standardDeviation": "116.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340077", "standardDeviation": "115462", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524800", "standardDeviation": "9887.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2616.91", "standardDeviation": "117.389", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "657554", "standardDeviation": "11486.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04794e+06", "standardDeviation": "16533.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2563.93", "standardDeviation": "121.261", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32035e+06", "standardDeviation": "18045.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09901e+06", "standardDeviation": "36685.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2593.2", "standardDeviation": "242.01", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113286", "standardDeviation": "3286.26", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "134391", "standardDeviation": "3329.26", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2620.46", "standardDeviation": "183.607", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "217772", "standardDeviation": "4308.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "266790", "standardDeviation": "5560.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2616.86", "standardDeviation": "115.379", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "451410", "standardDeviation": "7181.13", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536046", "standardDeviation": "9465.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2597.05", "standardDeviation": "114.295", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "925995", "standardDeviation": "12403.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07232e+06", "standardDeviation": "17879.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2550.26", "standardDeviation": "182.132", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.23689e+06", "standardDeviation": "44783.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.58709e+06", "standardDeviation": "134672", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2603.03", "standardDeviation": "548.706", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151609/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..d1f1c56 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Tue Sep 23 13:47:55 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:61:00.0 Off | 0 | +| N/A 29C P0 59W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..7dba333 --- /dev/null +++ b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82232.8", "standardDeviation": "2264.51", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131717", "standardDeviation": "2868.13", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2661.55", "standardDeviation": "159.275", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164125", "standardDeviation": "3178.98", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262626", "standardDeviation": "5137.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2652.28", "standardDeviation": "70.6148", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "339905", "standardDeviation": "112635", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "523851", "standardDeviation": "9771.76", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2646", "standardDeviation": "101.663", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "657245", "standardDeviation": "11235.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04855e+06", "standardDeviation": "15858.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2572.5", "standardDeviation": "71.319", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.31267e+06", "standardDeviation": "14527.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09519e+06", "standardDeviation": "20172.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2605.36", "standardDeviation": "291.865", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115313", "standardDeviation": "2422.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "132777", "standardDeviation": "2230.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2546.84", "standardDeviation": "127.625", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "214272", "standardDeviation": "4483.35", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "265489", "standardDeviation": "5490.59", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2505.64", "standardDeviation": "82.9276", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "440438", "standardDeviation": "8280.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "530992", "standardDeviation": "9981.36", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2544.81", "standardDeviation": "155.774", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "873718", "standardDeviation": "14116.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.05879e+06", "standardDeviation": "14814.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2511.55", "standardDeviation": "102.206", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.29652e+06", "standardDeviation": "24268.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.80672e+06", "standardDeviation": "38351.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2530.06", "standardDeviation": "209.51", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..18a39c1 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..1eaf80b Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..210b3f8 Binary files /dev/null and b/151609/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/divOperator.json b/151643/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..1d53928 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "280268", "standardDeviation": "9028.15", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "567218", "standardDeviation": "26923.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "608331", "standardDeviation": "119507", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "576043", "standardDeviation": "33586.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.01873e+06", "standardDeviation": "96147", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "664047", "standardDeviation": "30629.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98382e+06", "standardDeviation": "243158", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "685035", "standardDeviation": "28918.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.70983e+06", "standardDeviation": "154745", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "719574", "standardDeviation": "27206.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151643/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..2652891 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151643/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..cbc1779 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151643/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..e99c72d Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/field.json b/151643/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..3472c8b --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "104970", "standardDeviation": "7181.59", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93640.4", "standardDeviation": "9622.64", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "188236", "standardDeviation": "5468.55", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85029.5", "standardDeviation": "13043.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547121", "standardDeviation": "51630.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121486", "standardDeviation": "9409.09", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "968099", "standardDeviation": "148994", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "136893", "standardDeviation": "40615.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72501e+06", "standardDeviation": "290479", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161192", "standardDeviation": "56696.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "56149.7", "standardDeviation": "2668.23", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62173", "standardDeviation": "9894.92", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "189495", "standardDeviation": "5679.91", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63946.3", "standardDeviation": "9720.8", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "554248", "standardDeviation": "53015.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103494", "standardDeviation": "8915.01", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "978282", "standardDeviation": "150118", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118887", "standardDeviation": "31102.7", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.75142e+06", "standardDeviation": "294211", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144596", "standardDeviation": "35902", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151643/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..4ea84ce Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/field_relative.png b/151643/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..592bd32 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/field_time.png b/151643/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..70abb0e Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/linear.json b/151643/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..d6343ea --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "45780.6", "standardDeviation": "4502.36", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51100.1", "standardDeviation": "779.643", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1473.69", "standardDeviation": "997.554", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "139432", "standardDeviation": "2438.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "138958", "standardDeviation": "3753.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1504.68", "standardDeviation": "1587.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "483782", "standardDeviation": "289271", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "412576", "standardDeviation": "7592.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1639.14", "standardDeviation": "2969.47", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "714049", "standardDeviation": "84171.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "719535", "standardDeviation": "85931.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1983.07", "standardDeviation": "3571.13", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.25051e+06", "standardDeviation": "212884", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.25597e+06", "standardDeviation": "221567", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2023.43", "standardDeviation": "3208.79", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "210272", "standardDeviation": "6470.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "199170", "standardDeviation": "5958.87", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1605.61", "standardDeviation": "1508.06", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "397741", "standardDeviation": "26814.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "396315", "standardDeviation": "27597.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1749.88", "standardDeviation": "2104.88", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "720754", "standardDeviation": "84289.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "718279", "standardDeviation": "81933.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2010.59", "standardDeviation": "3627.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.27052e+06", "standardDeviation": "211227", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.27609e+06", "standardDeviation": "195555", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1955.27", "standardDeviation": "3256.28", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.60011e+06", "standardDeviation": "136123", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.83554e+06", "standardDeviation": "286211", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2099.1", "standardDeviation": "3674.77", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151643/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..2864f70 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151643/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..7187403 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/linear_time.png b/151643/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..37074c4 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151643/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..b3fe974 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "246348", "standardDeviation": "6644.62", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "550508", "standardDeviation": "26722.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "604106", "standardDeviation": "47331.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "746415", "standardDeviation": "59333.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.08374e+06", "standardDeviation": "131136", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "658031", "standardDeviation": "29983.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.9833e+06", "standardDeviation": "248485", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "694549", "standardDeviation": "32722.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.08457e+06", "standardDeviation": "386082", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "715769", "standardDeviation": "24599.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/main/field.json b/151643/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..4340f72 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49897.2", "standardDeviation": "3217.42", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "76462.1", "standardDeviation": "8494.82", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "191714", "standardDeviation": "6414.63", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81200.7", "standardDeviation": "11474.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "537575", "standardDeviation": "49950.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "114806", "standardDeviation": "44545.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "860058", "standardDeviation": "90570.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133023", "standardDeviation": "109812", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.62511e+06", "standardDeviation": "157442", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "165776", "standardDeviation": "120365", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "51160.7", "standardDeviation": "5210.43", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60420.5", "standardDeviation": "10107.9", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "195743", "standardDeviation": "5624.87", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "64214.3", "standardDeviation": "9365.35", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547948", "standardDeviation": "51461.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "108986", "standardDeviation": "110187", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "980083", "standardDeviation": "185905", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117483", "standardDeviation": "119830", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.61816e+06", "standardDeviation": "120832", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150997", "standardDeviation": "120304", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/main/linear.json b/151643/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..345403b --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43979", "standardDeviation": "4673.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51338.2", "standardDeviation": "989.372", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2534.55", "standardDeviation": "4453.44", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163149", "standardDeviation": "4320.31", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "174124", "standardDeviation": "5357.91", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2731.15", "standardDeviation": "6309.52", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "391250", "standardDeviation": "63625.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "385321", "standardDeviation": "28385.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2983.32", "standardDeviation": "12852.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "711900", "standardDeviation": "82710.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "720419", "standardDeviation": "85828.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "6352.01", "standardDeviation": "17821.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.02359e+06", "standardDeviation": "122333", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "942136", "standardDeviation": "52176.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2684.75", "standardDeviation": "6516.13", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "146533", "standardDeviation": "2504.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "130944", "standardDeviation": "1124.42", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2375.76", "standardDeviation": "4356.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "265450", "standardDeviation": "10087.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "262931", "standardDeviation": "11470.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2751.76", "standardDeviation": "6102.47", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "520535", "standardDeviation": "174985", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "479274", "standardDeviation": "21857.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3443.47", "standardDeviation": "8431.04", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01681e+06", "standardDeviation": "101175", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "941837", "standardDeviation": "45099.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "5078.39", "standardDeviation": "13447.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.9291e+06", "standardDeviation": "270904", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.77348e+06", "standardDeviation": "285017", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "12881.5", "standardDeviation": "81570.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151643/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..cccf932 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33546.9", "standardDeviation": "1181.01", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45851.1", "standardDeviation": "1473.04", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1515", "standardDeviation": "1085.34", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "150937", "standardDeviation": "3302.16", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "136384", "standardDeviation": "3789.59", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1458.56", "standardDeviation": "1190.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "277230", "standardDeviation": "11303.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "282151", "standardDeviation": "11391.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1579.6", "standardDeviation": "1645.09", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "561148", "standardDeviation": "48869.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "522471", "standardDeviation": "40297", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1681.74", "standardDeviation": "2345.76", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "986654", "standardDeviation": "97204.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "962010", "standardDeviation": "72398.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1642.13", "standardDeviation": "2078.25", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "160746", "standardDeviation": "3349.58", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "148308", "standardDeviation": "4066.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1520.36", "standardDeviation": "1374.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "323858", "standardDeviation": "15417.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "307013", "standardDeviation": "12216.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1618.14", "standardDeviation": "1527.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "602461", "standardDeviation": "47869.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "522246", "standardDeviation": "21795.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1487.7", "standardDeviation": "2280.31", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12725e+06", "standardDeviation": "111166", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0741e+06", "standardDeviation": "86281.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1430.26", "standardDeviation": "1697.95", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.51571e+06", "standardDeviation": "157819", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.3057e+06", "standardDeviation": "97661.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1711.45", "standardDeviation": "2510.31", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/system-info.log b/151643/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151643/neon-cluster-meta-runner-neon-amd/upwind.json b/151643/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..372fa47 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34665.1", "standardDeviation": "1435.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45189.6", "standardDeviation": "603.581", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1522.51", "standardDeviation": "1199.04", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "114302", "standardDeviation": "1991.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115600", "standardDeviation": "1259.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1571.4", "standardDeviation": "1357.08", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "254572", "standardDeviation": "10123.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "391704", "standardDeviation": "8877.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1800.68", "standardDeviation": "3436.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "635832", "standardDeviation": "66622.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "639965", "standardDeviation": "69347.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3065.07", "standardDeviation": "9712.92", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.1173e+06", "standardDeviation": "182015", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.11211e+06", "standardDeviation": "185885", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2042.08", "standardDeviation": "3353.08", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182100", "standardDeviation": "4934.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "201027", "standardDeviation": "6357.06", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1718.8", "standardDeviation": "1674.95", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "367747", "standardDeviation": "23011.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "383363", "standardDeviation": "25047.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1820.21", "standardDeviation": "2198.09", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "688096", "standardDeviation": "173360", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "560717", "standardDeviation": "37095.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1836.14", "standardDeviation": "3393.92", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.19e+06", "standardDeviation": "191863", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.22383e+06", "standardDeviation": "196847", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2053.27", "standardDeviation": "3642.85", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.81234e+06", "standardDeviation": "235488", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.51667e+06", "standardDeviation": "155118", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1454.03", "standardDeviation": "1012.03", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151643/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..2176f46 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151643/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..3b507ca Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151643/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..fb5edca Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..a3a22f8 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "393899", "standardDeviation": "14832.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277021", "standardDeviation": "3826.19", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "553166", "standardDeviation": "24081", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281525", "standardDeviation": "3364.89", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.06357e+06", "standardDeviation": "59811", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284113", "standardDeviation": "5950.83", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.13978e+06", "standardDeviation": "124685", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "290105", "standardDeviation": "4682.82", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.86559e+06", "standardDeviation": "543942", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "315261", "standardDeviation": "4032.59", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..8d9b089 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..39a68eb Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..b8a4c5c Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..32f2f43 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "307326", "standardDeviation": "3134.35", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43903.4", "standardDeviation": "4070.01", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "633129", "standardDeviation": "9786.12", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46399.2", "standardDeviation": "1071.93", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29203e+06", "standardDeviation": "13982.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46769.3", "standardDeviation": "1804.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.5782e+06", "standardDeviation": "30326.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41294.2", "standardDeviation": "2364.27", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66402e+06", "standardDeviation": "108326", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126968", "standardDeviation": "4397.66", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309898", "standardDeviation": "5128.27", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34157.7", "standardDeviation": "787.794", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "618454", "standardDeviation": "9948.88", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34045.3", "standardDeviation": "1440.07", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23462e+06", "standardDeviation": "19897.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34143.8", "standardDeviation": "1280.41", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.48353e+06", "standardDeviation": "37496", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41780", "standardDeviation": "2142.15", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.03554e+06", "standardDeviation": "69464.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122570", "standardDeviation": "4616.55", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..3b81e10 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..ec7b9d5 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..7fd2044 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..4586419 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99529.3", "standardDeviation": "3038.93", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "214347", "standardDeviation": "3366.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "9921.72", "standardDeviation": "5055.71", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "296152", "standardDeviation": "96841.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "427258", "standardDeviation": "2272.31", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3262.53", "standardDeviation": "136.745", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "572185", "standardDeviation": "6625.88", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "853123", "standardDeviation": "7645.43", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3347.22", "standardDeviation": "161.017", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "793359", "standardDeviation": "44490.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.18113e+06", "standardDeviation": "22978.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2575.95", "standardDeviation": "331.849", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.59515e+06", "standardDeviation": "100912", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.37122e+06", "standardDeviation": "40678.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2869.84", "standardDeviation": "3114.58", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137219", "standardDeviation": "13907.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "149511", "standardDeviation": "15208.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2535.51", "standardDeviation": "183.02", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "252985", "standardDeviation": "40945.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "302964", "standardDeviation": "35502", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2613.18", "standardDeviation": "196.509", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "556735", "standardDeviation": "79548.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "601952", "standardDeviation": "81220.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2565.02", "standardDeviation": "405.374", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.13759e+06", "standardDeviation": "186390", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.23943e+06", "standardDeviation": "187084", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2533.89", "standardDeviation": "739.758", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.69866e+06", "standardDeviation": "226019", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.87943e+06", "standardDeviation": "213840", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2594.5", "standardDeviation": "973.529", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..757dd80 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..f93ddeb Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..2178439 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..c5a5988 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "272158", "standardDeviation": "3333.78", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "267492", "standardDeviation": "6898.69", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "530865", "standardDeviation": "5654.21", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272922", "standardDeviation": "23549.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.0295e+06", "standardDeviation": "10758.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276688", "standardDeviation": "25710.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.02717e+06", "standardDeviation": "22893.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281108", "standardDeviation": "5403.55", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.33335e+06", "standardDeviation": "34207.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "308316", "standardDeviation": "22413.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..2132044 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306469", "standardDeviation": "1810.61", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40623.3", "standardDeviation": "2013.79", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "633422", "standardDeviation": "3035.53", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47414.8", "standardDeviation": "2661.61", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.12558e+06", "standardDeviation": "193302", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42282.3", "standardDeviation": "954.457", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79814e+06", "standardDeviation": "20031.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42882", "standardDeviation": "1034.39", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.60421e+06", "standardDeviation": "30650.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137308", "standardDeviation": "2038.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309242", "standardDeviation": "3252.42", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35587.4", "standardDeviation": "1170.04", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616867", "standardDeviation": "5396.84", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35744.2", "standardDeviation": "840.955", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23152e+06", "standardDeviation": "8666.46", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35972.8", "standardDeviation": "608.497", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.49678e+06", "standardDeviation": "200563", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39857.7", "standardDeviation": "3956.57", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94698e+06", "standardDeviation": "7715.52", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130682", "standardDeviation": "3969.01", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..e11bc58 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98985.1", "standardDeviation": "2220.52", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147236", "standardDeviation": "3030.39", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2565.41", "standardDeviation": "800.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197515", "standardDeviation": "5280.94", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295281", "standardDeviation": "6083.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2547.62", "standardDeviation": "156.864", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "396364", "standardDeviation": "10555", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "595572", "standardDeviation": "64618.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2518.71", "standardDeviation": "144.968", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "785080", "standardDeviation": "22547.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17786e+06", "standardDeviation": "18028.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2488.34", "standardDeviation": "153.258", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56327e+06", "standardDeviation": "64475.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35543e+06", "standardDeviation": "22859.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2556.8", "standardDeviation": "216.057", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "135707", "standardDeviation": "2572.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "252141", "standardDeviation": "5287.28", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3315.87", "standardDeviation": "178.744", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "528734", "standardDeviation": "197580", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "361783", "standardDeviation": "46450.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2476.66", "standardDeviation": "171.702", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "529870", "standardDeviation": "86832.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "589166", "standardDeviation": "170256", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2493.96", "standardDeviation": "148.765", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11125e+06", "standardDeviation": "210005", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.20908e+06", "standardDeviation": "188791", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2470.97", "standardDeviation": "162.484", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.54208e+06", "standardDeviation": "415490", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.72974e+06", "standardDeviation": "251365", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2548.54", "standardDeviation": "884.187", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..07cf1a9 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82866.6", "standardDeviation": "3983.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "132259", "standardDeviation": "4212.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2607.35", "standardDeviation": "162.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172095", "standardDeviation": "66813.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262973", "standardDeviation": "5730.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2596.05", "standardDeviation": "151.831", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332580", "standardDeviation": "20629.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "526287", "standardDeviation": "11724.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2514.74", "standardDeviation": "182.897", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "670498", "standardDeviation": "46736.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.07035e+06", "standardDeviation": "209242", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2594.84", "standardDeviation": "250.958", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33192e+06", "standardDeviation": "102989", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09773e+06", "standardDeviation": "35153.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2550.88", "standardDeviation": "319.257", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "114237", "standardDeviation": "12809.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135398", "standardDeviation": "12999", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2533.74", "standardDeviation": "204.534", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "221643", "standardDeviation": "32319.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "293785", "standardDeviation": "103313", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2570.82", "standardDeviation": "219.458", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "475200", "standardDeviation": "81973.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "545312", "standardDeviation": "71510.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2510.58", "standardDeviation": "190.438", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "943786", "standardDeviation": "181278", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.10313e+06", "standardDeviation": "156049", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2665.74", "standardDeviation": "454.316", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.7331e+06", "standardDeviation": "287079", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.83724e+06", "standardDeviation": "279024", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2585.35", "standardDeviation": "773.118", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151643/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..c644cf2 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Tue Sep 23 16:23:06 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 28C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..249eb53 --- /dev/null +++ b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82691.1", "standardDeviation": "3914.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131681", "standardDeviation": "3351.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2669.62", "standardDeviation": "265.562", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166798", "standardDeviation": "7824.29", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263269", "standardDeviation": "7251.79", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2615.84", "standardDeviation": "242.575", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332101", "standardDeviation": "22496.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525539", "standardDeviation": "11183.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2551.7", "standardDeviation": "254.89", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "663809", "standardDeviation": "48909.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05193e+06", "standardDeviation": "22054.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2606.61", "standardDeviation": "276.314", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34254e+06", "standardDeviation": "100636", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.11305e+06", "standardDeviation": "35952.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2646.28", "standardDeviation": "933.268", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "126842", "standardDeviation": "12488.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "140050", "standardDeviation": "12365.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2551.82", "standardDeviation": "125.306", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "234049", "standardDeviation": "36955.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "284709", "standardDeviation": "34078.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2608.82", "standardDeviation": "264.744", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "506526", "standardDeviation": "78831.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "568512", "standardDeviation": "74036.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2589.27", "standardDeviation": "489.885", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03318e+06", "standardDeviation": "171305", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.15585e+06", "standardDeviation": "165842", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2695.07", "standardDeviation": "464.149", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.22903e+06", "standardDeviation": "227383", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.34917e+06", "standardDeviation": "266791", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2596.74", "standardDeviation": "819.666", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..b1919c1 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..749d344 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..e6fa1e7 Binary files /dev/null and b/151643/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/divOperator.json b/151892/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..b67983a --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "234787", "standardDeviation": "4639.67", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "548551", "standardDeviation": "29349.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "505335", "standardDeviation": "24525.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "545023", "standardDeviation": "22971", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "982595", "standardDeviation": "122767", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "634851", "standardDeviation": "24519", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.8831e+06", "standardDeviation": "99161.7", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "686091", "standardDeviation": "187603", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.0003e+06", "standardDeviation": "189889", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "710157", "standardDeviation": "24717.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151892/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..dbe310f Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151892/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..7e7d2b3 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151892/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..f7d8436 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/field.json b/151892/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..dcd9a21 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98889.8", "standardDeviation": "4444", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89200.6", "standardDeviation": "10151.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "158114", "standardDeviation": "2615.78", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78093.2", "standardDeviation": "8584.76", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "376628", "standardDeviation": "10154", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "105597", "standardDeviation": "8324.87", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "776858", "standardDeviation": "109854", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124659", "standardDeviation": "15509.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.43599e+06", "standardDeviation": "41521.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "146903", "standardDeviation": "5470.66", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47105.9", "standardDeviation": "1987.27", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "57514.8", "standardDeviation": "10062.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "142215", "standardDeviation": "3607.35", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62006.1", "standardDeviation": "10865.9", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "412096", "standardDeviation": "79482.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127993", "standardDeviation": "322607", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "749752", "standardDeviation": "43892", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130718", "standardDeviation": "222116", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.45726e+06", "standardDeviation": "77202.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149081", "standardDeviation": "146507", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151892/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..8e47a5e Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/field_relative.png b/151892/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..00d6d9b Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/field_time.png b/151892/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..37c00fb Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/linear.json b/151892/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..78146b1 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49866.9", "standardDeviation": "2397.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "56224.9", "standardDeviation": "2199.4", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1505.61", "standardDeviation": "1195.69", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137880", "standardDeviation": "2415.05", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147532", "standardDeviation": "3654.95", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1537.68", "standardDeviation": "1381.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "256819", "standardDeviation": "8252.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "282621", "standardDeviation": "13521.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2059.12", "standardDeviation": "5429.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "558870", "standardDeviation": "50545.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "505463", "standardDeviation": "34698.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1687.95", "standardDeviation": "2423", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "960242", "standardDeviation": "75199.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "953917", "standardDeviation": "72280.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1707.98", "standardDeviation": "2334.27", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "135326", "standardDeviation": "3314.17", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "211685", "standardDeviation": "29765.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2634.64", "standardDeviation": "2052.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "393812", "standardDeviation": "26435.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "398206", "standardDeviation": "26969.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2672.32", "standardDeviation": "2712.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "488567", "standardDeviation": "17477.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "488997", "standardDeviation": "25484", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1683.03", "standardDeviation": "2264.21", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "963204", "standardDeviation": "38667.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "965897", "standardDeviation": "70212.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1608.76", "standardDeviation": "1718.97", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.3369e+06", "standardDeviation": "170661", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.4753e+06", "standardDeviation": "272896", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1666.88", "standardDeviation": "2318.15", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151892/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..7c5f3fb Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151892/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..647e84f Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/linear_time.png b/151892/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..8cb6864 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151892/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..8a751c0 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "232505", "standardDeviation": "4350.91", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "540149", "standardDeviation": "31446.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "451993", "standardDeviation": "12262.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "548316", "standardDeviation": "25010.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "908252", "standardDeviation": "50198.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "630606", "standardDeviation": "29060.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.70977e+06", "standardDeviation": "14045.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "673308", "standardDeviation": "28584.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "6.25127e+06", "standardDeviation": "748490", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "730959", "standardDeviation": "30292.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/main/field.json b/151892/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..21c7f81 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "46491.3", "standardDeviation": "1849.62", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "71188", "standardDeviation": "8501.15", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "135137", "standardDeviation": "3391.09", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78010.3", "standardDeviation": "10373.8", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "412264", "standardDeviation": "13751", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "106270", "standardDeviation": "7496.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "751486", "standardDeviation": "153140", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117732", "standardDeviation": "12052.8", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.45492e+06", "standardDeviation": "66044.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140512", "standardDeviation": "4186.05", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "45347.6", "standardDeviation": "2279.25", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59597.2", "standardDeviation": "9708.16", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "163986", "standardDeviation": "4465.27", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61366.4", "standardDeviation": "9598.16", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "480420", "standardDeviation": "33178.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109467", "standardDeviation": "16750.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "967320", "standardDeviation": "143505", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "105294", "standardDeviation": "51308.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.75788e+06", "standardDeviation": "355087", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140218", "standardDeviation": "64164.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/main/linear.json b/151892/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..36348da --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50032.9", "standardDeviation": "778.501", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50289.9", "standardDeviation": "903.831", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1450.8", "standardDeviation": "1421.36", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138878", "standardDeviation": "2387.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "145519", "standardDeviation": "4710.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1497.83", "standardDeviation": "1520.92", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "254966", "standardDeviation": "8906.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "267948", "standardDeviation": "10503.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3825.64", "standardDeviation": "9962.69", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "497794", "standardDeviation": "32836.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "509197", "standardDeviation": "35592.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1979.24", "standardDeviation": "3492.52", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.23337e+06", "standardDeviation": "202334", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.25559e+06", "standardDeviation": "220062", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1552.35", "standardDeviation": "1936.42", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "209057", "standardDeviation": "6926.34", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "210142", "standardDeviation": "7128.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1550.77", "standardDeviation": "2162.39", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "387124", "standardDeviation": "26467.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "395112", "standardDeviation": "26791.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1740.29", "standardDeviation": "2363.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "722770", "standardDeviation": "83914.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "713958", "standardDeviation": "81541.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2575.27", "standardDeviation": "7518.19", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.27211e+06", "standardDeviation": "212094", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28895e+06", "standardDeviation": "207000", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1579.55", "standardDeviation": "2242.26", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.85439e+06", "standardDeviation": "259654", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.69485e+06", "standardDeviation": "301136", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1551.12", "standardDeviation": "1198.32", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151892/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..9023d7e --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33529.1", "standardDeviation": "708.924", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44199.9", "standardDeviation": "716.004", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1497.95", "standardDeviation": "1186.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "106878", "standardDeviation": "831.896", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "119246", "standardDeviation": "3896.92", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2013.18", "standardDeviation": "4481.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "228377", "standardDeviation": "7824.42", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "240491", "standardDeviation": "9656.35", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1637.96", "standardDeviation": "1838.78", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "426865", "standardDeviation": "23170.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "439650", "standardDeviation": "40539.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1782.65", "standardDeviation": "2681.22", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "837023", "standardDeviation": "43110.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "859270", "standardDeviation": "67748.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1644.91", "standardDeviation": "1944.76", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "132043", "standardDeviation": "2586.62", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138230", "standardDeviation": "2536.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1537.41", "standardDeviation": "1472.91", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "262047", "standardDeviation": "6770.04", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "265848", "standardDeviation": "8899.94", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1626.05", "standardDeviation": "1794.15", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "476880", "standardDeviation": "3319.38", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "503235", "standardDeviation": "27525.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2633.27", "standardDeviation": "12711.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0143e+06", "standardDeviation": "76356.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "939628", "standardDeviation": "41257.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1461.98", "standardDeviation": "1682.22", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.54619e+06", "standardDeviation": "66797.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.14685e+06", "standardDeviation": "69994", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1755.09", "standardDeviation": "2171.87", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/system-info.log b/151892/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151892/neon-cluster-meta-runner-neon-amd/upwind.json b/151892/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..092ca61 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "36845.5", "standardDeviation": "7726.41", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "47016.1", "standardDeviation": "1732.03", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1721.34", "standardDeviation": "1572.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "189286", "standardDeviation": "74872.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "164157", "standardDeviation": "4145.81", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1654.29", "standardDeviation": "1300.12", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "347822", "standardDeviation": "21005.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "344918", "standardDeviation": "22582.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1776.4", "standardDeviation": "2028.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "637954", "standardDeviation": "66070.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "644456", "standardDeviation": "69633.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1812.8", "standardDeviation": "2758.02", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.12728e+06", "standardDeviation": "188671", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.14007e+06", "standardDeviation": "186993", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2310.06", "standardDeviation": "5469.64", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "193614", "standardDeviation": "6113.52", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "200908", "standardDeviation": "6690.47", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1687.96", "standardDeviation": "1881.3", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "371292", "standardDeviation": "22958.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "382665", "standardDeviation": "25502", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2791.82", "standardDeviation": "2637.51", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "486951", "standardDeviation": "12384.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "531396", "standardDeviation": "100498", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1622.61", "standardDeviation": "2045.49", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.02407e+06", "standardDeviation": "74193.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "980847", "standardDeviation": "69454.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1611.95", "standardDeviation": "1864.81", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.6444e+06", "standardDeviation": "96519.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.1935e+06", "standardDeviation": "92748.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1711.62", "standardDeviation": "2122.92", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151892/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..5720598 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151892/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..41ee2ee Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151892/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..66e6a67 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..9da81d3 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "308349", "standardDeviation": "29706.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284613", "standardDeviation": "2831.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "534028", "standardDeviation": "7441.09", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272446", "standardDeviation": "4037.95", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03848e+06", "standardDeviation": "11602.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "274201", "standardDeviation": "5800.27", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.022e+06", "standardDeviation": "6634.53", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279121", "standardDeviation": "2229.03", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.48914e+06", "standardDeviation": "171843", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "306963", "standardDeviation": "5008.06", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..75f472c Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..942947f Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..06148f3 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..1c3c574 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "316023", "standardDeviation": "6718.16", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45773.8", "standardDeviation": "2121.81", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "672599", "standardDeviation": "17973.2", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45610.6", "standardDeviation": "801.459", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.34831e+06", "standardDeviation": "46846.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47119.9", "standardDeviation": "2750.66", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.71208e+06", "standardDeviation": "157345", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "54712.8", "standardDeviation": "2031.8", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.3442e+06", "standardDeviation": "21624.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "181281", "standardDeviation": "4249.96", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "462428", "standardDeviation": "55709.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38508.3", "standardDeviation": "934.901", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "910893", "standardDeviation": "2119.79", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39172.1", "standardDeviation": "3253.11", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80253e+06", "standardDeviation": "5331.46", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40494.6", "standardDeviation": "3141.02", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47814e+06", "standardDeviation": "62767.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41714.4", "standardDeviation": "2490.61", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.93941e+06", "standardDeviation": "5268.21", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122876", "standardDeviation": "4438.72", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..edcdda8 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..dbd80c9 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..a7c1f24 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..4114fc0 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99020.8", "standardDeviation": "3724.08", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "214689", "standardDeviation": "6519.19", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3284.74", "standardDeviation": "2252.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "295262", "standardDeviation": "85746.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "427431", "standardDeviation": "2489.02", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3079.31", "standardDeviation": "155.887", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "569305", "standardDeviation": "12338", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "853761", "standardDeviation": "4902.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3092.5", "standardDeviation": "294.349", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.13622e+06", "standardDeviation": "29910.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.70823e+06", "standardDeviation": "18487.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3091.94", "standardDeviation": "182.596", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "2.17434e+06", "standardDeviation": "137799", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "3.41201e+06", "standardDeviation": "11066.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3149.74", "standardDeviation": "176.305", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "145165", "standardDeviation": "68791.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150776", "standardDeviation": "8656.35", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2311.42", "standardDeviation": "106.973", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "255046", "standardDeviation": "3555.99", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "271439", "standardDeviation": "5187.99", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2252.99", "standardDeviation": "148.526", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "546287", "standardDeviation": "5651.45", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "591110", "standardDeviation": "6721.31", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2774.91", "standardDeviation": "898.248", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10935e+06", "standardDeviation": "20958.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18475e+06", "standardDeviation": "24391.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2337.24", "standardDeviation": "116.442", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.76002e+06", "standardDeviation": "37975.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.32853e+06", "standardDeviation": "40220", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2452.36", "standardDeviation": "378.311", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..6b2a008 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..28cd311 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..05e958b Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..c68afa1 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "278670", "standardDeviation": "29772.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286898", "standardDeviation": "4982.71", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "562346", "standardDeviation": "195024", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291041", "standardDeviation": "4386.36", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05698e+06", "standardDeviation": "60674.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291493", "standardDeviation": "3933.88", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.11065e+06", "standardDeviation": "127478", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "299608", "standardDeviation": "16297.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.96314e+06", "standardDeviation": "173497", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "324411", "standardDeviation": "4012.78", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..d6701a2 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306466", "standardDeviation": "3347.37", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40673.6", "standardDeviation": "2510.99", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "635978", "standardDeviation": "8767.5", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46776.2", "standardDeviation": "5754.81", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29288e+06", "standardDeviation": "13495.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48779", "standardDeviation": "1736.46", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80414e+06", "standardDeviation": "56424.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42949.2", "standardDeviation": "1635.23", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.65403e+06", "standardDeviation": "104835", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139551", "standardDeviation": "21657.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "310095", "standardDeviation": "4029.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36399.9", "standardDeviation": "1226.12", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "618173", "standardDeviation": "9050.21", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36426", "standardDeviation": "1330.97", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23388e+06", "standardDeviation": "18830.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37393.3", "standardDeviation": "10131.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.48485e+06", "standardDeviation": "34794.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40563", "standardDeviation": "3690.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.07733e+06", "standardDeviation": "66888.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131450", "standardDeviation": "4330.57", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..016615f --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99057.5", "standardDeviation": "4288.69", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "148548", "standardDeviation": "7998.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2937.5", "standardDeviation": "1618.52", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199566", "standardDeviation": "13410.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "296792", "standardDeviation": "7880.41", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2880.19", "standardDeviation": "436.553", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "443493", "standardDeviation": "463744", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "590797", "standardDeviation": "14278.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2555.82", "standardDeviation": "140.214", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "798105", "standardDeviation": "46301", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17959e+06", "standardDeviation": "20724.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2597.03", "standardDeviation": "268.871", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.60135e+06", "standardDeviation": "107435", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38243e+06", "standardDeviation": "68376.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2486.81", "standardDeviation": "307.186", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "139201", "standardDeviation": "13921.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150709", "standardDeviation": "13028.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2520.29", "standardDeviation": "431.799", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "253501", "standardDeviation": "38669.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "296752", "standardDeviation": "33695.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2464.62", "standardDeviation": "220.074", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "563485", "standardDeviation": "80640.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "582875", "standardDeviation": "77754.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2484.25", "standardDeviation": "218.312", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.20065e+06", "standardDeviation": "175882", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.3056e+06", "standardDeviation": "173149", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2655.18", "standardDeviation": "816.544", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.78543e+06", "standardDeviation": "219076", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "4.01468e+06", "standardDeviation": "285145", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2596.33", "standardDeviation": "1005.57", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..5096166 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82405.1", "standardDeviation": "3456.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131587", "standardDeviation": "3939.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2650.14", "standardDeviation": "157.081", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172146", "standardDeviation": "65736.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263518", "standardDeviation": "6070.32", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2580.21", "standardDeviation": "128.839", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "331600", "standardDeviation": "19751.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525556", "standardDeviation": "12662", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2565.22", "standardDeviation": "120.934", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "663859", "standardDeviation": "47308.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.07236e+06", "standardDeviation": "212252", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2551.06", "standardDeviation": "138.762", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33692e+06", "standardDeviation": "98306.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.108e+06", "standardDeviation": "52026.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2515.39", "standardDeviation": "165.46", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115466", "standardDeviation": "14294.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136700", "standardDeviation": "10953.7", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2605.53", "standardDeviation": "132.009", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "222987", "standardDeviation": "39502.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "274782", "standardDeviation": "33352", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2536.73", "standardDeviation": "240.764", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "471195", "standardDeviation": "84823.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "547037", "standardDeviation": "72467.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2601.12", "standardDeviation": "132.487", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "966742", "standardDeviation": "181660", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28739e+06", "standardDeviation": "150063", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2652.64", "standardDeviation": "250.87", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.25485e+06", "standardDeviation": "250353", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.32552e+06", "standardDeviation": "227674", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2630.84", "standardDeviation": "752.185", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151892/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..2652acf --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Sep 24 15:15:11 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 29C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..5486a17 --- /dev/null +++ b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82153.4", "standardDeviation": "2293.06", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131579", "standardDeviation": "2930.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2439.54", "standardDeviation": "165.032", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171631", "standardDeviation": "59197.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262614", "standardDeviation": "5341.23", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2641.2", "standardDeviation": "141.232", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "351691", "standardDeviation": "8601.87", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "526095", "standardDeviation": "10169.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2489.72", "standardDeviation": "106.594", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "660957", "standardDeviation": "11792", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05881e+06", "standardDeviation": "92543.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2400.88", "standardDeviation": "76.0925", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.3321e+06", "standardDeviation": "33385.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09754e+06", "standardDeviation": "23088.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2816.99", "standardDeviation": "161.866", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "201402", "standardDeviation": "7942.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138579", "standardDeviation": "4616.77", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2345.69", "standardDeviation": "138.894", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "231674", "standardDeviation": "10834.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "268060", "standardDeviation": "7779.16", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2290.63", "standardDeviation": "78.1369", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "505377", "standardDeviation": "18525.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "563440", "standardDeviation": "22724.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2363.79", "standardDeviation": "214.517", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.02321e+06", "standardDeviation": "58405.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12196e+06", "standardDeviation": "54937.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2424.47", "standardDeviation": "323.352", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.73462e+06", "standardDeviation": "126858", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.93411e+06", "standardDeviation": "242511", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3211.74", "standardDeviation": "581.389", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..5bf7cd3 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..8755ba4 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..0a53b18 Binary files /dev/null and b/151892/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/divOperator.json b/151914/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..19bda30 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "223672", "standardDeviation": "3436.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "557286", "standardDeviation": "24959.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "478982", "standardDeviation": "22848.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "557536", "standardDeviation": "28808.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "981492", "standardDeviation": "46065.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "677043", "standardDeviation": "237747", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.25912e+06", "standardDeviation": "177904", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "724037", "standardDeviation": "241085", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.04662e+06", "standardDeviation": "188094", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "740996", "standardDeviation": "35496", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151914/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..56174d7 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151914/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..4d0b151 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151914/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..bb3551c Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/field.json b/151914/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..94c68ce --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "102509", "standardDeviation": "4355.43", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "75235.1", "standardDeviation": "2283.53", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "148028", "standardDeviation": "4112.02", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85795.5", "standardDeviation": "7588.23", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "645392", "standardDeviation": "17715", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113093", "standardDeviation": "9825.29", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "964113", "standardDeviation": "145544", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126569", "standardDeviation": "32238.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72652e+06", "standardDeviation": "283462", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "155429", "standardDeviation": "65909.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "57458.3", "standardDeviation": "16882.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61630.9", "standardDeviation": "9919", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "193299", "standardDeviation": "7789.6", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63596.5", "standardDeviation": "9703.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "549238", "standardDeviation": "49962.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "95341", "standardDeviation": "9729.86", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976956", "standardDeviation": "187982", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104761", "standardDeviation": "10844.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74327e+06", "standardDeviation": "279305", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "136108", "standardDeviation": "10216.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151914/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..accf5d4 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/field_relative.png b/151914/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..22b18b0 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/field_time.png b/151914/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..6f7f486 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/linear.json b/151914/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..d3a745c --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "41887.9", "standardDeviation": "3266.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50776.1", "standardDeviation": "2693.59", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1457.4", "standardDeviation": "1023.15", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "139518", "standardDeviation": "2256.78", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "136946", "standardDeviation": "4030", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3891.63", "standardDeviation": "10139.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "246514", "standardDeviation": "6213.81", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "268531", "standardDeviation": "11239.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1465.29", "standardDeviation": "1288.14", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "529893", "standardDeviation": "42143.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "493062", "standardDeviation": "65155.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1694.43", "standardDeviation": "2445.57", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "957854", "standardDeviation": "88453.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "950302", "standardDeviation": "69859.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1683.69", "standardDeviation": "2119.64", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "127921", "standardDeviation": "2557.29", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137080", "standardDeviation": "3097.96", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1509.94", "standardDeviation": "1304.76", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "253589", "standardDeviation": "5918.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "262240", "standardDeviation": "11481.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1495.38", "standardDeviation": "1788.87", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "478441", "standardDeviation": "10805.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "504397", "standardDeviation": "32465.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1686.93", "standardDeviation": "2265.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "973344", "standardDeviation": "55468.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "984853", "standardDeviation": "90097.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1737.92", "standardDeviation": "2056.24", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.44572e+06", "standardDeviation": "68717.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.33372e+06", "standardDeviation": "68056", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1890.85", "standardDeviation": "2741.39", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151914/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..f1192aa Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151914/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..7d7e5b4 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/linear_time.png b/151914/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..212a1a8 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151914/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..9d3a233 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210446", "standardDeviation": "3032.31", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "536152", "standardDeviation": "23640.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "439298", "standardDeviation": "4288.99", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "521008", "standardDeviation": "3213.07", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "874053", "standardDeviation": "7797.75", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "622474", "standardDeviation": "21192.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72619e+06", "standardDeviation": "87060.1", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "769875", "standardDeviation": "29056.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "6.4865e+06", "standardDeviation": "30429.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "704765", "standardDeviation": "22267.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/main/field.json b/151914/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..0660e4e --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50286.5", "standardDeviation": "10297", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77529.5", "standardDeviation": "15982.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "143578", "standardDeviation": "14996.4", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "82899.9", "standardDeviation": "15717.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "390714", "standardDeviation": "27401.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117301", "standardDeviation": "11040.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "779293", "standardDeviation": "58870", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130264", "standardDeviation": "44389.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.62088e+06", "standardDeviation": "292765", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "159009", "standardDeviation": "61880.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47855", "standardDeviation": "5863.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "64951", "standardDeviation": "4304.63", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "148382", "standardDeviation": "20201.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "67850.3", "standardDeviation": "5528.35", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "391939", "standardDeviation": "20272.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103936", "standardDeviation": "23071.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "974456", "standardDeviation": "147381", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "116832", "standardDeviation": "35287.1", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74975e+06", "standardDeviation": "293239", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143395", "standardDeviation": "43040.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/main/linear.json b/151914/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..c318f23 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "41266.9", "standardDeviation": "3964.06", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50945.3", "standardDeviation": "919.854", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1775.05", "standardDeviation": "2586.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129930", "standardDeviation": "1175.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130540", "standardDeviation": "1156.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1445.32", "standardDeviation": "1391.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "259237", "standardDeviation": "3763.02", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "335409", "standardDeviation": "16130", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2220.5", "standardDeviation": "4561.36", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "710896", "standardDeviation": "83023.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "718298", "standardDeviation": "85325.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2133.01", "standardDeviation": "2974.41", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.04119e+06", "standardDeviation": "5241.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.03558e+06", "standardDeviation": "1571.43", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1484.65", "standardDeviation": "1610.64", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129894", "standardDeviation": "2492.41", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "212639", "standardDeviation": "2802.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2315.22", "standardDeviation": "1369.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "402795", "standardDeviation": "3485.35", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "350833", "standardDeviation": "19442.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2800.4", "standardDeviation": "6607.13", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "720944", "standardDeviation": "83347.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "540752", "standardDeviation": "2522.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3509.82", "standardDeviation": "10014.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.19358e+06", "standardDeviation": "151628", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.17744e+06", "standardDeviation": "116201", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3661.39", "standardDeviation": "13060.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.62671e+06", "standardDeviation": "267943", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.87275e+06", "standardDeviation": "269396", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4307.62", "standardDeviation": "14078.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151914/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..229a1c4 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33502.9", "standardDeviation": "876.144", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44107.5", "standardDeviation": "846.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1472.51", "standardDeviation": "987.348", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "111859", "standardDeviation": "1389.18", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115714", "standardDeviation": "1327.31", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1421.48", "standardDeviation": "1078.88", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "229694", "standardDeviation": "2305.37", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "271415", "standardDeviation": "9814.28", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1487.59", "standardDeviation": "1473.28", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "459448", "standardDeviation": "2325.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "463670", "standardDeviation": "2479.38", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1630.87", "standardDeviation": "2315.94", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "917261", "standardDeviation": "4298.63", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "926478", "standardDeviation": "1626.77", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1554.09", "standardDeviation": "1840.53", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130605", "standardDeviation": "1641.7", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "131365", "standardDeviation": "2981.51", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1398.94", "standardDeviation": "1235.6", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "269968", "standardDeviation": "5803.07", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "255427", "standardDeviation": "2016.43", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1450.74", "standardDeviation": "1221.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "539741", "standardDeviation": "16378.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "503598", "standardDeviation": "2098.76", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1431.08", "standardDeviation": "1951.54", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.22461e+06", "standardDeviation": "190127", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.00659e+06", "standardDeviation": "2380.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1357.16", "standardDeviation": "1444.99", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.38566e+06", "standardDeviation": "31432.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.4404e+06", "standardDeviation": "300218", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1744.97", "standardDeviation": "2452.03", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/system-info.log b/151914/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151914/neon-cluster-meta-runner-neon-amd/upwind.json b/151914/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..957d473 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49558.9", "standardDeviation": "581.722", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44630.9", "standardDeviation": "2605.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1525.33", "standardDeviation": "1205.13", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115961", "standardDeviation": "1009.04", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "128211", "standardDeviation": "3884.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1517.39", "standardDeviation": "972.194", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "228926", "standardDeviation": "6047.73", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "240307", "standardDeviation": "8443.86", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2384.5", "standardDeviation": "5993.77", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "416788", "standardDeviation": "19681.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "445510", "standardDeviation": "29797.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1679.55", "standardDeviation": "2405.68", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "821398", "standardDeviation": "33654.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "849434", "standardDeviation": "89679.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1748.78", "standardDeviation": "2351.03", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130367", "standardDeviation": "2386.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137600", "standardDeviation": "1936.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1525.8", "standardDeviation": "1387.44", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "269606", "standardDeviation": "7281.25", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "269323", "standardDeviation": "8534.82", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1516.06", "standardDeviation": "1255.03", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "516002", "standardDeviation": "24028.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "549190", "standardDeviation": "41383.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1594.24", "standardDeviation": "1962.98", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00109e+06", "standardDeviation": "61506.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "951258", "standardDeviation": "50198.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1677.51", "standardDeviation": "2047.11", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.3475e+06", "standardDeviation": "100407", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.17968e+06", "standardDeviation": "69263.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1725.07", "standardDeviation": "2383.75", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151914/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..3184c46 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151914/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..ef4b565 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151914/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..a8ccab4 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..8b5ec9a --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "275972", "standardDeviation": "7204.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285366", "standardDeviation": "3917.81", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "568190", "standardDeviation": "18580.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291741", "standardDeviation": "3826.81", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.06122e+06", "standardDeviation": "30859.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "292414", "standardDeviation": "2842.54", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.06141e+06", "standardDeviation": "63029.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "297815", "standardDeviation": "2859.1", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.32092e+06", "standardDeviation": "116335", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "322090", "standardDeviation": "2636.77", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..c123256 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..f2ea110 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..2101a93 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..a84d8c2 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "316097", "standardDeviation": "2917.86", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45860.7", "standardDeviation": "1961.35", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "671744", "standardDeviation": "17706.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45626.2", "standardDeviation": "606.425", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.34936e+06", "standardDeviation": "46009.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48768.4", "standardDeviation": "778.388", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.72159e+06", "standardDeviation": "381790", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "55530.3", "standardDeviation": "1421.96", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.58776e+06", "standardDeviation": "19639.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126385", "standardDeviation": "2096.72", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "312208", "standardDeviation": "34116.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34684.4", "standardDeviation": "1036.82", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616832", "standardDeviation": "7827.68", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34159.5", "standardDeviation": "833.866", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23168e+06", "standardDeviation": "12690.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34155.9", "standardDeviation": "611.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.49115e+06", "standardDeviation": "183024", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41302.2", "standardDeviation": "2615.96", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.9395e+06", "standardDeviation": "1679.28", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122249", "standardDeviation": "3884.74", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..0b04f30 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..12ba0b6 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..b2a4d50 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..be262c3 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98712.1", "standardDeviation": "2233.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147675", "standardDeviation": "2947.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2376.38", "standardDeviation": "518.616", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197585", "standardDeviation": "4301.98", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299280", "standardDeviation": "48560.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2300.46", "standardDeviation": "83.6059", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "395643", "standardDeviation": "7969.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588518", "standardDeviation": "11151.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2314.1", "standardDeviation": "53.1132", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "789570", "standardDeviation": "15340.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17541e+06", "standardDeviation": "17063.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2606.65", "standardDeviation": "2286.24", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.55573e+06", "standardDeviation": "57224.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35111e+06", "standardDeviation": "20148", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2294.91", "standardDeviation": "82.7014", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "125004", "standardDeviation": "2369.02", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139380", "standardDeviation": "2816.69", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2261.9", "standardDeviation": "134.66", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "259720", "standardDeviation": "6168.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "283516", "standardDeviation": "4607.52", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2252.82", "standardDeviation": "56.9642", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "521152", "standardDeviation": "6788.29", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "563698", "standardDeviation": "8851.53", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2250.06", "standardDeviation": "77.831", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.02193e+06", "standardDeviation": "12338.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.1301e+06", "standardDeviation": "14554.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2282.45", "standardDeviation": "77.0469", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.1969e+06", "standardDeviation": "9372.86", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.15601e+06", "standardDeviation": "10350", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2246.03", "standardDeviation": "190.34", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..d6b1d6b Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..875e92e Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..22e0a43 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..7bc0e1f --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "272092", "standardDeviation": "3544.56", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "269582", "standardDeviation": "4434.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "532637", "standardDeviation": "6312.25", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "270975", "standardDeviation": "3580.28", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03575e+06", "standardDeviation": "8177.74", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275246", "standardDeviation": "6766.44", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.05616e+06", "standardDeviation": "86535.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280485", "standardDeviation": "3989.54", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.30966e+06", "standardDeviation": "61221.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "303096", "standardDeviation": "2496.53", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..b9cc8d9 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306630", "standardDeviation": "1679.49", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42334.9", "standardDeviation": "3981.31", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "632110", "standardDeviation": "1790.2", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41031.1", "standardDeviation": "1560.84", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "897895", "standardDeviation": "9327.38", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41233.6", "standardDeviation": "943.732", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.81914e+06", "standardDeviation": "87037.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41227.9", "standardDeviation": "716.843", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.60623e+06", "standardDeviation": "33211.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128202", "standardDeviation": "15831.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "311209", "standardDeviation": "4907.38", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34037", "standardDeviation": "566.613", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "618607", "standardDeviation": "9880.87", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34170.9", "standardDeviation": "1020.33", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23417e+06", "standardDeviation": "20297.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35780.8", "standardDeviation": "10117", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47837e+06", "standardDeviation": "22643.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41941", "standardDeviation": "1566.43", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94549e+06", "standardDeviation": "4708.38", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123483", "standardDeviation": "4041.53", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..dfcaadf --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98705.7", "standardDeviation": "2140.62", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147997", "standardDeviation": "3306.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2254.19", "standardDeviation": "95.6142", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197397", "standardDeviation": "4146.18", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295069", "standardDeviation": "6047", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2338.23", "standardDeviation": "124.985", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394942", "standardDeviation": "7821.56", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589656", "standardDeviation": "11203.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2354.55", "standardDeviation": "211.908", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "797147", "standardDeviation": "52304.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17993e+06", "standardDeviation": "18799.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2391.6", "standardDeviation": "293.105", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56728e+06", "standardDeviation": "47124.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35826e+06", "standardDeviation": "23785.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2276.21", "standardDeviation": "136.207", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "136884", "standardDeviation": "1759.73", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156131", "standardDeviation": "64783.3", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2265.69", "standardDeviation": "65.4235", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "247756", "standardDeviation": "4066.62", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "302307", "standardDeviation": "4387.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2310.05", "standardDeviation": "159.663", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "550221", "standardDeviation": "5529.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "573773", "standardDeviation": "6426.33", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2367.86", "standardDeviation": "284.671", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12202e+06", "standardDeviation": "263057", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.19366e+06", "standardDeviation": "12125.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2293.09", "standardDeviation": "119.332", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.70899e+06", "standardDeviation": "104803", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.14588e+06", "standardDeviation": "15261.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2380.02", "standardDeviation": "615.62", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..15d7f99 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82300.4", "standardDeviation": "2381.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130544", "standardDeviation": "2128.41", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2434.21", "standardDeviation": "112.714", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164893", "standardDeviation": "3775.01", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263039", "standardDeviation": "5819.27", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2480.76", "standardDeviation": "179.722", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340571", "standardDeviation": "115234", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "539339", "standardDeviation": "34749.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2382.68", "standardDeviation": "129.107", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "663847", "standardDeviation": "11666.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04934e+06", "standardDeviation": "16840.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2359.49", "standardDeviation": "76.377", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32177e+06", "standardDeviation": "17455.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09371e+06", "standardDeviation": "21072.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2340.58", "standardDeviation": "83.7002", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "112881", "standardDeviation": "2270.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "133861", "standardDeviation": "2848.83", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2354.42", "standardDeviation": "82.5181", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "225983", "standardDeviation": "3890.08", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "266723", "standardDeviation": "5922.07", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2374.09", "standardDeviation": "85.8363", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "453263", "standardDeviation": "6590.72", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536278", "standardDeviation": "9732.47", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2465.28", "standardDeviation": "222.746", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "905122", "standardDeviation": "12415.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07176e+06", "standardDeviation": "16473.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2366.03", "standardDeviation": "81.1797", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.22008e+06", "standardDeviation": "19868.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.419e+06", "standardDeviation": "22797.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2364.67", "standardDeviation": "216.506", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151914/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..771d661 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Sep 24 16:26:39 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 30C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..34093c5 --- /dev/null +++ b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83034.1", "standardDeviation": "3906.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130988", "standardDeviation": "2367.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2624", "standardDeviation": "75.2565", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166417", "standardDeviation": "3197.98", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "261474", "standardDeviation": "4158.22", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2597.85", "standardDeviation": "94.7676", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "346221", "standardDeviation": "122817", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525415", "standardDeviation": "9853.23", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2513.96", "standardDeviation": "78.559", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "681310", "standardDeviation": "13726.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04888e+06", "standardDeviation": "17003", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2381.19", "standardDeviation": "142.543", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34635e+06", "standardDeviation": "34149", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.0943e+06", "standardDeviation": "21533.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2852.07", "standardDeviation": "108.575", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137013", "standardDeviation": "3387.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "165548", "standardDeviation": "67793.6", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2549.15", "standardDeviation": "81.9404", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "257945", "standardDeviation": "7782.66", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "281551", "standardDeviation": "8532.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2676.22", "standardDeviation": "295.156", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "511720", "standardDeviation": "31654.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "649515", "standardDeviation": "62270.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2697.61", "standardDeviation": "192.326", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "967018", "standardDeviation": "174248", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08725e+06", "standardDeviation": "29490.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2768.93", "standardDeviation": "114.367", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.46948e+06", "standardDeviation": "98214.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.71014e+06", "standardDeviation": "124884", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2752.58", "standardDeviation": "155.847", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..a50f625 Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..60a3a3e Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..1335f2f Binary files /dev/null and b/151914/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/divOperator.json b/151942/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..1c7fe36 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "254770", "standardDeviation": "7691.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "749657", "standardDeviation": "57694.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540037", "standardDeviation": "39849.9", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "757550", "standardDeviation": "52956.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "980229", "standardDeviation": "101080", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "847637", "standardDeviation": "68004.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83829e+06", "standardDeviation": "221485", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "891356", "standardDeviation": "84893.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.9844e+06", "standardDeviation": "273902", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "778551", "standardDeviation": "58489.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151942/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..3bfb315 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151942/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..6689174 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151942/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..d17ca87 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/field.json b/151942/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..a11b01c --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "105788", "standardDeviation": "5648.73", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92496.1", "standardDeviation": "9240.56", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "162830", "standardDeviation": "5065.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85235.8", "standardDeviation": "8319.25", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "471990", "standardDeviation": "38403.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "120021", "standardDeviation": "9689.81", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "816128", "standardDeviation": "86440.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133491", "standardDeviation": "7955.53", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54557e+06", "standardDeviation": "198791", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "156084", "standardDeviation": "5399.57", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "52036.9", "standardDeviation": "2482.03", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62024.6", "standardDeviation": "9032.87", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "168700", "standardDeviation": "4933.76", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62815.7", "standardDeviation": "13288.6", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "476121", "standardDeviation": "37750.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "102053", "standardDeviation": "8871.69", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "848383", "standardDeviation": "105712", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109054", "standardDeviation": "8514", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.5667e+06", "standardDeviation": "220620", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152854", "standardDeviation": "116861", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151942/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..7bd7163 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/field_relative.png b/151942/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..77574a3 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/field_time.png b/151942/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..9b96664 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/linear.json b/151942/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..3462b02 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "58227.2", "standardDeviation": "2561.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "56410.8", "standardDeviation": "1623.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1974.41", "standardDeviation": "1388.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206311", "standardDeviation": "6811.18", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "207673", "standardDeviation": "6960.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1996.78", "standardDeviation": "1670.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "344297", "standardDeviation": "19996.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "392099", "standardDeviation": "27046.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1940.89", "standardDeviation": "3032.24", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "710096", "standardDeviation": "88765.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "715331", "standardDeviation": "84193.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2325.69", "standardDeviation": "2937.68", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.2483e+06", "standardDeviation": "213167", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.25043e+06", "standardDeviation": "217199", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2119.98", "standardDeviation": "2518.24", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "205106", "standardDeviation": "7247.22", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "206101", "standardDeviation": "7947.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1772.77", "standardDeviation": "1149.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "383603", "standardDeviation": "26343.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "392721", "standardDeviation": "26360.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2033.96", "standardDeviation": "2094.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "710692", "standardDeviation": "82932.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "706841", "standardDeviation": "83166.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2484.41", "standardDeviation": "3203.93", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.22137e+06", "standardDeviation": "199456", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.25176e+06", "standardDeviation": "213386", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2193.77", "standardDeviation": "2589.75", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.67076e+06", "standardDeviation": "295961", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.6814e+06", "standardDeviation": "323430", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2377.76", "standardDeviation": "2716.63", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151942/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..9f87cdc Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151942/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..0628169 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/linear_time.png b/151942/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..427ad67 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151942/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..7fbe56d --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "249588", "standardDeviation": "7501.95", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "594811", "standardDeviation": "31778.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "539850", "standardDeviation": "38295.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "601995", "standardDeviation": "33981.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "986881", "standardDeviation": "101198", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "693265", "standardDeviation": "32450.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83027e+06", "standardDeviation": "260724", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "729815", "standardDeviation": "39046.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.86743e+06", "standardDeviation": "138459", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "773523", "standardDeviation": "40837.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/main/field.json b/151942/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..ba188c4 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "54525.3", "standardDeviation": "8997.29", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "80788.5", "standardDeviation": "12757.9", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "195076", "standardDeviation": "5208.86", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81602.9", "standardDeviation": "7849.33", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "549530", "standardDeviation": "50722", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119623", "standardDeviation": "24667", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "970167", "standardDeviation": "148520", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142376", "standardDeviation": "73554.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.73396e+06", "standardDeviation": "295347", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "166798", "standardDeviation": "89566.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "51870.9", "standardDeviation": "2271.28", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63164.8", "standardDeviation": "10626.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "191306", "standardDeviation": "5298.32", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "64719.5", "standardDeviation": "9625.29", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "529379", "standardDeviation": "43722.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "105660", "standardDeviation": "46309.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "975821", "standardDeviation": "148858", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122457", "standardDeviation": "77453.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.75596e+06", "standardDeviation": "295915", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149035", "standardDeviation": "78103.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/main/linear.json b/151942/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..4d07348 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40026.9", "standardDeviation": "2972.92", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "54945.4", "standardDeviation": "2674.71", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2021.46", "standardDeviation": "1502.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "207054", "standardDeviation": "6807.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "208990", "standardDeviation": "6863.04", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2095.66", "standardDeviation": "1986.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "349234", "standardDeviation": "22283.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "362641", "standardDeviation": "22002.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2770.81", "standardDeviation": "2935.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "614071", "standardDeviation": "70199", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "623391", "standardDeviation": "72628.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3117.22", "standardDeviation": "3278.11", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.09344e+06", "standardDeviation": "174930", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.09558e+06", "standardDeviation": "201538", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2866.29", "standardDeviation": "2341.03", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177656", "standardDeviation": "5689.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "179261", "standardDeviation": "6419.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2661.71", "standardDeviation": "2225.29", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "337329", "standardDeviation": "20256.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "340394", "standardDeviation": "21573.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2212.8", "standardDeviation": "1944.29", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "615700", "standardDeviation": "70215.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "611499", "standardDeviation": "69862.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3251.42", "standardDeviation": "3398.93", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09741e+06", "standardDeviation": "168544", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08959e+06", "standardDeviation": "177954", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2899.18", "standardDeviation": "2264.22", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.40088e+06", "standardDeviation": "238119", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.41553e+06", "standardDeviation": "254666", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4467.9", "standardDeviation": "8709.95", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151942/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..97d7a78 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33720.5", "standardDeviation": "5582.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "46211.6", "standardDeviation": "698.078", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2222.79", "standardDeviation": "1249.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "180063", "standardDeviation": "6179.92", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "182901", "standardDeviation": "6540.23", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2167.8", "standardDeviation": "1300.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340695", "standardDeviation": "21669.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "351719", "standardDeviation": "22438.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2194.44", "standardDeviation": "1926.62", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "628136", "standardDeviation": "66158", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "644272", "standardDeviation": "68391.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2148.06", "standardDeviation": "2886.93", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.1039e+06", "standardDeviation": "177134", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.12563e+06", "standardDeviation": "188181", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2713.51", "standardDeviation": "4521.16", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197406", "standardDeviation": "6027.08", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "196708", "standardDeviation": "5983.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2135.7", "standardDeviation": "1991.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "374823", "standardDeviation": "23223.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "371540", "standardDeviation": "24678.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2097.28", "standardDeviation": "1656.22", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "689743", "standardDeviation": "72533.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "633366", "standardDeviation": "116492", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2221.69", "standardDeviation": "2556.64", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.22998e+06", "standardDeviation": "188889", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.21375e+06", "standardDeviation": "194040", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2315.05", "standardDeviation": "2526.21", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.6156e+06", "standardDeviation": "275060", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.43768e+06", "standardDeviation": "301074", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2196.7", "standardDeviation": "2524.41", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/system-info.log b/151942/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151942/neon-cluster-meta-runner-neon-amd/upwind.json b/151942/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..9536e3d --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34049.9", "standardDeviation": "5210.42", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50419.9", "standardDeviation": "2529.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2280.09", "standardDeviation": "1438.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "181238", "standardDeviation": "5784.59", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "186137", "standardDeviation": "6028.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2315.09", "standardDeviation": "1422.39", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "338320", "standardDeviation": "75158", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "356185", "standardDeviation": "21228.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2746.43", "standardDeviation": "2047.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "635998", "standardDeviation": "65404.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "642615", "standardDeviation": "69587", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4152.99", "standardDeviation": "10883.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.12353e+06", "standardDeviation": "180513", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.0712e+06", "standardDeviation": "129242", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2698.37", "standardDeviation": "3631", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194676", "standardDeviation": "6065.72", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "202857", "standardDeviation": "6304.16", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2458.75", "standardDeviation": "1929.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "370334", "standardDeviation": "22814.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "375260", "standardDeviation": "24402.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2468.91", "standardDeviation": "1983.41", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "707037", "standardDeviation": "264146", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "696997", "standardDeviation": "76722.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2601.28", "standardDeviation": "3608.06", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.19051e+06", "standardDeviation": "188958", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.22841e+06", "standardDeviation": "199717", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2200.62", "standardDeviation": "2223.27", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.41805e+06", "standardDeviation": "294455", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.43342e+06", "standardDeviation": "289715", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2987.39", "standardDeviation": "3804.68", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151942/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..856ca44 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151942/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..055ff07 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151942/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..4e92755 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..6b81edb --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "392318", "standardDeviation": "3230.63", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "323686", "standardDeviation": "4659.19", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "767111", "standardDeviation": "4033.03", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281524", "standardDeviation": "3913.55", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03523e+06", "standardDeviation": "7059.75", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "282507", "standardDeviation": "2500.87", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.01845e+06", "standardDeviation": "9435.18", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "289029", "standardDeviation": "1968.81", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.48973e+06", "standardDeviation": "476616", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "314211", "standardDeviation": "2055.57", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..a28f71e Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..034f5f5 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..d20261e Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..aa99c14 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306552", "standardDeviation": "1345.83", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40474.2", "standardDeviation": "1727.83", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "637148", "standardDeviation": "2351.75", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46688.8", "standardDeviation": "3065.25", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.38666e+06", "standardDeviation": "57353.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "52521.5", "standardDeviation": "17022.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.76134e+06", "standardDeviation": "73155.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58990.9", "standardDeviation": "2035.51", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.59524e+06", "standardDeviation": "23384.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139743", "standardDeviation": "16075.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "308923", "standardDeviation": "3260.22", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36040.6", "standardDeviation": "792.722", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "616606", "standardDeviation": "4753.66", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35855.3", "standardDeviation": "458.351", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.22963e+06", "standardDeviation": "7360.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36086.2", "standardDeviation": "629.703", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47526e+06", "standardDeviation": "7370.48", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39173", "standardDeviation": "3752.76", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94349e+06", "standardDeviation": "4197.73", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130841", "standardDeviation": "3691.66", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..bd64542 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..a4e1e54 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..cb99166 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..d9feabb --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98406.5", "standardDeviation": "2006.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "148054", "standardDeviation": "1869.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2591.63", "standardDeviation": "530.791", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196663", "standardDeviation": "5075.84", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "298406", "standardDeviation": "56942.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2544.62", "standardDeviation": "80.8406", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394184", "standardDeviation": "7494.47", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "595968", "standardDeviation": "43684.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2518.07", "standardDeviation": "62.0962", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "789689", "standardDeviation": "16552.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.16668e+06", "standardDeviation": "8628.28", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2714.46", "standardDeviation": "2182.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.55171e+06", "standardDeviation": "63573", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.34963e+06", "standardDeviation": "7750.55", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2533.3", "standardDeviation": "296.872", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137863", "standardDeviation": "2075.1", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "157794", "standardDeviation": "93200.8", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2513.16", "standardDeviation": "65.8931", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "246865", "standardDeviation": "3724.97", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275409", "standardDeviation": "4703.64", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2554.78", "standardDeviation": "152.558", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "555647", "standardDeviation": "6013.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "569375", "standardDeviation": "6498.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2488.08", "standardDeviation": "184.53", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09959e+06", "standardDeviation": "6449.93", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18431e+06", "standardDeviation": "12697.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2466.62", "standardDeviation": "94.4901", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.73552e+06", "standardDeviation": "11074.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.82171e+06", "standardDeviation": "16884", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2632.6", "standardDeviation": "610.877", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..e517f84 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..81a3ea0 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..9767486 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..2f5ac8b --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "360513", "standardDeviation": "51733.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277585", "standardDeviation": "8147.29", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "533712", "standardDeviation": "17515.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "282284", "standardDeviation": "22863.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.04107e+06", "standardDeviation": "9368.19", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "297004", "standardDeviation": "138054", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.02215e+06", "standardDeviation": "19774.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "288457", "standardDeviation": "1855.15", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.29837e+06", "standardDeviation": "38551.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "314332", "standardDeviation": "19191.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..c0af29a --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "320543", "standardDeviation": "3936.28", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50657.3", "standardDeviation": "7892.38", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "687459", "standardDeviation": "20340", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "51592.9", "standardDeviation": "17695.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "937044", "standardDeviation": "25555.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47488.4", "standardDeviation": "1310.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83558e+06", "standardDeviation": "56157.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48072.4", "standardDeviation": "843.145", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.63722e+06", "standardDeviation": "89018.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "169386", "standardDeviation": "4566.23", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "310500", "standardDeviation": "3527.69", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32931.2", "standardDeviation": "964.814", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "619995", "standardDeviation": "7820.29", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38955.5", "standardDeviation": "1493.94", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23243e+06", "standardDeviation": "11305", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40799.7", "standardDeviation": "1146.52", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47621e+06", "standardDeviation": "6210.15", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41251.2", "standardDeviation": "1740.75", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.99175e+06", "standardDeviation": "333311", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "159835", "standardDeviation": "3846.85", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..01efe1d --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98758.1", "standardDeviation": "1799.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "146895", "standardDeviation": "1687.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2522.69", "standardDeviation": "499.831", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196434", "standardDeviation": "3680.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "296826", "standardDeviation": "29498", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2537.44", "standardDeviation": "83.6614", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394303", "standardDeviation": "7628.23", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "585457", "standardDeviation": "6312.88", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2545.68", "standardDeviation": "108.536", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "786462", "standardDeviation": "17773.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17213e+06", "standardDeviation": "13357.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2660.86", "standardDeviation": "1594.66", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.55587e+06", "standardDeviation": "58878.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.34698e+06", "standardDeviation": "18107.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2542.76", "standardDeviation": "94.1091", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "127847", "standardDeviation": "1814.79", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141543", "standardDeviation": "2455.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2438.51", "standardDeviation": "115.473", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "245054", "standardDeviation": "4692.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275623", "standardDeviation": "4837.39", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2480.39", "standardDeviation": "54.5905", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "502198", "standardDeviation": "7328.44", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "556199", "standardDeviation": "8195.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2594.52", "standardDeviation": "197.391", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0161e+06", "standardDeviation": "13057.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11569e+06", "standardDeviation": "14264.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2493.12", "standardDeviation": "103.035", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.71266e+06", "standardDeviation": "14442.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.8258e+06", "standardDeviation": "15542.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2466.13", "standardDeviation": "174.81", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..b5044fe --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82758.1", "standardDeviation": "3796.25", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130725", "standardDeviation": "1932.59", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2690.45", "standardDeviation": "81.7026", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164930", "standardDeviation": "3406.55", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262711", "standardDeviation": "5415.75", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2594.15", "standardDeviation": "140.097", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340449", "standardDeviation": "100237", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524547", "standardDeviation": "9956.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2622.28", "standardDeviation": "156.138", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "658879", "standardDeviation": "13154.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04704e+06", "standardDeviation": "16615.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2611.71", "standardDeviation": "176.372", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.31167e+06", "standardDeviation": "19286.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09467e+06", "standardDeviation": "35130.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2524.68", "standardDeviation": "220.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122546", "standardDeviation": "4177.13", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137599", "standardDeviation": "2804.73", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2694.16", "standardDeviation": "90.6074", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "244970", "standardDeviation": "5618.24", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "274345", "standardDeviation": "74099.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2618.99", "standardDeviation": "66.2385", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "492497", "standardDeviation": "6946.35", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "532024", "standardDeviation": "9906.33", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2651.34", "standardDeviation": "341.348", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "996690", "standardDeviation": "14829", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07619e+06", "standardDeviation": "13985.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2571.14", "standardDeviation": "275.674", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.43001e+06", "standardDeviation": "20612.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.53566e+06", "standardDeviation": "25218.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2520.2", "standardDeviation": "236.123", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151942/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..8615dc9 --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Sep 24 17:54:04 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 29C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..db0485f --- /dev/null +++ b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82140.7", "standardDeviation": "1975.38", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131573", "standardDeviation": "2939.47", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2640.42", "standardDeviation": "90.9026", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170694", "standardDeviation": "55057.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262434", "standardDeviation": "5398.03", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2605.2", "standardDeviation": "139.118", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "328792", "standardDeviation": "6641.12", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524188", "standardDeviation": "9500.88", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2572.28", "standardDeviation": "146.737", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "656874", "standardDeviation": "11926.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05227e+06", "standardDeviation": "40639.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2750.05", "standardDeviation": "271.209", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33485e+06", "standardDeviation": "37872.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09616e+06", "standardDeviation": "19618.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3059.37", "standardDeviation": "115.266", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170986", "standardDeviation": "5613.03", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "184271", "standardDeviation": "5451.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3026.54", "standardDeviation": "88.6586", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "309778", "standardDeviation": "16019.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "339546", "standardDeviation": "120326", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3069.3", "standardDeviation": "260.214", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "610867", "standardDeviation": "59785.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "642803", "standardDeviation": "63080", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3064.37", "standardDeviation": "355.926", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.14068e+06", "standardDeviation": "175564", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.1859e+06", "standardDeviation": "124284", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2982.86", "standardDeviation": "214.754", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.42417e+06", "standardDeviation": "269214", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.69151e+06", "standardDeviation": "191338", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3009.39", "standardDeviation": "224.118", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..44d791e Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..1c69a90 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..bd85ef1 Binary files /dev/null and b/151942/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/divOperator.json b/151960/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..9bb0d81 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "224944", "standardDeviation": "4690.79", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "555206", "standardDeviation": "54386.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "464230", "standardDeviation": "34316.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "549986", "standardDeviation": "30948.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "887273", "standardDeviation": "28313.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "654303", "standardDeviation": "32876.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.97847e+06", "standardDeviation": "241593", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "688120", "standardDeviation": "34794.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.03394e+06", "standardDeviation": "264277", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "710863", "standardDeviation": "30010.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/151960/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..73c04c8 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/151960/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..8913440 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/151960/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..baa0c95 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/field.json b/151960/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..82c4811 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "93150", "standardDeviation": "4469.94", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88199.7", "standardDeviation": "13643.9", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "146524", "standardDeviation": "5635.12", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "74575", "standardDeviation": "8297.18", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "383623", "standardDeviation": "15478.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109969", "standardDeviation": "9077.89", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "762697", "standardDeviation": "54955.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124374", "standardDeviation": "33228.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.43854e+06", "standardDeviation": "121246", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147168", "standardDeviation": "3279.23", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "44246", "standardDeviation": "1597.26", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59196.9", "standardDeviation": "11076.1", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "160482", "standardDeviation": "3848.57", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60287.9", "standardDeviation": "8459.26", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "392433", "standardDeviation": "18028.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "95546.1", "standardDeviation": "11700.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "730745", "standardDeviation": "32248.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104922", "standardDeviation": "40361.1", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.46898e+06", "standardDeviation": "103858", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "134186", "standardDeviation": "5818.67", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/field_fvops.png b/151960/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..296bafb Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/field_relative.png b/151960/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..ec2b55a Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/field_time.png b/151960/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..94b53f2 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/linear.json b/151960/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..9f6d976 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43379.8", "standardDeviation": "3392.28", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51894.8", "standardDeviation": "1798.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1437.66", "standardDeviation": "1020.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164276", "standardDeviation": "3647.84", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "157460", "standardDeviation": "3563.61", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1481.61", "standardDeviation": "1318.71", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "311670", "standardDeviation": "94835.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "331115", "standardDeviation": "17654.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1472.59", "standardDeviation": "1483.67", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "588254", "standardDeviation": "47449.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "550312", "standardDeviation": "31281.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1756.32", "standardDeviation": "2674.74", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.11855e+06", "standardDeviation": "99616.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.13742e+06", "standardDeviation": "127169", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1560.47", "standardDeviation": "1724.05", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182556", "standardDeviation": "4930.86", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "209204", "standardDeviation": "6942.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1465.18", "standardDeviation": "1505.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "333415", "standardDeviation": "15247", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "338060", "standardDeviation": "25739.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1486.19", "standardDeviation": "1285.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "584016", "standardDeviation": "48886.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "596070", "standardDeviation": "49976.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1773.97", "standardDeviation": "2587.09", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.06435e+06", "standardDeviation": "54067.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18351e+06", "standardDeviation": "153854", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1601.58", "standardDeviation": "1733.91", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.54569e+06", "standardDeviation": "157070", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.5086e+06", "standardDeviation": "215405", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1721.02", "standardDeviation": "2372.33", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/151960/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..ce8bca0 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/linear_relative.png b/151960/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..74a4782 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/linear_time.png b/151960/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..27cf1dc Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/151960/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..01470fc --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "245831", "standardDeviation": "6445.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "544124", "standardDeviation": "23924.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "587672", "standardDeviation": "131084", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "564826", "standardDeviation": "27096.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.02693e+06", "standardDeviation": "97024.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "658699", "standardDeviation": "136273", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.95512e+06", "standardDeviation": "206970", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "733810", "standardDeviation": "8416.08", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.12391e+06", "standardDeviation": "364030", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "740059", "standardDeviation": "33044.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/main/field.json b/151960/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..114b20d --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51016.2", "standardDeviation": "6127.19", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72599.9", "standardDeviation": "8551.31", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "174415", "standardDeviation": "20834.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78343.5", "standardDeviation": "7799.43", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445450", "standardDeviation": "31479", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "110428", "standardDeviation": "12262.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "963544", "standardDeviation": "144995", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118977", "standardDeviation": "24461.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.49419e+06", "standardDeviation": "128184", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144713", "standardDeviation": "21812.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "49470.8", "standardDeviation": "2756.85", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58970.5", "standardDeviation": "11373.6", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "183916", "standardDeviation": "4909.34", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60906.7", "standardDeviation": "9324.83", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "470752", "standardDeviation": "88793.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88454.5", "standardDeviation": "9819.65", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "789711", "standardDeviation": "71604.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104321", "standardDeviation": "46591.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.47776e+06", "standardDeviation": "104597", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126506", "standardDeviation": "5577.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/main/linear.json b/151960/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..e5377ed --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44724.6", "standardDeviation": "2222.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52531.5", "standardDeviation": "872.992", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1576.36", "standardDeviation": "1393.04", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "145661", "standardDeviation": "4280.03", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "165895", "standardDeviation": "5792.64", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1581.86", "standardDeviation": "1836.39", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "300282", "standardDeviation": "15824.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "301727", "standardDeviation": "15951.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1624.88", "standardDeviation": "1758.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "584612", "standardDeviation": "61654", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589544", "standardDeviation": "62241.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1774.19", "standardDeviation": "2630.39", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.0522e+06", "standardDeviation": "147552", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "980913", "standardDeviation": "99561.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1778.27", "standardDeviation": "3069.54", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164982", "standardDeviation": "4834.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "146925", "standardDeviation": "3133.25", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1561.36", "standardDeviation": "1446.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "312914", "standardDeviation": "18779.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275410", "standardDeviation": "13898", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1527.56", "standardDeviation": "1372.49", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "611443", "standardDeviation": "69444.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "579440", "standardDeviation": "222166", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1725.23", "standardDeviation": "2262.16", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "975280", "standardDeviation": "55307.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.05359e+06", "standardDeviation": "146814", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1743.71", "standardDeviation": "2658.19", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.45013e+06", "standardDeviation": "127260", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.36293e+06", "standardDeviation": "174261", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1749.7", "standardDeviation": "1960.95", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/main/upwind.json b/151960/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..00e6fa4 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34981.3", "standardDeviation": "7804.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "47617", "standardDeviation": "1370.73", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1683.95", "standardDeviation": "1421.69", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163904", "standardDeviation": "5390.96", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "150655", "standardDeviation": "2957.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1541.24", "standardDeviation": "1362.28", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "316617", "standardDeviation": "74662", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299929", "standardDeviation": "13491.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1763.29", "standardDeviation": "2913.38", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "639395", "standardDeviation": "66974.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "645165", "standardDeviation": "68869.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3576.68", "standardDeviation": "13799.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "881932", "standardDeviation": "83948.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "914552", "standardDeviation": "114501", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1695.92", "standardDeviation": "2114.49", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "153614", "standardDeviation": "4012.58", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "199867", "standardDeviation": "6591.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1654.17", "standardDeviation": "2436.06", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "370898", "standardDeviation": "23250.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "381491", "standardDeviation": "24486.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1762.58", "standardDeviation": "2004.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "769481", "standardDeviation": "559746", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "492478", "standardDeviation": "26737.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1552.31", "standardDeviation": "2382.99", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.04187e+06", "standardDeviation": "86050.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.02751e+06", "standardDeviation": "100209", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1510.38", "standardDeviation": "1835.92", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.40372e+06", "standardDeviation": "129632", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.41976e+06", "standardDeviation": "192059", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1768.91", "standardDeviation": "2477.58", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/system-info.log b/151960/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/151960/neon-cluster-meta-runner-neon-amd/upwind.json b/151960/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..789edea --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49325.8", "standardDeviation": "1733.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "43848.8", "standardDeviation": "964.61", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1531.72", "standardDeviation": "1046.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129962", "standardDeviation": "1654", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115088", "standardDeviation": "1334.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1471.17", "standardDeviation": "968.141", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "252627", "standardDeviation": "10716.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "219281", "standardDeviation": "8418.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1540.29", "standardDeviation": "1427.94", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "472769", "standardDeviation": "31514.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "433338", "standardDeviation": "62775.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1618.43", "standardDeviation": "2818.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "863613", "standardDeviation": "89226.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "859612", "standardDeviation": "85763.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1607.94", "standardDeviation": "1889.91", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "141268", "standardDeviation": "2061.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "130493", "standardDeviation": "1901.41", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1501.89", "standardDeviation": "1316.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "277510", "standardDeviation": "8787.94", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "266603", "standardDeviation": "7786.96", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1521.12", "standardDeviation": "1458.18", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "500006", "standardDeviation": "22080.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "476608", "standardDeviation": "20380.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1958.63", "standardDeviation": "4329.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "977804", "standardDeviation": "44023.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "979771", "standardDeviation": "81107.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1587.26", "standardDeviation": "1871.82", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.29372e+06", "standardDeviation": "84822", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.32076e+06", "standardDeviation": "127672", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1664.93", "standardDeviation": "2174.06", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/151960/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..432c25e Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/151960/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..7f8136d Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-amd/upwind_time.png b/151960/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..2a70af2 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..3617f7b --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "273723", "standardDeviation": "2815.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "267252", "standardDeviation": "3901.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540301", "standardDeviation": "5398.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "270650", "standardDeviation": "3796.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05781e+06", "standardDeviation": "7364.09", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272923", "standardDeviation": "4087.59", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.08133e+06", "standardDeviation": "18761.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279430", "standardDeviation": "3662.05", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.33421e+06", "standardDeviation": "6752.21", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "304174", "standardDeviation": "3281.21", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..9404b75 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..591b6dd Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..4f5de90 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..f4b1b4b --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "319913", "standardDeviation": "4823.59", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "45725.5", "standardDeviation": "700.406", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "690640", "standardDeviation": "16824.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46229.7", "standardDeviation": "2046.18", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.386e+06", "standardDeviation": "56013.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47429.9", "standardDeviation": "2593.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.77671e+06", "standardDeviation": "68465.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "55097.2", "standardDeviation": "1685.45", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.51241e+06", "standardDeviation": "97994.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127599", "standardDeviation": "2196.17", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309439", "standardDeviation": "4345.13", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34157.2", "standardDeviation": "903.666", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "617055", "standardDeviation": "7408.18", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34833.3", "standardDeviation": "686.761", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23231e+06", "standardDeviation": "15336.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34145.6", "standardDeviation": "699.365", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47365e+06", "standardDeviation": "6250.72", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41971.4", "standardDeviation": "1990.57", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94012e+06", "standardDeviation": "1456.49", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123449", "standardDeviation": "3570.95", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..d9f4fa5 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..91e3ca9 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..5d8923f Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..580f54d --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98877.4", "standardDeviation": "2773.17", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147551", "standardDeviation": "3051.02", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2573.33", "standardDeviation": "110.246", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198272", "standardDeviation": "4896.61", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295313", "standardDeviation": "6076.32", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2381.38", "standardDeviation": "64.0945", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "408994", "standardDeviation": "135998", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588541", "standardDeviation": "10829.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2446.12", "standardDeviation": "163.508", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "789053", "standardDeviation": "13934", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17869e+06", "standardDeviation": "17356", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2555.68", "standardDeviation": "66.2411", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58168e+06", "standardDeviation": "20159.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35077e+06", "standardDeviation": "20207.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2676.36", "standardDeviation": "341.032", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "148469", "standardDeviation": "3350.89", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156310", "standardDeviation": "65154.5", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2398.1", "standardDeviation": "157.094", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "266290", "standardDeviation": "8556.05", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "304610", "standardDeviation": "6824.26", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2269.58", "standardDeviation": "130.524", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "536412", "standardDeviation": "15684", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "589631", "standardDeviation": "23334.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2358.17", "standardDeviation": "206.017", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.15078e+06", "standardDeviation": "259156", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.14604e+06", "standardDeviation": "41502.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2669.52", "standardDeviation": "106.663", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.6571e+06", "standardDeviation": "106052", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.20535e+06", "standardDeviation": "61888.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2650.9", "standardDeviation": "306.61", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..43796bf Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..a863515 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..15c82a9 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..13e3c13 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "271252", "standardDeviation": "3578.39", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "268035", "standardDeviation": "8475.44", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "531881", "standardDeviation": "6304.87", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272633", "standardDeviation": "21513.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03093e+06", "standardDeviation": "9958.73", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275252", "standardDeviation": "22027.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.02543e+06", "standardDeviation": "19973.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279565", "standardDeviation": "3824.03", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.166e+06", "standardDeviation": "16952.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "304429", "standardDeviation": "2921.86", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..7e12b75 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "307143", "standardDeviation": "1513.07", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40970.9", "standardDeviation": "684.341", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "453316", "standardDeviation": "7273.91", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43440.4", "standardDeviation": "814.139", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "910285", "standardDeviation": "15915.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "44008.2", "standardDeviation": "1156.05", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80584e+06", "standardDeviation": "28849.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "44086.5", "standardDeviation": "691.974", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.61343e+06", "standardDeviation": "29232.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "146806", "standardDeviation": "17291.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "309930", "standardDeviation": "3955.52", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37009.4", "standardDeviation": "1388.68", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "618382", "standardDeviation": "7475.76", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37270.3", "standardDeviation": "1203.46", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.23319e+06", "standardDeviation": "14574.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37675.8", "standardDeviation": "8998.24", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.47474e+06", "standardDeviation": "7283.38", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38000.2", "standardDeviation": "2826.88", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.94757e+06", "standardDeviation": "3435.06", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133879", "standardDeviation": "2294.15", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..9084d48 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "142749", "standardDeviation": "2272.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "213802", "standardDeviation": "5296.72", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3036.46", "standardDeviation": "92.4509", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "293745", "standardDeviation": "2491.72", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "427432", "standardDeviation": "1804.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2309.14", "standardDeviation": "55.7564", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "407415", "standardDeviation": "129943", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "586487", "standardDeviation": "7462.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2302.81", "standardDeviation": "69.0798", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "809716", "standardDeviation": "210062", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17459e+06", "standardDeviation": "13682.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2391.03", "standardDeviation": "699.473", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.54187e+06", "standardDeviation": "78428.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.34481e+06", "standardDeviation": "16754.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2650.99", "standardDeviation": "2474.44", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "136664", "standardDeviation": "1361.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "144644", "standardDeviation": "2075.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2233.62", "standardDeviation": "108.882", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "271653", "standardDeviation": "2709.87", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "299391", "standardDeviation": "4067.48", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2306.89", "standardDeviation": "99.9486", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "553825", "standardDeviation": "7691.54", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "592701", "standardDeviation": "6817.97", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2360.8", "standardDeviation": "121.31", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09638e+06", "standardDeviation": "8398.86", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18713e+06", "standardDeviation": "11340.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2515.26", "standardDeviation": "2049.78", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.70801e+06", "standardDeviation": "18682.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.00149e+06", "standardDeviation": "13190.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2316.55", "standardDeviation": "165.033", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..fa00e44 --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "81867.8", "standardDeviation": "2173.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131564", "standardDeviation": "2773.91", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2405.47", "standardDeviation": "79.8094", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164163", "standardDeviation": "3503.82", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262772", "standardDeviation": "5435.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2414.45", "standardDeviation": "74.9735", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340331", "standardDeviation": "113048", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524204", "standardDeviation": "10052.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2422.34", "standardDeviation": "90.3529", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "661686", "standardDeviation": "11317.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04657e+06", "standardDeviation": "15547.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2501.11", "standardDeviation": "204.283", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32151e+06", "standardDeviation": "17223.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09191e+06", "standardDeviation": "20256.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2432.08", "standardDeviation": "147.031", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "112983", "standardDeviation": "2453.63", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "134382", "standardDeviation": "4634.84", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2357.8", "standardDeviation": "134.757", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "217572", "standardDeviation": "3954.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "266339", "standardDeviation": "4929.54", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2373.4", "standardDeviation": "76.7432", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "454423", "standardDeviation": "6404.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "531519", "standardDeviation": "10069", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2380.82", "standardDeviation": "117.122", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "915986", "standardDeviation": "10350.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06767e+06", "standardDeviation": "14288.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2390.03", "standardDeviation": "103.161", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.80029e+06", "standardDeviation": "17892.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.20121e+06", "standardDeviation": "26581.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2487.59", "standardDeviation": "171.958", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/151960/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..5bba3be --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Sep 24 19:41:40 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 29C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..229714f --- /dev/null +++ b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82079.4", "standardDeviation": "2411.25", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131232", "standardDeviation": "2819.09", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2387.73", "standardDeviation": "80.0603", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "165760", "standardDeviation": "3536.97", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262477", "standardDeviation": "5280.58", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2475.76", "standardDeviation": "103.123", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "340988", "standardDeviation": "114127", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "523952", "standardDeviation": "10460.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2415.03", "standardDeviation": "152.638", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "663762", "standardDeviation": "10922.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.0478e+06", "standardDeviation": "16129.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2461.64", "standardDeviation": "129.007", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32309e+06", "standardDeviation": "17471.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09295e+06", "standardDeviation": "22187.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2446.36", "standardDeviation": "584.456", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "116920", "standardDeviation": "1763.61", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "134322", "standardDeviation": "2907.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2376.7", "standardDeviation": "159.935", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "246550", "standardDeviation": "5769.34", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278932", "standardDeviation": "86167.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2379.02", "standardDeviation": "87.7669", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "498948", "standardDeviation": "8455.79", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "556472", "standardDeviation": "13777.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2411.45", "standardDeviation": "345.856", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "995019", "standardDeviation": "15444.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.1219e+06", "standardDeviation": "23599.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2390.53", "standardDeviation": "122.067", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.37547e+06", "standardDeviation": "22773.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.64561e+06", "standardDeviation": "46647.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2404.13", "standardDeviation": "306.453", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..5fb4448 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..f8ffb53 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..1522621 Binary files /dev/null and b/151960/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/divOperator.json b/153953/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..17b9a84 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "280934", "standardDeviation": "10056.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "602779", "standardDeviation": "38005.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "606980", "standardDeviation": "53911.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "601174", "standardDeviation": "42540.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.08408e+06", "standardDeviation": "136137", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "695970", "standardDeviation": "46407.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98398e+06", "standardDeviation": "250769", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "728770", "standardDeviation": "43596.7", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.11263e+06", "standardDeviation": "349464", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "771284", "standardDeviation": "36340.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/153953/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..5316b31 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/153953/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..56806f4 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/153953/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..f1b4361 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/field.json b/153953/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..bcc0778 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "97861.5", "standardDeviation": "6700.03", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92942.2", "standardDeviation": "8970.07", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "175161", "standardDeviation": "4538.58", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85457.6", "standardDeviation": "8334.59", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "469272", "standardDeviation": "38538.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121666", "standardDeviation": "9929.68", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "849028", "standardDeviation": "105798", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131700", "standardDeviation": "40761.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55177e+06", "standardDeviation": "208740", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "168219", "standardDeviation": "93289.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "50088.6", "standardDeviation": "1999.92", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62501.4", "standardDeviation": "9766.14", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "184043", "standardDeviation": "39511.7", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "65956.7", "standardDeviation": "8850.28", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "473054", "standardDeviation": "38584.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103739", "standardDeviation": "10120", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "754354", "standardDeviation": "51975.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119628", "standardDeviation": "29970.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55508e+06", "standardDeviation": "211377", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152829", "standardDeviation": "76511.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/field_fvops.png b/153953/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..d8d13cb Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/field_relative.png b/153953/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..9be75bf Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/field_time.png b/153953/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..bbcc693 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/linear.json b/153953/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..83c877f --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51993", "standardDeviation": "2626.3", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52986.5", "standardDeviation": "3175.13", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2116.44", "standardDeviation": "1463.89", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176247", "standardDeviation": "5916.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "180704", "standardDeviation": "5765.12", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2158.86", "standardDeviation": "1889.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332444", "standardDeviation": "21620.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "340823", "standardDeviation": "21747.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1968.83", "standardDeviation": "2400.15", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "614860", "standardDeviation": "69056.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "615857", "standardDeviation": "70581.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2327.48", "standardDeviation": "3936.72", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.09164e+06", "standardDeviation": "178778", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.09016e+06", "standardDeviation": "183030", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2112.12", "standardDeviation": "2395.22", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176443", "standardDeviation": "5882.43", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "179734", "standardDeviation": "5397.23", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1835.63", "standardDeviation": "1745.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "334682", "standardDeviation": "21590.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "341976", "standardDeviation": "30521.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1959.2", "standardDeviation": "2248.43", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "616126", "standardDeviation": "70253.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "620480", "standardDeviation": "71955.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2225.64", "standardDeviation": "2790.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0944e+06", "standardDeviation": "168723", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09522e+06", "standardDeviation": "179127", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2231.14", "standardDeviation": "2330.87", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.52049e+06", "standardDeviation": "240984", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.54186e+06", "standardDeviation": "230686", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2089.15", "standardDeviation": "2639.97", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/153953/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..b6cf191 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/linear_relative.png b/153953/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..f9ebfce Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/linear_time.png b/153953/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..0a42de4 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/153953/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..ce96649 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "283473", "standardDeviation": "39396", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "604669", "standardDeviation": "37753.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "601382", "standardDeviation": "47396", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "620505", "standardDeviation": "40932.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.13186e+06", "standardDeviation": "126666", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699873", "standardDeviation": "35720.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.95379e+06", "standardDeviation": "207876", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "740652", "standardDeviation": "43861.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.01197e+06", "standardDeviation": "340276", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "784224", "standardDeviation": "39745.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/main/field.json b/153953/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..41e897c --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50274.9", "standardDeviation": "3264.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78635.4", "standardDeviation": "8944.09", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "198597", "standardDeviation": "7154.5", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81220.9", "standardDeviation": "8515.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "541115", "standardDeviation": "49428.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121895", "standardDeviation": "34720.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "960912", "standardDeviation": "144536", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "141183", "standardDeviation": "92813.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71439e+06", "standardDeviation": "271527", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "165453", "standardDeviation": "125091", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "49658.8", "standardDeviation": "2872.98", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63931.1", "standardDeviation": "10095.8", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "204091", "standardDeviation": "6764.19", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "65596.8", "standardDeviation": "9599", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540318", "standardDeviation": "51221.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "110664", "standardDeviation": "63772.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "972291", "standardDeviation": "145226", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126722", "standardDeviation": "116939", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74022e+06", "standardDeviation": "279528", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151657", "standardDeviation": "120762", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/main/linear.json b/153953/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..bfbbd71 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51824.3", "standardDeviation": "3023.85", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "53390.3", "standardDeviation": "1196.51", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1996.17", "standardDeviation": "1463.52", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "173814", "standardDeviation": "6321.62", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "179409", "standardDeviation": "5808.01", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2143.13", "standardDeviation": "1862.91", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "337279", "standardDeviation": "19877.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "333920", "standardDeviation": "22914.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2073.34", "standardDeviation": "1813.64", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "634875", "standardDeviation": "260418", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "617984", "standardDeviation": "70840.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2390.73", "standardDeviation": "3114.38", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.09027e+06", "standardDeviation": "174337", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08686e+06", "standardDeviation": "181743", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2607.64", "standardDeviation": "3655.36", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "230635", "standardDeviation": "5645.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "209552", "standardDeviation": "8119.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2230.42", "standardDeviation": "1658.45", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "392834", "standardDeviation": "26700.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "399951", "standardDeviation": "26684.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2235.2", "standardDeviation": "2692.52", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "722019", "standardDeviation": "84770", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "728700", "standardDeviation": "82527.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.55", "standardDeviation": "3626.88", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.26983e+06", "standardDeviation": "211462", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28694e+06", "standardDeviation": "206036", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2795.51", "standardDeviation": "3805.64", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.75864e+06", "standardDeviation": "278975", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.63306e+06", "standardDeviation": "254742", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2729.27", "standardDeviation": "3179.17", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/main/upwind.json b/153953/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..3b56dac --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "47842.9", "standardDeviation": "5663.83", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44900.8", "standardDeviation": "935.892", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2384.01", "standardDeviation": "1829.36", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "152331", "standardDeviation": "4023.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "158494", "standardDeviation": "4687.51", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2196.84", "standardDeviation": "1272.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "297970", "standardDeviation": "17474.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "302098", "standardDeviation": "18531.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2183.38", "standardDeviation": "2052.19", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "518319", "standardDeviation": "48982.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "553795", "standardDeviation": "69308.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2410.77", "standardDeviation": "3102.25", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "977484", "standardDeviation": "153948", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "982176", "standardDeviation": "162386", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2441.05", "standardDeviation": "2591.69", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169889", "standardDeviation": "5278.63", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "170581", "standardDeviation": "5403.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2284.65", "standardDeviation": "1844.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "328698", "standardDeviation": "16710.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "328657", "standardDeviation": "18106.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2145.49", "standardDeviation": "1660.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "608336", "standardDeviation": "56854.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "595923", "standardDeviation": "61018.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2285.59", "standardDeviation": "2840.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.14413e+06", "standardDeviation": "86917.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.17081e+06", "standardDeviation": "107687", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2009.35", "standardDeviation": "2033.61", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34789e+06", "standardDeviation": "239888", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.23139e+06", "standardDeviation": "231218", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2604.26", "standardDeviation": "2881.07", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/system-info.log b/153953/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/153953/neon-cluster-meta-runner-neon-amd/upwind.json b/153953/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..99e0571 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44015.1", "standardDeviation": "7502.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52893.9", "standardDeviation": "2115.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2228.13", "standardDeviation": "1866.65", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "180137", "standardDeviation": "5376", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "183611", "standardDeviation": "5933.28", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2147.51", "standardDeviation": "1303.35", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "351249", "standardDeviation": "70568.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "352148", "standardDeviation": "21770.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2654.84", "standardDeviation": "1809.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "627616", "standardDeviation": "66896.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "641665", "standardDeviation": "68716.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3399.89", "standardDeviation": "8647.59", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.11632e+06", "standardDeviation": "187004", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.12439e+06", "standardDeviation": "190648", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2480.65", "standardDeviation": "2895.25", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197404", "standardDeviation": "6429.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "202227", "standardDeviation": "8639.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2198.5", "standardDeviation": "1915.24", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "376759", "standardDeviation": "22973.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "370924", "standardDeviation": "24013.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2053.46", "standardDeviation": "1778.49", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "694104", "standardDeviation": "189926", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "671725", "standardDeviation": "75684.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2580.54", "standardDeviation": "2769.37", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.22251e+06", "standardDeviation": "191589", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.20813e+06", "standardDeviation": "196404", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2183.32", "standardDeviation": "2457.61", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.57867e+06", "standardDeviation": "301290", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.46826e+06", "standardDeviation": "284298", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2319.36", "standardDeviation": "3141.67", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/153953/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..65c3689 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/153953/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..2f486d4 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-amd/upwind_time.png b/153953/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..10b0161 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..6409c70 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "274705", "standardDeviation": "3611.47", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "325798", "standardDeviation": "17257.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "767726", "standardDeviation": "4293.32", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "325928", "standardDeviation": "3179.07", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.49274e+06", "standardDeviation": "10548.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "327875", "standardDeviation": "2497.94", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.90812e+06", "standardDeviation": "39473.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "335014", "standardDeviation": "3491.91", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.37818e+06", "standardDeviation": "431211", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "314713", "standardDeviation": "5617.75", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..e7e4bf0 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..d7feeac Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..067f345 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..3cee578 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "194439", "standardDeviation": "2756.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42549.7", "standardDeviation": "4633.66", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "412029", "standardDeviation": "3740.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43302.7", "standardDeviation": "10203.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "835930", "standardDeviation": "5430.64", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43000.3", "standardDeviation": "968.175", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.66571e+06", "standardDeviation": "10594.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43222.7", "standardDeviation": "896.126", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.35951e+06", "standardDeviation": "17502.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137535", "standardDeviation": "2507.79", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "249508", "standardDeviation": "35953.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36291.5", "standardDeviation": "784.054", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "490792", "standardDeviation": "4089.78", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36242.6", "standardDeviation": "882.228", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "977368", "standardDeviation": "6234.78", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36147.2", "standardDeviation": "621.41", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98234e+06", "standardDeviation": "148297", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39474.5", "standardDeviation": "3720.62", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.93415e+06", "standardDeviation": "9915.54", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131218", "standardDeviation": "3589.89", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..ad2ab95 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..ff1a47b Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..f126d4d Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..49120a7 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99350.4", "standardDeviation": "2476.74", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147149", "standardDeviation": "2547.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2621.64", "standardDeviation": "575.799", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198230", "standardDeviation": "4194.31", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "296254", "standardDeviation": "32503.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2550.33", "standardDeviation": "128.513", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "395930", "standardDeviation": "7837.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "585009", "standardDeviation": "5729.82", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2578.2", "standardDeviation": "182.045", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "791095", "standardDeviation": "12966.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.16799e+06", "standardDeviation": "9202.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2804.35", "standardDeviation": "2706.23", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58207e+06", "standardDeviation": "18687.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35285e+06", "standardDeviation": "18278.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2683.83", "standardDeviation": "366.487", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138601", "standardDeviation": "2072.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150894", "standardDeviation": "2663.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2529.29", "standardDeviation": "112.173", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "276055", "standardDeviation": "3870.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "298661", "standardDeviation": "4723.48", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2627.47", "standardDeviation": "134.087", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "553305", "standardDeviation": "5783.48", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "597550", "standardDeviation": "7220.12", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2655.52", "standardDeviation": "253.296", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09058e+06", "standardDeviation": "6246.18", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.17893e+06", "standardDeviation": "11526.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2533.64", "standardDeviation": "91.1401", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.7322e+06", "standardDeviation": "13046.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.96062e+06", "standardDeviation": "14734.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2509.98", "standardDeviation": "139.87", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..14c23b0 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..dec86b1 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..8ec5001 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..6ad0d2a --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "275772", "standardDeviation": "23750.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275676", "standardDeviation": "2665.32", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "532595", "standardDeviation": "5425.93", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279587", "standardDeviation": "4348.94", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.03419e+06", "standardDeviation": "8926.84", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281627", "standardDeviation": "4011.12", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.03056e+06", "standardDeviation": "27521.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "288745", "standardDeviation": "4132.63", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.26037e+06", "standardDeviation": "27598.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "313633", "standardDeviation": "3511.46", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..e107636 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "282355", "standardDeviation": "2460.63", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40234", "standardDeviation": "2043.99", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "587388", "standardDeviation": "2236.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47321.5", "standardDeviation": "2392.23", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.19867e+06", "standardDeviation": "1697.44", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42281.2", "standardDeviation": "630.959", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.66703e+06", "standardDeviation": "22573.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43508.4", "standardDeviation": "910.574", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.34553e+06", "standardDeviation": "15228.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "138711", "standardDeviation": "12045.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "246079", "standardDeviation": "2503.09", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35454.7", "standardDeviation": "610.671", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "490150", "standardDeviation": "4185.41", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35871.6", "standardDeviation": "964.613", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "977715", "standardDeviation": "6366.58", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35705.7", "standardDeviation": "586.904", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.96062e+06", "standardDeviation": "20965", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39720.7", "standardDeviation": "3909.87", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.92736e+06", "standardDeviation": "9034.55", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131056", "standardDeviation": "4002.31", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..34f3d66 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98853.5", "standardDeviation": "2652.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147420", "standardDeviation": "3098.56", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2587.65", "standardDeviation": "505.331", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197535", "standardDeviation": "4745.75", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "301181", "standardDeviation": "61758.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2576.64", "standardDeviation": "138.411", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394442", "standardDeviation": "7714.83", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589509", "standardDeviation": "11119.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2605.09", "standardDeviation": "188.469", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "790643", "standardDeviation": "15017.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17724e+06", "standardDeviation": "16955.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2597.23", "standardDeviation": "1093.82", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.54966e+06", "standardDeviation": "78597.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.36577e+06", "standardDeviation": "86640.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2612.62", "standardDeviation": "271.01", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "135628", "standardDeviation": "1965.79", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "149946", "standardDeviation": "2650.59", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2593.04", "standardDeviation": "125.024", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "277896", "standardDeviation": "3790.64", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275549", "standardDeviation": "5331.33", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2523.26", "standardDeviation": "87.7757", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "557108", "standardDeviation": "5746.33", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "589979", "standardDeviation": "7594.44", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2492.62", "standardDeviation": "199.21", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09855e+06", "standardDeviation": "7229.66", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.19109e+06", "standardDeviation": "9171.82", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2518.43", "standardDeviation": "235.181", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.69252e+06", "standardDeviation": "16467", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.84464e+06", "standardDeviation": "19685.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2531.13", "standardDeviation": "593.246", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..b3ca7b3 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82275.4", "standardDeviation": "2292.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131914", "standardDeviation": "3250.07", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2726.11", "standardDeviation": "140.708", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170449", "standardDeviation": "56148.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262943", "standardDeviation": "5445.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2677.52", "standardDeviation": "100.345", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "330718", "standardDeviation": "6388.61", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "525352", "standardDeviation": "10231.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2632.93", "standardDeviation": "161.924", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "663820", "standardDeviation": "13068.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.03767e+06", "standardDeviation": "5352.93", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2585.49", "standardDeviation": "75.8377", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.331e+06", "standardDeviation": "16689", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09569e+06", "standardDeviation": "20443.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2720.82", "standardDeviation": "141.617", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "125255", "standardDeviation": "24184.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141168", "standardDeviation": "2267.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2644.74", "standardDeviation": "105.109", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "227873", "standardDeviation": "2668.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "277825", "standardDeviation": "6889.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2551.57", "standardDeviation": "93.1181", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "506005", "standardDeviation": "6665.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "561257", "standardDeviation": "13033.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2513.04", "standardDeviation": "125.982", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "999366", "standardDeviation": "17114.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11826e+06", "standardDeviation": "18636.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2554.92", "standardDeviation": "79.8322", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.31059e+06", "standardDeviation": "29500.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.4665e+06", "standardDeviation": "29653.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2576.98", "standardDeviation": "429.384", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/153953/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..8e86ca5 --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Thu Oct 2 23:45:35 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 29C P0 61W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..cd6860a --- /dev/null +++ b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82123.6", "standardDeviation": "1940.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131789", "standardDeviation": "3276.11", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2748.99", "standardDeviation": "114.654", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170173", "standardDeviation": "55355.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262895", "standardDeviation": "5534.14", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2699.94", "standardDeviation": "80.2585", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "329228", "standardDeviation": "6836.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524638", "standardDeviation": "9857.06", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2601.74", "standardDeviation": "139.691", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "658258", "standardDeviation": "12010", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.07116e+06", "standardDeviation": "214754", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2646.18", "standardDeviation": "138.425", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.3173e+06", "standardDeviation": "17565.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09752e+06", "standardDeviation": "20682.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2746.52", "standardDeviation": "167.238", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115991", "standardDeviation": "2244.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135045", "standardDeviation": "2970.81", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2725.82", "standardDeviation": "173.661", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "225840", "standardDeviation": "4313.15", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "280693", "standardDeviation": "110563", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2696.64", "standardDeviation": "178.74", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "456271", "standardDeviation": "7264.52", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536260", "standardDeviation": "9908.77", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2587.96", "standardDeviation": "83.4717", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "876512", "standardDeviation": "12171.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07132e+06", "standardDeviation": "16282.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2620.53", "standardDeviation": "237.306", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.18677e+06", "standardDeviation": "26467.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.45334e+06", "standardDeviation": "24308.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2562.7", "standardDeviation": "158.529", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..0b12e2e Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..cb1bb63 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..c7f7bd6 Binary files /dev/null and b/153953/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/155439/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log b/155439/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log new file mode 100644 index 0000000..f0bb0cf --- /dev/null +++ b/155439/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Thu Oct 9 10:49:44 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 30C P0 61W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/160496/neon-cluster-meta-runner-neon-amd/divOperator.json b/160496/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..2720d5b --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "229222", "standardDeviation": "36915.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "533568", "standardDeviation": "25594.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "470522", "standardDeviation": "7687.46", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "572647", "standardDeviation": "29695", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.08096e+06", "standardDeviation": "188733", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "665212", "standardDeviation": "31783.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98986e+06", "standardDeviation": "244457", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "696288", "standardDeviation": "31327.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.12854e+06", "standardDeviation": "401134", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "741966", "standardDeviation": "31994.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/160496/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..c4fb708 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/160496/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..f880672 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/160496/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..75f6008 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/field.json b/160496/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..3acaa11 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "94443.9", "standardDeviation": "2594.97", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "75563.9", "standardDeviation": "8364.39", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "137683", "standardDeviation": "21714.5", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "74021.9", "standardDeviation": "8632.54", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "383155", "standardDeviation": "1998.71", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "108136", "standardDeviation": "24502.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "765084", "standardDeviation": "1930.51", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128193", "standardDeviation": "82683.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.53032e+06", "standardDeviation": "42133.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151923", "standardDeviation": "97254.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48586.7", "standardDeviation": "1442.28", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "55958", "standardDeviation": "12846.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "139387", "standardDeviation": "19421.5", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59475.4", "standardDeviation": "12319.5", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "389082", "standardDeviation": "2177.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "95741.1", "standardDeviation": "66168.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "775268", "standardDeviation": "1803.47", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "107457", "standardDeviation": "81669.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.58622e+06", "standardDeviation": "87497.7", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147077", "standardDeviation": "125580", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/field_fvops.png b/160496/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..7264063 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/field_relative.png b/160496/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..b76d92a Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/field_time.png b/160496/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..ef6d2ea Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/linear.json b/160496/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..e796551 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50087.8", "standardDeviation": "2236.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "53979.8", "standardDeviation": "2457.34", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3089.2", "standardDeviation": "5106.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206957", "standardDeviation": "6977.22", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "210697", "standardDeviation": "7267.28", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1486.01", "standardDeviation": "1570.04", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "286003", "standardDeviation": "11278.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "392312", "standardDeviation": "27604.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1782.38", "standardDeviation": "2061.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "711470", "standardDeviation": "95899.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "715264", "standardDeviation": "85669.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2061.79", "standardDeviation": "3563.78", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24946e+06", "standardDeviation": "217794", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.2562e+06", "standardDeviation": "224578", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2046.75", "standardDeviation": "3876.95", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "207362", "standardDeviation": "9945.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "211019", "standardDeviation": "7130.27", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1600.26", "standardDeviation": "1448.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "407167", "standardDeviation": "30333.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "384632", "standardDeviation": "31709.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1816.38", "standardDeviation": "2238.02", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "731223", "standardDeviation": "79405.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "739941", "standardDeviation": "89167.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2372.5", "standardDeviation": "4596.59", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.1943e+06", "standardDeviation": "146439", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.33267e+06", "standardDeviation": "217338", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2326.43", "standardDeviation": "5373.47", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.73976e+06", "standardDeviation": "105995", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.76604e+06", "standardDeviation": "91009.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1394.45", "standardDeviation": "1043.23", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/160496/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..32412d8 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/linear_relative.png b/160496/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..fb134ee Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/linear_time.png b/160496/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..2a34bf8 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/160496/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..e1f132c --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "213720", "standardDeviation": "13637.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "533863", "standardDeviation": "24235.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "474679", "standardDeviation": "25721.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "541578", "standardDeviation": "22984.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "942941", "standardDeviation": "60828.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "622711", "standardDeviation": "23036.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71548e+06", "standardDeviation": "71845.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "729678", "standardDeviation": "247546", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "6.667e+06", "standardDeviation": "94695.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "703176", "standardDeviation": "27628.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/main/field.json b/160496/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..6e8b7b7 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "52453.8", "standardDeviation": "9861.37", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "69899.4", "standardDeviation": "12607.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "133600", "standardDeviation": "38449.9", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "75836.9", "standardDeviation": "10502.2", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "359438", "standardDeviation": "22606.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "106772", "standardDeviation": "10057.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "714909", "standardDeviation": "58684.8", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119492", "standardDeviation": "16990.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.43235e+06", "standardDeviation": "123924", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143150", "standardDeviation": "9499.49", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47124.7", "standardDeviation": "4956.12", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "55509.3", "standardDeviation": "11127.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "132506", "standardDeviation": "2450.97", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58602.1", "standardDeviation": "9164.02", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "354750", "standardDeviation": "1613.51", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89195.3", "standardDeviation": "8469.24", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "707893", "standardDeviation": "1486.1", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "105658", "standardDeviation": "133844", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.41657e+06", "standardDeviation": "7772.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137958", "standardDeviation": "101939", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/main/linear.json b/160496/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..6a756e2 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49871.6", "standardDeviation": "1787.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51609.2", "standardDeviation": "1966.88", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2419.8", "standardDeviation": "4720.76", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130098", "standardDeviation": "5170.02", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131171", "standardDeviation": "5406.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2627.74", "standardDeviation": "5758.45", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "262140", "standardDeviation": "14005.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262951", "standardDeviation": "13135.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2525.72", "standardDeviation": "5152.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "523667", "standardDeviation": "30004.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "523982", "standardDeviation": "30060.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3249.68", "standardDeviation": "9119.81", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08858e+06", "standardDeviation": "64407.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05236e+06", "standardDeviation": "68458.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1920.7", "standardDeviation": "4905.37", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129836", "standardDeviation": "5651.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "131655", "standardDeviation": "6138.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2152.5", "standardDeviation": "3878.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "259753", "standardDeviation": "14555.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "263312", "standardDeviation": "17078.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2668.47", "standardDeviation": "5418.26", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "518744", "standardDeviation": "22571.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "526684", "standardDeviation": "36640.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3163.15", "standardDeviation": "8050.03", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.04773e+06", "standardDeviation": "69736.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06728e+06", "standardDeviation": "80377.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2462.92", "standardDeviation": "5228.17", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.89078e+06", "standardDeviation": "116957", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.90273e+06", "standardDeviation": "139245", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3202.95", "standardDeviation": "8731.93", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/main/upwind.json b/160496/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..0192087 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43404.8", "standardDeviation": "8042.36", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49875", "standardDeviation": "2242.02", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2028.52", "standardDeviation": "3034.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113304", "standardDeviation": "5431.48", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "112675", "standardDeviation": "6491.07", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2337.34", "standardDeviation": "5168.48", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "235530", "standardDeviation": "16390.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "238824", "standardDeviation": "15510.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2318.28", "standardDeviation": "5365.39", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "472939", "standardDeviation": "22104.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "478604", "standardDeviation": "30672.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3130.02", "standardDeviation": "9947.87", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "929481", "standardDeviation": "75763.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "928081", "standardDeviation": "69415.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3312.82", "standardDeviation": "10944.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "123519", "standardDeviation": "5998.13", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "129270", "standardDeviation": "3453.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2280.86", "standardDeviation": "5326.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "247581", "standardDeviation": "18008.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "259434", "standardDeviation": "16967.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2504.57", "standardDeviation": "6331.15", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "506798", "standardDeviation": "39844.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "538681", "standardDeviation": "89145", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2605.11", "standardDeviation": "6767.26", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "988859", "standardDeviation": "16295.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.02753e+06", "standardDeviation": "1312.04", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1684.95", "standardDeviation": "2505.62", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.28642e+06", "standardDeviation": "183076", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.25174e+06", "standardDeviation": "14476", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1736.63", "standardDeviation": "2365.38", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/system-info.log b/160496/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/160496/neon-cluster-meta-runner-neon-amd/upwind.json b/160496/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..916aafd --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "37372.1", "standardDeviation": "7303.98", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50337.9", "standardDeviation": "2180.72", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2308.42", "standardDeviation": "3574.58", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "117812", "standardDeviation": "5281.31", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "118192", "standardDeviation": "5731.71", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2187.85", "standardDeviation": "3232.31", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "230722", "standardDeviation": "13711.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "234391", "standardDeviation": "13761.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2153.32", "standardDeviation": "4369.83", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "464803", "standardDeviation": "31328.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "468751", "standardDeviation": "29544.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2540.8", "standardDeviation": "7228.75", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "926629", "standardDeviation": "78292.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "938021", "standardDeviation": "63881.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2463.82", "standardDeviation": "6386.19", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130283", "standardDeviation": "7448.21", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "129724", "standardDeviation": "7384.7", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2331.44", "standardDeviation": "4636.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261854", "standardDeviation": "17801.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "257220", "standardDeviation": "17154.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2310.85", "standardDeviation": "6092.89", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "822201", "standardDeviation": "205622", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "835744", "standardDeviation": "256164", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3958.23", "standardDeviation": "9929.82", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.1253e+06", "standardDeviation": "268532", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.04269e+06", "standardDeviation": "86753", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2989.09", "standardDeviation": "9194", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.92878e+06", "standardDeviation": "57553", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.13516e+06", "standardDeviation": "106799", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2906.67", "standardDeviation": "9338.43", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/160496/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..7f2cc83 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/160496/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..39b6331 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-amd/upwind_time.png b/160496/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..5d850d8 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..99b108e --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "366143", "standardDeviation": "2645.88", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "316939", "standardDeviation": "3107.16", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "718044", "standardDeviation": "4522.64", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "320331", "standardDeviation": "2833.65", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.39677e+06", "standardDeviation": "25858", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "322399", "standardDeviation": "3817.36", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.77386e+06", "standardDeviation": "75437.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "328500", "standardDeviation": "3098.81", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.04849e+06", "standardDeviation": "615750", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "309845", "standardDeviation": "4726.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..772b7f6 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..d108324 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..7e97815 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..f020234 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "315327", "standardDeviation": "2737.13", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40264.9", "standardDeviation": "2675.65", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "662734", "standardDeviation": "8685.23", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46983", "standardDeviation": "1861.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.31513e+06", "standardDeviation": "209226", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47535.3", "standardDeviation": "934.05", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.5793e+06", "standardDeviation": "2272.99", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48068.6", "standardDeviation": "1221.42", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.19672e+06", "standardDeviation": "403540", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151414", "standardDeviation": "2508.97", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "358812", "standardDeviation": "1887.95", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33736.6", "standardDeviation": "2460.61", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "715089", "standardDeviation": "1744.47", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40653.7", "standardDeviation": "1610.84", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.42533e+06", "standardDeviation": "1638.28", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40835.8", "standardDeviation": "971.011", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.43006e+06", "standardDeviation": "440921", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41651.7", "standardDeviation": "2992.7", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.96191e+06", "standardDeviation": "238541", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122616", "standardDeviation": "3925.13", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..8222ea0 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..fc23848 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..411bf96 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..34e5a12 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "121312", "standardDeviation": "2781.94", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "167685", "standardDeviation": "2951.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3242.13", "standardDeviation": "194.539", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "245365", "standardDeviation": "6314.87", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "334698", "standardDeviation": "3048.81", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3218.51", "standardDeviation": "202.909", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "492890", "standardDeviation": "14803.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "457947", "standardDeviation": "13685.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2474.2", "standardDeviation": "273.333", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "685733", "standardDeviation": "62543.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "914620", "standardDeviation": "34080.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2669.27", "standardDeviation": "1658.86", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.43879e+06", "standardDeviation": "144345", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.87746e+06", "standardDeviation": "77080.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2465.89", "standardDeviation": "364.524", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "141525", "standardDeviation": "15971.1", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "155537", "standardDeviation": "14443.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2486.38", "standardDeviation": "297.807", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261461", "standardDeviation": "40668.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "321059", "standardDeviation": "35782.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2515.94", "standardDeviation": "232.447", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "580997", "standardDeviation": "83596.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "627927", "standardDeviation": "73359.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2562.77", "standardDeviation": "279.287", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.1665e+06", "standardDeviation": "183121", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.32288e+06", "standardDeviation": "169036", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2493.59", "standardDeviation": "468.801", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.58515e+06", "standardDeviation": "227467", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.69892e+06", "standardDeviation": "242034", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2484.35", "standardDeviation": "934.451", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..d6ecfc2 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..f23c6f7 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..3e35811 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..3c07db4 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "256373", "standardDeviation": "3234.93", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "274992", "standardDeviation": "4204.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "502790", "standardDeviation": "4901.96", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278692", "standardDeviation": "4352.21", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "975149", "standardDeviation": "11014.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281162", "standardDeviation": "3956.53", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.91965e+06", "standardDeviation": "79165.7", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286768", "standardDeviation": "2506.95", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.9423e+06", "standardDeviation": "34687.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "312383", "standardDeviation": "3746.33", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..ae7f08c --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "305861", "standardDeviation": "1781.63", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40265.9", "standardDeviation": "2635.47", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "632818", "standardDeviation": "5994.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47145.5", "standardDeviation": "1438.22", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.31342e+06", "standardDeviation": "207459", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47401.2", "standardDeviation": "903.933", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.60768e+06", "standardDeviation": "292908", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "48099.1", "standardDeviation": "1085.75", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.14641e+06", "standardDeviation": "14953.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151015", "standardDeviation": "2148.42", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "359057", "standardDeviation": "1833.62", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33909.3", "standardDeviation": "2638.92", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "714637", "standardDeviation": "1986.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35263.4", "standardDeviation": "691.307", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976596", "standardDeviation": "6627.06", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35353.8", "standardDeviation": "898.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.97426e+06", "standardDeviation": "196752", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41406.8", "standardDeviation": "3194.67", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.91547e+06", "standardDeviation": "13754", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122798", "standardDeviation": "3882.77", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..3d5750e --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "122072", "standardDeviation": "1484.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "168468", "standardDeviation": "8904.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3273.11", "standardDeviation": "166.956", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "260013", "standardDeviation": "158952", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "334128", "standardDeviation": "2013.65", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3267.15", "standardDeviation": "127.491", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "339162", "standardDeviation": "16227.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "461098", "standardDeviation": "8913.37", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2541.81", "standardDeviation": "106.791", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "674413", "standardDeviation": "12175.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "943306", "standardDeviation": "185915", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2490.13", "standardDeviation": "182.518", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.39031e+06", "standardDeviation": "126956", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.85411e+06", "standardDeviation": "29211.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2508.41", "standardDeviation": "244.724", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "136140", "standardDeviation": "2324.22", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "155168", "standardDeviation": "2811.88", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2427.06", "standardDeviation": "98.5039", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261599", "standardDeviation": "3761.33", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "319014", "standardDeviation": "24472.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2427.99", "standardDeviation": "131.287", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "565606", "standardDeviation": "68313.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "635500", "standardDeviation": "76832.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2461.37", "standardDeviation": "244.012", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.14363e+06", "standardDeviation": "179634", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.29024e+06", "standardDeviation": "170746", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2578.35", "standardDeviation": "391.405", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.06448e+06", "standardDeviation": "304945", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.72412e+06", "standardDeviation": "220070", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2613.61", "standardDeviation": "1090.85", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..1c765cd --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98815.8", "standardDeviation": "3741", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131505", "standardDeviation": "3494.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2483.64", "standardDeviation": "222.344", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198971", "standardDeviation": "22520.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263308", "standardDeviation": "6085.55", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2377.99", "standardDeviation": "265.763", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "395353", "standardDeviation": "18141.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "526165", "standardDeviation": "11806.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2448.24", "standardDeviation": "246.956", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "790187", "standardDeviation": "32156.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05281e+06", "standardDeviation": "28392.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2418", "standardDeviation": "338.411", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.58308e+06", "standardDeviation": "70989.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.11108e+06", "standardDeviation": "38437.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2382.26", "standardDeviation": "336.178", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "125835", "standardDeviation": "78460.7", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141200", "standardDeviation": "12383.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2383.13", "standardDeviation": "216.991", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "236296", "standardDeviation": "35867.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272243", "standardDeviation": "32618.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2421.41", "standardDeviation": "243.756", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "534227", "standardDeviation": "290968", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "565140", "standardDeviation": "71844", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2358.34", "standardDeviation": "289.309", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03144e+06", "standardDeviation": "176506", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.2173e+06", "standardDeviation": "171628", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2374.59", "standardDeviation": "341.643", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.57211e+06", "standardDeviation": "179490", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.52153e+06", "standardDeviation": "201862", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2357.53", "standardDeviation": "743.375", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/160496/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..84cc43d --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Oct 29 11:32:07 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:61:00.0 Off | 0 | +| N/A 28C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..41b7a22 --- /dev/null +++ b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98419.3", "standardDeviation": "3660.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131880", "standardDeviation": "3673.71", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2732.25", "standardDeviation": "520.26", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "197423", "standardDeviation": "6120.87", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "266375", "standardDeviation": "35053.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2638.26", "standardDeviation": "246.106", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "394179", "standardDeviation": "14989.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "526077", "standardDeviation": "12262.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2564.22", "standardDeviation": "254.49", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "789584", "standardDeviation": "32706.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05309e+06", "standardDeviation": "23638.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2703.37", "standardDeviation": "1023.27", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.61569e+06", "standardDeviation": "104624", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.10349e+06", "standardDeviation": "41532.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2568.36", "standardDeviation": "393.266", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122568", "standardDeviation": "80615.3", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136541", "standardDeviation": "13200.3", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2546.76", "standardDeviation": "240.369", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "224923", "standardDeviation": "36936.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "273676", "standardDeviation": "30740.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2545.33", "standardDeviation": "339.228", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "465322", "standardDeviation": "80912.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "549416", "standardDeviation": "74382.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2550.6", "standardDeviation": "490.272", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "946365", "standardDeviation": "192322", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.13166e+06", "standardDeviation": "173664", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2626.47", "standardDeviation": "431.814", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.15025e+06", "standardDeviation": "236295", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.33315e+06", "standardDeviation": "285389", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2590.23", "standardDeviation": "776.76", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..938c494 Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..7a9bb7f Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..0fd6afb Binary files /dev/null and b/160496/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/divOperator.json b/160509/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..5aebbd6 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "250970", "standardDeviation": "23391.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "539002", "standardDeviation": "27842.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "492528", "standardDeviation": "28622.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "552492", "standardDeviation": "26005.9", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "888100", "standardDeviation": "88580.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "666162", "standardDeviation": "241635", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72163e+06", "standardDeviation": "44270.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "663931", "standardDeviation": "26234.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.68507e+06", "standardDeviation": "134249", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "712770", "standardDeviation": "29489.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/160509/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..5970602 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/160509/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..2661b77 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/160509/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..ca2faa6 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/field.json b/160509/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..934357f --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "112999", "standardDeviation": "6623.05", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "71634.2", "standardDeviation": "10115.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "164495", "standardDeviation": "3474.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77629.2", "standardDeviation": "7684.26", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "435096", "standardDeviation": "38467.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109822", "standardDeviation": "7546.23", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "808310", "standardDeviation": "57565.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125873", "standardDeviation": "22620.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.61391e+06", "standardDeviation": "158391", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "159041", "standardDeviation": "62254", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "52571.7", "standardDeviation": "1111.86", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58634.8", "standardDeviation": "8931.32", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "172677", "standardDeviation": "3878.24", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61238.8", "standardDeviation": "8541.25", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "441124", "standardDeviation": "33917.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "95302.6", "standardDeviation": "10307.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "816255", "standardDeviation": "56397", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103730", "standardDeviation": "7955.02", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.63464e+06", "standardDeviation": "156714", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "136645", "standardDeviation": "15331", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/field_fvops.png b/160509/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..f462b6b Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/field_relative.png b/160509/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..e6754e5 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/field_time.png b/160509/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..7810bb0 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/linear.json b/160509/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..276b740 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50256.1", "standardDeviation": "3242.62", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51431.2", "standardDeviation": "1182.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1482.02", "standardDeviation": "1290.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164242", "standardDeviation": "4015.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "196771", "standardDeviation": "6031.07", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1488.86", "standardDeviation": "1591.93", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "301734", "standardDeviation": "12006.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "329294", "standardDeviation": "17772.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1558.64", "standardDeviation": "1867.18", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "565331", "standardDeviation": "41842.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "571608", "standardDeviation": "43094.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1673.7", "standardDeviation": "2465.79", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.10486e+06", "standardDeviation": "98949", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.16254e+06", "standardDeviation": "151058", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1602.97", "standardDeviation": "2129.29", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163995", "standardDeviation": "3883.36", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "166033", "standardDeviation": "4189.75", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1427.08", "standardDeviation": "1788.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "301260", "standardDeviation": "11908.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "335985", "standardDeviation": "15893.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1461.73", "standardDeviation": "1293.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "582882", "standardDeviation": "48767.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "661692", "standardDeviation": "124381", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1750.56", "standardDeviation": "2556.01", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.13833e+06", "standardDeviation": "128173", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09794e+06", "standardDeviation": "75531.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1641.23", "standardDeviation": "1832.33", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.63415e+06", "standardDeviation": "83172.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.5558e+06", "standardDeviation": "118772", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1704.73", "standardDeviation": "2332.11", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/160509/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..2f8fa6b Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/linear_relative.png b/160509/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..bad4ef9 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/linear_time.png b/160509/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..d49e87e Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/160509/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..be57772 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "237936", "standardDeviation": "4375.31", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "541850", "standardDeviation": "26782.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "516917", "standardDeviation": "28080.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "547973", "standardDeviation": "31151.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.00338e+06", "standardDeviation": "136135", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "622025", "standardDeviation": "25562.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.8725e+06", "standardDeviation": "103631", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "670959", "standardDeviation": "28928.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.94146e+06", "standardDeviation": "251071", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "697261", "standardDeviation": "22545.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/main/field.json b/160509/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..7f2f5ff --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51193.7", "standardDeviation": "1750.22", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72502.6", "standardDeviation": "8441.48", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "153165", "standardDeviation": "3442.89", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81685.5", "standardDeviation": "33547.8", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "399235", "standardDeviation": "21454.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109684", "standardDeviation": "12511.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "809470", "standardDeviation": "88819.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131762", "standardDeviation": "88356.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.43525e+06", "standardDeviation": "62269.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160830", "standardDeviation": "128229", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "51129.7", "standardDeviation": "1407.95", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59189.8", "standardDeviation": "8936.95", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "145879", "standardDeviation": "2668.55", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62175.8", "standardDeviation": "10703.4", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "470282", "standardDeviation": "38831", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "98658.5", "standardDeviation": "48134.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "822220", "standardDeviation": "89584", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122320", "standardDeviation": "107147", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.46839e+06", "standardDeviation": "105193", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150995", "standardDeviation": "132288", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/main/linear.json b/160509/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..4023151 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53859.9", "standardDeviation": "4918.71", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "58807.6", "standardDeviation": "2378.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1635.11", "standardDeviation": "1345.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "207289", "standardDeviation": "6878.74", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "210771", "standardDeviation": "7222.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1760.31", "standardDeviation": "3109.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "389960", "standardDeviation": "26473.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "394834", "standardDeviation": "55359", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1643.87", "standardDeviation": "3029.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "711699", "standardDeviation": "82818", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "719263", "standardDeviation": "86448.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1965.57", "standardDeviation": "3523.72", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.20871e+06", "standardDeviation": "182153", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.26241e+06", "standardDeviation": "251867", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1952.75", "standardDeviation": "3700.44", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "208303", "standardDeviation": "8326.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "211179", "standardDeviation": "7172.14", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1552.07", "standardDeviation": "2173.41", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "392029", "standardDeviation": "26816.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "395684", "standardDeviation": "27340.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1661.34", "standardDeviation": "2689.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "721967", "standardDeviation": "83733.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "688599", "standardDeviation": "70404.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2260.35", "standardDeviation": "5180.62", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.27399e+06", "standardDeviation": "212478", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.28902e+06", "standardDeviation": "204090", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1922.17", "standardDeviation": "3178.09", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.67856e+06", "standardDeviation": "298537", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.91416e+06", "standardDeviation": "248058", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2090.16", "standardDeviation": "3201.62", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/main/upwind.json b/160509/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..e17fb24 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "46730", "standardDeviation": "8390.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "43500.7", "standardDeviation": "1775.16", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1601.93", "standardDeviation": "1202.89", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "152331", "standardDeviation": "4267.53", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "154143", "standardDeviation": "4168.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1557.47", "standardDeviation": "1376.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "282978", "standardDeviation": "10558.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "297927", "standardDeviation": "13290.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1875.62", "standardDeviation": "3352.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "502743", "standardDeviation": "30883.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "554689", "standardDeviation": "45643.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1728.33", "standardDeviation": "2821.33", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.03232e+06", "standardDeviation": "101553", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04807e+06", "standardDeviation": "105455", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2036.77", "standardDeviation": "3506.72", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "192976", "standardDeviation": "6612.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "200187", "standardDeviation": "6209.28", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1722.19", "standardDeviation": "1890.95", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "358892", "standardDeviation": "23451.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "379254", "standardDeviation": "24516.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1791.13", "standardDeviation": "2198.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "645678", "standardDeviation": "62097.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "694340", "standardDeviation": "77468.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2141.51", "standardDeviation": "6530.18", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.18124e+06", "standardDeviation": "194399", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.22306e+06", "standardDeviation": "198631", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1753.5", "standardDeviation": "2407.21", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.64778e+06", "standardDeviation": "265573", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.43025e+06", "standardDeviation": "301190", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2107.98", "standardDeviation": "3565.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/system-info.log b/160509/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/160509/neon-cluster-meta-runner-neon-amd/upwind.json b/160509/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..2187496 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51014.3", "standardDeviation": "2133.84", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51939.6", "standardDeviation": "1255.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1678.18", "standardDeviation": "1354.61", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "183264", "standardDeviation": "5870.06", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "186724", "standardDeviation": "5632.58", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1657.54", "standardDeviation": "1278.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "350527", "standardDeviation": "20178.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "353989", "standardDeviation": "20946.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2162.76", "standardDeviation": "4103.77", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "637852", "standardDeviation": "66330.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "643753", "standardDeviation": "70765.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1949.17", "standardDeviation": "3602.12", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.1269e+06", "standardDeviation": "175815", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.14488e+06", "standardDeviation": "179491", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2032.65", "standardDeviation": "3545.31", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194002", "standardDeviation": "6212.2", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "201441", "standardDeviation": "6290.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1740.81", "standardDeviation": "1893.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "332297", "standardDeviation": "15629.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "375480", "standardDeviation": "24122", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1724.15", "standardDeviation": "1790.37", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "644285", "standardDeviation": "61918.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "693411", "standardDeviation": "77165.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1996.51", "standardDeviation": "3490.24", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.18783e+06", "standardDeviation": "190155", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.19244e+06", "standardDeviation": "170276", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2017.3", "standardDeviation": "3518.11", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.42634e+06", "standardDeviation": "291223", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.50526e+06", "standardDeviation": "282926", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2107.24", "standardDeviation": "3313.09", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/160509/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..a16b8f8 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/160509/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..200a9ca Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-amd/upwind_time.png b/160509/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..b159762 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..dd0a24a --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "367722", "standardDeviation": "3505.37", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "319130", "standardDeviation": "2899.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "722648", "standardDeviation": "5709.61", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "321708", "standardDeviation": "3237.78", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.41081e+06", "standardDeviation": "4475.09", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "324689", "standardDeviation": "3062.86", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.9069e+06", "standardDeviation": "4425.99", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285132", "standardDeviation": "2216.34", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.98541e+06", "standardDeviation": "125575", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "310466", "standardDeviation": "3626.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..6969dd3 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..8cf715d Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..39cfaf5 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..d95147b --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210338", "standardDeviation": "2925.78", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41653.7", "standardDeviation": "735.859", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "463316", "standardDeviation": "5115.36", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42784.4", "standardDeviation": "10845.2", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "898417", "standardDeviation": "5686.71", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42412.4", "standardDeviation": "982.572", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79766e+06", "standardDeviation": "18001.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42917.9", "standardDeviation": "1079.63", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.61395e+06", "standardDeviation": "16581.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130753", "standardDeviation": "2698", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "249440", "standardDeviation": "33615.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35207.3", "standardDeviation": "833.325", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "490627", "standardDeviation": "4068.05", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35944.1", "standardDeviation": "850.232", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976544", "standardDeviation": "6222.94", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35513.9", "standardDeviation": "862.915", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.97866e+06", "standardDeviation": "164366", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39356.7", "standardDeviation": "3794.73", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.92632e+06", "standardDeviation": "9368.19", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124262", "standardDeviation": "3859.73", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..660d2f8 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..fd2b42b Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..bda5cd5 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..ca80799 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "121236", "standardDeviation": "1114.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "167354", "standardDeviation": "1832.92", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3253.68", "standardDeviation": "115.393", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "251224", "standardDeviation": "81606.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "333655", "standardDeviation": "1711.34", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3230.61", "standardDeviation": "125.382", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "486151", "standardDeviation": "8008.37", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "666612", "standardDeviation": "1787.88", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2494.69", "standardDeviation": "80.0608", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "664965", "standardDeviation": "2947.98", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "924127", "standardDeviation": "119714", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2488.64", "standardDeviation": "71.0927", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32918e+06", "standardDeviation": "6953.35", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.82183e+06", "standardDeviation": "7162.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2502.2", "standardDeviation": "162.303", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "134742", "standardDeviation": "1380.69", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156544", "standardDeviation": "1374.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2492.07", "standardDeviation": "114.107", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "252823", "standardDeviation": "4287.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "328847", "standardDeviation": "125179", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2504.2", "standardDeviation": "98.4853", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "545062", "standardDeviation": "4834.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "631211", "standardDeviation": "9355.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2517.26", "standardDeviation": "98.3942", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11406e+06", "standardDeviation": "6069.18", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.24961e+06", "standardDeviation": "13427.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2584.98", "standardDeviation": "326.948", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.57424e+06", "standardDeviation": "19660.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.02123e+06", "standardDeviation": "16546.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2441.35", "standardDeviation": "259.391", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..ac5f405 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..3a6b82b Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..66a5297 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..0bfdc58 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "260742", "standardDeviation": "22785", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272580", "standardDeviation": "3228.11", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "510660", "standardDeviation": "4147.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276535", "standardDeviation": "2349.65", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "997098", "standardDeviation": "5927.92", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279615", "standardDeviation": "3831.75", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.94879e+06", "standardDeviation": "12829.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285695", "standardDeviation": "3299.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.33126e+06", "standardDeviation": "116523", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "310985", "standardDeviation": "3537.54", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..5db3ed5 --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210640", "standardDeviation": "3627.01", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39881.4", "standardDeviation": "3163.05", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "438712", "standardDeviation": "4550", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41499.6", "standardDeviation": "1244.77", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "899559", "standardDeviation": "5402.84", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41600.1", "standardDeviation": "916.107", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.79799e+06", "standardDeviation": "19265.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42577.3", "standardDeviation": "951.78", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.60526e+06", "standardDeviation": "16814", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130380", "standardDeviation": "2416.95", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "246444", "standardDeviation": "2727.01", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35753.4", "standardDeviation": "885.571", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "497520", "standardDeviation": "64797.4", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35447.7", "standardDeviation": "1101.86", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "983037", "standardDeviation": "6417.27", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35689.2", "standardDeviation": "791.591", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.96004e+06", "standardDeviation": "21296.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40705.3", "standardDeviation": "8844.85", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.9255e+06", "standardDeviation": "9487.03", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124799", "standardDeviation": "3859.94", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..cccd5fe --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83679.4", "standardDeviation": "1997.52", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115045", "standardDeviation": "2106.68", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2441.41", "standardDeviation": "95.988", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168336", "standardDeviation": "2455.25", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "229784", "standardDeviation": "2818.56", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2479.58", "standardDeviation": "157.031", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "347955", "standardDeviation": "125693", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "459165", "standardDeviation": "5972.37", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2509.32", "standardDeviation": "118.654", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "671983", "standardDeviation": "10967.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "917380", "standardDeviation": "8860.45", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2430.01", "standardDeviation": "133.536", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34761e+06", "standardDeviation": "17145.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.84527e+06", "standardDeviation": "75536.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2438.93", "standardDeviation": "163.943", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "128514", "standardDeviation": "1710.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "151360", "standardDeviation": "2376.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2462.22", "standardDeviation": "136.284", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "251147", "standardDeviation": "3348.03", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "300378", "standardDeviation": "4215.79", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2521.64", "standardDeviation": "174.223", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "518845", "standardDeviation": "5661.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "598894", "standardDeviation": "8479.07", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2436.5", "standardDeviation": "195.032", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01953e+06", "standardDeviation": "10947.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.21244e+06", "standardDeviation": "12854.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2452.68", "standardDeviation": "151.36", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.65713e+06", "standardDeviation": "15151.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.03681e+06", "standardDeviation": "11171.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2383.41", "standardDeviation": "165.666", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..5f2dc5c --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "142096", "standardDeviation": "1427.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "190121", "standardDeviation": "1381.28", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3473.51", "standardDeviation": "128.793", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "284396", "standardDeviation": "1732.13", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "267504", "standardDeviation": "55357.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2607.56", "standardDeviation": "117.566", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "392759", "standardDeviation": "7933.73", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524664", "standardDeviation": "9612.43", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2572.59", "standardDeviation": "94.3596", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "785143", "standardDeviation": "13584.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04818e+06", "standardDeviation": "16738.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2627.9", "standardDeviation": "149.996", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56941e+06", "standardDeviation": "19907.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.0946e+06", "standardDeviation": "21976.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2606.44", "standardDeviation": "735.529", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122288", "standardDeviation": "2500.45", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "140050", "standardDeviation": "2217.31", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2540.13", "standardDeviation": "124.283", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "249053", "standardDeviation": "4441.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278518", "standardDeviation": "7384.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2600.02", "standardDeviation": "142.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "491965", "standardDeviation": "8665.66", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "556696", "standardDeviation": "9829.45", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2540.47", "standardDeviation": "226.311", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "982489", "standardDeviation": "12951.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.10491e+06", "standardDeviation": "18985", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2552.03", "standardDeviation": "103.432", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.04956e+06", "standardDeviation": "26888.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.48208e+06", "standardDeviation": "20510.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2535.53", "standardDeviation": "155.305", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/160509/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..84dd7ad --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Oct 29 12:00:07 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:61:00.0 Off | 0 | +| N/A 29C P0 59W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..a82fa0a --- /dev/null +++ b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98174.6", "standardDeviation": "2197.4", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131552", "standardDeviation": "2822.4", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2687.32", "standardDeviation": "452.008", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196658", "standardDeviation": "4318.09", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "268226", "standardDeviation": "52537.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2595.15", "standardDeviation": "106.294", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "393022", "standardDeviation": "49241.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "518901", "standardDeviation": "5451.59", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2581.39", "standardDeviation": "171.229", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "774862", "standardDeviation": "1601.02", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04743e+06", "standardDeviation": "16178.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2591.82", "standardDeviation": "76.2343", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56988e+06", "standardDeviation": "20146.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09562e+06", "standardDeviation": "23068.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2520.78", "standardDeviation": "149.797", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "124345", "standardDeviation": "3013.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "143036", "standardDeviation": "31710.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2551.02", "standardDeviation": "81.312", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "247514", "standardDeviation": "4032.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278207", "standardDeviation": "5786.58", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2539.86", "standardDeviation": "109.712", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "493770", "standardDeviation": "7786.69", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "553759", "standardDeviation": "10725.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2489.4", "standardDeviation": "102.804", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00447e+06", "standardDeviation": "12515.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11246e+06", "standardDeviation": "21840.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2467.74", "standardDeviation": "143.145", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.36057e+06", "standardDeviation": "17141.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.03636e+06", "standardDeviation": "19005.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2483.22", "standardDeviation": "346.37", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..9106b98 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..4d6ca0d Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..bd4a371 Binary files /dev/null and b/160509/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/divOperator.json b/160541/neon-cluster-meta-runner-neon-amd/divOperator.json new file mode 100644 index 0000000..8493d3e --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "249823", "standardDeviation": "6805.18", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "602522", "standardDeviation": "32476.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540391", "standardDeviation": "38482.9", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "609100", "standardDeviation": "32868.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "982351", "standardDeviation": "141190", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "696830", "standardDeviation": "30196.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82905e+06", "standardDeviation": "186664", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "727913", "standardDeviation": "34251.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.74733e+06", "standardDeviation": "357449", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "780217", "standardDeviation": "32186.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png b/160541/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png new file mode 100644 index 0000000..f9bcbb6 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/divOperator_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/divOperator_relative.png b/160541/neon-cluster-meta-runner-neon-amd/divOperator_relative.png new file mode 100644 index 0000000..c197aef Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/divOperator_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/divOperator_time.png b/160541/neon-cluster-meta-runner-neon-amd/divOperator_time.png new file mode 100644 index 0000000..7c66582 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/divOperator_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/field.json b/160541/neon-cluster-meta-runner-neon-amd/field.json new file mode 100644 index 0000000..6e38127 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "103666", "standardDeviation": "33920.8", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88635.4", "standardDeviation": "13165.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "166303", "standardDeviation": "5192.63", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "76953.3", "standardDeviation": "7720.87", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "389046", "standardDeviation": "15971.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "107814", "standardDeviation": "9257.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "729883", "standardDeviation": "24851", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125040", "standardDeviation": "5059.02", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.46512e+06", "standardDeviation": "91618.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149824", "standardDeviation": "5883.85", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48203.9", "standardDeviation": "2164.31", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59390.8", "standardDeviation": "7159.49", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "142074", "standardDeviation": "2196.57", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60474.8", "standardDeviation": "9201.97", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "377149", "standardDeviation": "13622.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93632.4", "standardDeviation": "9719.08", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "734008", "standardDeviation": "30824", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118024", "standardDeviation": "79998.1", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50254e+06", "standardDeviation": "136515", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "135696", "standardDeviation": "16519.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/field_fvops.png b/160541/neon-cluster-meta-runner-neon-amd/field_fvops.png new file mode 100644 index 0000000..b4dca87 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/field_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/field_relative.png b/160541/neon-cluster-meta-runner-neon-amd/field_relative.png new file mode 100644 index 0000000..e1ed063 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/field_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/field_time.png b/160541/neon-cluster-meta-runner-neon-amd/field_time.png new file mode 100644 index 0000000..d2d3ce2 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/field_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/linear.json b/160541/neon-cluster-meta-runner-neon-amd/linear.json new file mode 100644 index 0000000..987af09 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51736.4", "standardDeviation": "3541.87", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50600.8", "standardDeviation": "1024.28", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1965.79", "standardDeviation": "1451.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177462", "standardDeviation": "5600.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149014", "standardDeviation": "3461.05", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1999.81", "standardDeviation": "1949.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "337865", "standardDeviation": "20124", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "340238", "standardDeviation": "20824.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1973.62", "standardDeviation": "1776.75", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "615909", "standardDeviation": "68193.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "613936", "standardDeviation": "72136.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2509.96", "standardDeviation": "2855.02", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.0893e+06", "standardDeviation": "176294", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08609e+06", "standardDeviation": "182986", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2263.56", "standardDeviation": "3418.42", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177251", "standardDeviation": "5213.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "179120", "standardDeviation": "5656.55", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1940.42", "standardDeviation": "1333.66", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "335528", "standardDeviation": "19183.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "331116", "standardDeviation": "23059.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1981.53", "standardDeviation": "1679.51", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "605531", "standardDeviation": "69072.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "637097", "standardDeviation": "163748", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2440.02", "standardDeviation": "2986.78", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09044e+06", "standardDeviation": "168940", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07951e+06", "standardDeviation": "173300", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2236.36", "standardDeviation": "2041.91", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34643e+06", "standardDeviation": "263510", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.63002e+06", "standardDeviation": "246525", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2017.99", "standardDeviation": "1141.34", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/linear_fvops.png b/160541/neon-cluster-meta-runner-neon-amd/linear_fvops.png new file mode 100644 index 0000000..83bf96f Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/linear_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/linear_relative.png b/160541/neon-cluster-meta-runner-neon-amd/linear_relative.png new file mode 100644 index 0000000..9e87b5c Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/linear_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/linear_time.png b/160541/neon-cluster-meta-runner-neon-amd/linear_time.png new file mode 100644 index 0000000..3c2e225 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/linear_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/main/divOperator.json b/160541/neon-cluster-meta-runner-neon-amd/main/divOperator.json new file mode 100644 index 0000000..ec5a92f --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "270034", "standardDeviation": "8967.68", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "604170", "standardDeviation": "42168.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "602756", "standardDeviation": "46580.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "609560", "standardDeviation": "37528.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.07924e+06", "standardDeviation": "133324", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "687698", "standardDeviation": "30882.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98475e+06", "standardDeviation": "248045", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "755937", "standardDeviation": "284596", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.95663e+06", "standardDeviation": "365313", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "770878", "standardDeviation": "32511.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/main/field.json b/160541/neon-cluster-meta-runner-neon-amd/main/field.json new file mode 100644 index 0000000..5531a94 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49072.2", "standardDeviation": "2651.71", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "95574.3", "standardDeviation": "10323.9", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "200025", "standardDeviation": "5434.5", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "97196.3", "standardDeviation": "9497.57", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "433239", "standardDeviation": "32456.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117412", "standardDeviation": "8670.53", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "846795", "standardDeviation": "104945", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137400", "standardDeviation": "33156", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54961e+06", "standardDeviation": "197188", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "162478", "standardDeviation": "58598.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48031.6", "standardDeviation": "2842.31", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61015.1", "standardDeviation": "9359.26", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "181483", "standardDeviation": "4688.42", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "64172.6", "standardDeviation": "9269.87", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "476960", "standardDeviation": "39471.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99905.2", "standardDeviation": "11497.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "853318", "standardDeviation": "105943", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118634", "standardDeviation": "24699.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.56313e+06", "standardDeviation": "207457", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145351", "standardDeviation": "30381.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/main/linear.json b/160541/neon-cluster-meta-runner-neon-amd/main/linear.json new file mode 100644 index 0000000..933d5ec --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50092.2", "standardDeviation": "3020.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51281.7", "standardDeviation": "4572.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2016.55", "standardDeviation": "1387", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206552", "standardDeviation": "7242.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "185071", "standardDeviation": "5021.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2052.36", "standardDeviation": "1585.41", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "389597", "standardDeviation": "26637", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "396321", "standardDeviation": "50878.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2007.61", "standardDeviation": "2852.37", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "675388", "standardDeviation": "72140.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "706302", "standardDeviation": "82979.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2190.38", "standardDeviation": "3181.92", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24671e+06", "standardDeviation": "215738", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.24863e+06", "standardDeviation": "219486", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1886.74", "standardDeviation": "1805.27", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "205422", "standardDeviation": "6995.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "207899", "standardDeviation": "7124.75", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1981.38", "standardDeviation": "2469.56", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "391077", "standardDeviation": "26805.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "395197", "standardDeviation": "26836.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2099.47", "standardDeviation": "1792.22", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "701733", "standardDeviation": "80775.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "706560", "standardDeviation": "82493.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2504.95", "standardDeviation": "3953.22", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.24698e+06", "standardDeviation": "211466", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.24894e+06", "standardDeviation": "211232", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2181.26", "standardDeviation": "2024.18", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.64345e+06", "standardDeviation": "295789", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.53867e+06", "standardDeviation": "307050", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2227.81", "standardDeviation": "2283.27", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/main/upwind.json b/160541/neon-cluster-meta-runner-neon-amd/main/upwind.json new file mode 100644 index 0000000..1ba666b --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49852.3", "standardDeviation": "2499.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "46890.4", "standardDeviation": "3257.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2703.66", "standardDeviation": "1900.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "159809", "standardDeviation": "4320.38", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "162170", "standardDeviation": "4924.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2255.58", "standardDeviation": "1814.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "316389", "standardDeviation": "131793", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "304723", "standardDeviation": "17583.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2681.84", "standardDeviation": "2198.61", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "557639", "standardDeviation": "55134.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "553504", "standardDeviation": "61303.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2925.32", "standardDeviation": "3595.36", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "977894", "standardDeviation": "151530", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "964553", "standardDeviation": "159006", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3309.03", "standardDeviation": "3353.43", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172868", "standardDeviation": "4967.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "174467", "standardDeviation": "5140.62", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2696.84", "standardDeviation": "1540.21", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "336636", "standardDeviation": "16684.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "330824", "standardDeviation": "17705.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3112.51", "standardDeviation": "2208.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "620008", "standardDeviation": "55579.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "605227", "standardDeviation": "60824.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3200.86", "standardDeviation": "3365.97", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10384e+06", "standardDeviation": "145700", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08388e+06", "standardDeviation": "156247", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3083.74", "standardDeviation": "2990.75", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.31734e+06", "standardDeviation": "255659", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.56784e+06", "standardDeviation": "221355", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2562.31", "standardDeviation": "3360.02", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/system-info.log b/160541/neon-cluster-meta-runner-neon-amd/system-info.log new file mode 100644 index 0000000..e481c06 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/system-info.log @@ -0,0 +1,80 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/160541/neon-cluster-meta-runner-neon-amd/upwind.json b/160541/neon-cluster-meta-runner-neon-amd/upwind.json new file mode 100644 index 0000000..20beb04 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "47856.1", "standardDeviation": "6744.05", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44758.6", "standardDeviation": "1035.43", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3352.18", "standardDeviation": "3579.31", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "159091", "standardDeviation": "4359.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "160974", "standardDeviation": "4914.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3603.68", "standardDeviation": "5920.71", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "296075", "standardDeviation": "17080.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "305399", "standardDeviation": "17034", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4432.22", "standardDeviation": "10526.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "556959", "standardDeviation": "53144.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "554616", "standardDeviation": "60783.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4220.72", "standardDeviation": "11956.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "976289", "standardDeviation": "154971", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "976529", "standardDeviation": "164974", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4228.03", "standardDeviation": "12391.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171720", "standardDeviation": "4600.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "173823", "standardDeviation": "5140.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3386.59", "standardDeviation": "6248.72", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "332537", "standardDeviation": "17813.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "311503", "standardDeviation": "15061.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4364.45", "standardDeviation": "8348.06", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "612156", "standardDeviation": "56270.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "610388", "standardDeviation": "121145", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4464.46", "standardDeviation": "9881.93", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10587e+06", "standardDeviation": "146943", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08015e+06", "standardDeviation": "150900", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "5274.33", "standardDeviation": "11729.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.28648e+06", "standardDeviation": "250854", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.25759e+06", "standardDeviation": "252117", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "5432.24", "standardDeviation": "12234.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-amd/upwind_fvops.png b/160541/neon-cluster-meta-runner-neon-amd/upwind_fvops.png new file mode 100644 index 0000000..dcae698 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/upwind_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/upwind_relative.png b/160541/neon-cluster-meta-runner-neon-amd/upwind_relative.png new file mode 100644 index 0000000..8fa8878 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/upwind_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-amd/upwind_time.png b/160541/neon-cluster-meta-runner-neon-amd/upwind_time.png new file mode 100644 index 0000000..8d70063 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-amd/upwind_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json new file mode 100644 index 0000000..0c03252 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "368627", "standardDeviation": "3704.93", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "318586", "standardDeviation": "5724.71", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "724303", "standardDeviation": "8495.65", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "321149", "standardDeviation": "3014.03", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.40137e+06", "standardDeviation": "5267.86", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "323641", "standardDeviation": "2892.22", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.75828e+06", "standardDeviation": "9802.99", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "329134", "standardDeviation": "3823.18", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.84592e+06", "standardDeviation": "729702", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "312392", "standardDeviation": "5277.94", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..b24a935 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..9466e6d Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..08f84db Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/divOperator_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/field.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field.json new file mode 100644 index 0000000..84eb705 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306865", "standardDeviation": "2459.34", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40147.4", "standardDeviation": "2921.62", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "636895", "standardDeviation": "4147.58", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "46841.3", "standardDeviation": "1399.49", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29171e+06", "standardDeviation": "1530.58", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47673.8", "standardDeviation": "1025.41", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.60658e+06", "standardDeviation": "277367", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42288.2", "standardDeviation": "891.903", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.60847e+06", "standardDeviation": "16228.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "129441", "standardDeviation": "1961.71", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "245299", "standardDeviation": "2354.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35427.1", "standardDeviation": "776.792", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "490342", "standardDeviation": "4075.7", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35539.9", "standardDeviation": "912.218", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976735", "standardDeviation": "6272.12", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35714.8", "standardDeviation": "762.553", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.96017e+06", "standardDeviation": "21309", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40991.5", "standardDeviation": "3378.64", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.94938e+06", "standardDeviation": "234042", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123789", "standardDeviation": "3906.31", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..cb940fe Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png new file mode 100644 index 0000000..e1be4fe Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png new file mode 100644 index 0000000..6fa687c Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/field_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear.json new file mode 100644 index 0000000..1019695 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84652.7", "standardDeviation": "2138.31", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115575", "standardDeviation": "2483.05", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2477.93", "standardDeviation": "108.003", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168668", "standardDeviation": "3614.13", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230523", "standardDeviation": "4600.33", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2484.75", "standardDeviation": "103.976", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "336474", "standardDeviation": "6865.96", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "460452", "standardDeviation": "9407.25", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2498.91", "standardDeviation": "95.1941", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "672724", "standardDeviation": "12432.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "933204", "standardDeviation": "122693", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2438.36", "standardDeviation": "73.9164", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.3524e+06", "standardDeviation": "32443.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.84122e+06", "standardDeviation": "19839.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2455.06", "standardDeviation": "117.501", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "127086", "standardDeviation": "2348.69", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "151335", "standardDeviation": "3106.62", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2426.72", "standardDeviation": "88.5851", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "258449", "standardDeviation": "4511.42", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "303148", "standardDeviation": "5976.22", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2449.63", "standardDeviation": "83.6072", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "502319", "standardDeviation": "7665.47", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "603628", "standardDeviation": "10033.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2397.99", "standardDeviation": "123.042", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.02784e+06", "standardDeviation": "12513", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.21487e+06", "standardDeviation": "16693.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2460.92", "standardDeviation": "112.424", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.72053e+06", "standardDeviation": "96010.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.9764e+06", "standardDeviation": "20094.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2518.85", "standardDeviation": "308.943", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..c0bbfad Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..ad59506 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png new file mode 100644 index 0000000..c56b029 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/linear_time.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..79f8d60 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "262023", "standardDeviation": "12662.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "271717", "standardDeviation": "2590.97", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "511291", "standardDeviation": "4616.01", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275766", "standardDeviation": "3628.07", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "995427", "standardDeviation": "5577.17", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278151", "standardDeviation": "3153.95", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.95987e+06", "standardDeviation": "13357.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284379", "standardDeviation": "3126.15", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.93612e+06", "standardDeviation": "16379.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "310640", "standardDeviation": "3731.15", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json new file mode 100644 index 0000000..295dc09 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210742", "standardDeviation": "3075.06", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41259.4", "standardDeviation": "1492.8", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "436857", "standardDeviation": "3452.1", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42030.1", "standardDeviation": "1759.88", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "898596", "standardDeviation": "5610.81", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41884.1", "standardDeviation": "1017.37", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.81903e+06", "standardDeviation": "212842", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42605.2", "standardDeviation": "923.106", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.6063e+06", "standardDeviation": "15092.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130452", "standardDeviation": "1679.88", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "251717", "standardDeviation": "48247.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35374.9", "standardDeviation": "1071.82", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "489902", "standardDeviation": "4106.98", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35913.2", "standardDeviation": "802.525", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976803", "standardDeviation": "6275.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35825.4", "standardDeviation": "605.12", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.96097e+06", "standardDeviation": "20798.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40892.4", "standardDeviation": "3512.77", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.92633e+06", "standardDeviation": "8784.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124305", "standardDeviation": "3655.53", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json new file mode 100644 index 0000000..51895cf --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84348.1", "standardDeviation": "2232.4", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115262", "standardDeviation": "2266.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2458.42", "standardDeviation": "68.1237", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168193", "standardDeviation": "3648.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230458", "standardDeviation": "4793.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2528.46", "standardDeviation": "146.556", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "349615", "standardDeviation": "125291", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "460957", "standardDeviation": "8882.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2415.37", "standardDeviation": "74.0854", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "673237", "standardDeviation": "11455.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "920296", "standardDeviation": "14918.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2450.21", "standardDeviation": "101.383", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34401e+06", "standardDeviation": "18040.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.83773e+06", "standardDeviation": "20051.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2460.82", "standardDeviation": "133.476", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138412", "standardDeviation": "1946.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159918", "standardDeviation": "61273.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2477.07", "standardDeviation": "138.537", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "248779", "standardDeviation": "3341.68", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "315277", "standardDeviation": "4030.23", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2440.78", "standardDeviation": "102.295", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "546913", "standardDeviation": "4761.62", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "621433", "standardDeviation": "7786.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2417.24", "standardDeviation": "98.0829", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11089e+06", "standardDeviation": "188415", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.26333e+06", "standardDeviation": "19442.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2438.59", "standardDeviation": "114.032", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.66647e+06", "standardDeviation": "16678.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.024e+06", "standardDeviation": "13124.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2467.8", "standardDeviation": "253.391", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..99b88a4 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "98018.9", "standardDeviation": "1917.76", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "130866", "standardDeviation": "2167.58", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2605.28", "standardDeviation": "61.1018", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196571", "standardDeviation": "2787.89", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "261502", "standardDeviation": "3580.23", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2663.53", "standardDeviation": "150.903", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "390567", "standardDeviation": "4755.34", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "521961", "standardDeviation": "6141.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2585.62", "standardDeviation": "172.741", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "780375", "standardDeviation": "7647.89", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.07094e+06", "standardDeviation": "254021", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2599.19", "standardDeviation": "89.209", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56011e+06", "standardDeviation": "11188.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.08365e+06", "standardDeviation": "11964.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2533.25", "standardDeviation": "106.883", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113941", "standardDeviation": "1753.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "133616", "standardDeviation": "2255.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2583.3", "standardDeviation": "353.807", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "221308", "standardDeviation": "2769.35", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "278281", "standardDeviation": "121696", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2565.79", "standardDeviation": "69.3371", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "456665", "standardDeviation": "7480.27", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "530096", "standardDeviation": "5776.97", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2549.4", "standardDeviation": "225.382", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "920683", "standardDeviation": "10917.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0661e+06", "standardDeviation": "9672.72", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2572.78", "standardDeviation": "362.046", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34854e+06", "standardDeviation": "23657.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.75193e+06", "standardDeviation": "19244.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2565.4", "standardDeviation": "170.903", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log b/160541/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log new file mode 100644 index 0000000..978ef3e --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Oct 29 14:04:08 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:61:00.0 Off | 0 | +| N/A 28C P0 59W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json new file mode 100644 index 0000000..69dec04 --- /dev/null +++ b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "97130.9", "standardDeviation": "1297.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "129966", "standardDeviation": "871.436", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2674.77", "standardDeviation": "96.2327", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194214", "standardDeviation": "1270.86", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "260001", "standardDeviation": "1602.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2696.27", "standardDeviation": "1010.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "391496", "standardDeviation": "6159.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "522638", "standardDeviation": "6451.47", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2611.61", "standardDeviation": "87.0783", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "783528", "standardDeviation": "12464.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04399e+06", "standardDeviation": "10452", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2661.66", "standardDeviation": "130.011", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56849e+06", "standardDeviation": "18521.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.08815e+06", "standardDeviation": "15930.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2646.17", "standardDeviation": "139.318", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "114545", "standardDeviation": "2646.02", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "134388", "standardDeviation": "2500.4", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2608.93", "standardDeviation": "103.414", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "228224", "standardDeviation": "3574.22", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "269723", "standardDeviation": "5790.57", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2582.1", "standardDeviation": "98.8384", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "452224", "standardDeviation": "6973.45", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "535470", "standardDeviation": "9633.08", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2609.98", "standardDeviation": "215.232", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "913004", "standardDeviation": "11213.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07026e+06", "standardDeviation": "15442.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2534.28", "standardDeviation": "203.436", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.19174e+06", "standardDeviation": "25719.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.60378e+06", "standardDeviation": "28161.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2589.84", "standardDeviation": "153.359", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..5ffa18e Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_fvops.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..a8ae369 Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_relative.png differ diff --git a/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..682221a Binary files /dev/null and b/160541/neon-cluster-meta-runner-neon-nvidia-h100/upwind_time.png differ diff --git a/172462/neon-cluster-meta-runner-amd/divOperator.json b/172462/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..09b5e31 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "217267", "standardDeviation": "2984.03", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "626729", "standardDeviation": "343042", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "471331", "standardDeviation": "2860.64", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "573236", "standardDeviation": "21051.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "923796", "standardDeviation": "2296.19", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "659276", "standardDeviation": "22823.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83385e+06", "standardDeviation": "30469.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "698056", "standardDeviation": "22033.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.91029e+06", "standardDeviation": "23831.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "737015", "standardDeviation": "23899.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/divOperator_fvops.png b/172462/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..6af5e38 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-amd/divOperator_relative.png b/172462/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..06362a0 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/172462/neon-cluster-meta-runner-amd/divOperator_time.png b/172462/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..da92518 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/172462/neon-cluster-meta-runner-amd/field.json b/172462/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..f2ff64d --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84072.1", "standardDeviation": "3298.95", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "82592.3", "standardDeviation": "8381.43", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "294571", "standardDeviation": "16127.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "79454.1", "standardDeviation": "8422.1", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "366582", "standardDeviation": "1708.55", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113339", "standardDeviation": "26532.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "712842", "standardDeviation": "1852.74", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128336", "standardDeviation": "61413.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.42261e+06", "standardDeviation": "68402", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152080", "standardDeviation": "64170.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "43053.9", "standardDeviation": "2019.54", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59161.7", "standardDeviation": "9021.59", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "140837", "standardDeviation": "1725.61", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60956.4", "standardDeviation": "8913.49", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "356331", "standardDeviation": "1765.46", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "94984.6", "standardDeviation": "43427.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "711576", "standardDeviation": "1669.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "110177", "standardDeviation": "60793.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.41736e+06", "standardDeviation": "1868.14", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "135997", "standardDeviation": "46504.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/field_fvops.png b/172462/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..412ffb4 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-amd/field_relative.png b/172462/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..a3831e2 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/172462/neon-cluster-meta-runner-amd/field_time.png b/172462/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..471084b Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/172462/neon-cluster-meta-runner-amd/linear.json b/172462/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..bdc9735 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39132.2", "standardDeviation": "1474.27", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51050.8", "standardDeviation": "967.998", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1718.92", "standardDeviation": "911.367", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113873", "standardDeviation": "1150.89", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "113248", "standardDeviation": "1617.73", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1768.6", "standardDeviation": "1172.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "228104", "standardDeviation": "1454.03", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "226249", "standardDeviation": "1665.03", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1729.23", "standardDeviation": "1299.68", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "455119", "standardDeviation": "2010.94", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "452066", "standardDeviation": "2338.07", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1855.55", "standardDeviation": "2219.77", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "916740", "standardDeviation": "28171.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "904751", "standardDeviation": "1608.13", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1780.6", "standardDeviation": "1682.87", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "117618", "standardDeviation": "2070.09", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "114332", "standardDeviation": "1468.75", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1704.24", "standardDeviation": "1235.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "234589", "standardDeviation": "1298.52", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "227933", "standardDeviation": "1408.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1702.16", "standardDeviation": "1157.57", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "468888", "standardDeviation": "1620.21", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "457200", "standardDeviation": "1949.02", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1895.41", "standardDeviation": "2069.11", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "936386", "standardDeviation": "1044.44", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "911208", "standardDeviation": "1813.17", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1745.51", "standardDeviation": "1709.74", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.30414e+06", "standardDeviation": "15278.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.34098e+06", "standardDeviation": "33002.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1866.08", "standardDeviation": "1962.54", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/linear_fvops.png b/172462/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..56c97bb Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-amd/linear_relative.png b/172462/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..cb6ec95 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/172462/neon-cluster-meta-runner-amd/linear_time.png b/172462/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..85ef04e Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/172462/neon-cluster-meta-runner-amd/main/divOperator.json b/172462/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..951b659 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "213027", "standardDeviation": "3379.98", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "547960", "standardDeviation": "5001.85", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "435512", "standardDeviation": "3042.96", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "552876", "standardDeviation": "4140.62", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "872530", "standardDeviation": "6374.53", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "736675", "standardDeviation": "25770.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82262e+06", "standardDeviation": "5342.05", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "691633", "standardDeviation": "24554", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.94758e+06", "standardDeviation": "21229.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "738885", "standardDeviation": "23321.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/main/field.json b/172462/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..3dc3d1c --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "46890.4", "standardDeviation": "1493.51", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72494.9", "standardDeviation": "8158.35", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "150560", "standardDeviation": "2035.21", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "76559.3", "standardDeviation": "8279.44", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "355364", "standardDeviation": "1633.49", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109435", "standardDeviation": "7358.33", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "706112", "standardDeviation": "1483.97", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121649", "standardDeviation": "8451.07", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.40614e+06", "standardDeviation": "2033.17", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147411", "standardDeviation": "10220.1", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "45356.6", "standardDeviation": "1672.35", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58222.4", "standardDeviation": "9465.12", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "139353", "standardDeviation": "1558.16", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60836.3", "standardDeviation": "8552.01", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "353624", "standardDeviation": "1651.83", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93022.7", "standardDeviation": "8632.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "704659", "standardDeviation": "1755.25", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "107583", "standardDeviation": "13875.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.40601e+06", "standardDeviation": "1776.7", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132286", "standardDeviation": "4988.78", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/main/linear.json b/172462/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..ae1ed80 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40165.1", "standardDeviation": "2162.28", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51615.1", "standardDeviation": "1073.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1708.06", "standardDeviation": "1088.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130527", "standardDeviation": "1559.81", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131059", "standardDeviation": "1442.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1734.25", "standardDeviation": "1180.83", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "259765", "standardDeviation": "2111.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "261595", "standardDeviation": "1767.19", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1689.12", "standardDeviation": "1444.52", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "519140", "standardDeviation": "4480.69", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "519166", "standardDeviation": "2103.89", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1913.65", "standardDeviation": "2584.17", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.03386e+06", "standardDeviation": "6252.79", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.03256e+06", "standardDeviation": "2577.25", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1909.86", "standardDeviation": "2310.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "133768", "standardDeviation": "1252.76", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136989", "standardDeviation": "1577.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1647.51", "standardDeviation": "1475.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261433", "standardDeviation": "1632.66", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "261506", "standardDeviation": "2763.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1786.14", "standardDeviation": "1846.64", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "533192", "standardDeviation": "3680.96", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "545874", "standardDeviation": "2534.59", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1937.79", "standardDeviation": "2532.98", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.06627e+06", "standardDeviation": "1836.92", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09713e+06", "standardDeviation": "4285.94", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1876.29", "standardDeviation": "2676.85", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.49826e+06", "standardDeviation": "13245.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.54143e+06", "standardDeviation": "14332", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2051.97", "standardDeviation": "2931.94", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/main/upwind.json b/172462/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..93d00f0 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44653.7", "standardDeviation": "7568.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49445", "standardDeviation": "1448.63", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1507.77", "standardDeviation": "1010.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115199", "standardDeviation": "1158.13", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116363", "standardDeviation": "1408.43", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1596.2", "standardDeviation": "1545.46", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "226386", "standardDeviation": "3631.91", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "224718", "standardDeviation": "1917.58", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1535.41", "standardDeviation": "1344.04", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "453074", "standardDeviation": "5439.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "456793", "standardDeviation": "4898.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1725.78", "standardDeviation": "2849.11", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "909071", "standardDeviation": "8015.69", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "922272", "standardDeviation": "8072.45", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1692.78", "standardDeviation": "2173.07", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130875", "standardDeviation": "1766.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "127735", "standardDeviation": "1154.95", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1566.84", "standardDeviation": "1507.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261166", "standardDeviation": "2070.31", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "252168", "standardDeviation": "1858.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1610.65", "standardDeviation": "1690.78", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "518386", "standardDeviation": "5164.19", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "505321", "standardDeviation": "1896.55", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1796.81", "standardDeviation": "2367.02", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03295e+06", "standardDeviation": "4248.88", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0119e+06", "standardDeviation": "1433.91", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1674.24", "standardDeviation": "2096.46", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.32124e+06", "standardDeviation": "17638.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.2769e+06", "standardDeviation": "16987.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1695.79", "standardDeviation": "1965.43", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/system-info.log b/172462/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/172462/neon-cluster-meta-runner-amd/upwind.json b/172462/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..864c2b2 --- /dev/null +++ b/172462/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33484.7", "standardDeviation": "2576.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50425.7", "standardDeviation": "1079.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1545.49", "standardDeviation": "1287.04", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "100344", "standardDeviation": "1109.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "102326", "standardDeviation": "1421.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1632.58", "standardDeviation": "1270.44", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "201579", "standardDeviation": "1758.47", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "201766", "standardDeviation": "1973.94", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1582.26", "standardDeviation": "1290.96", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "402186", "standardDeviation": "1831.72", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "398801", "standardDeviation": "1942.18", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2224.78", "standardDeviation": "4585.48", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "851826", "standardDeviation": "21850.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "793792", "standardDeviation": "4668.18", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1677.83", "standardDeviation": "2041.12", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "120531", "standardDeviation": "1361.76", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "119566", "standardDeviation": "1667.27", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1589.33", "standardDeviation": "1389.69", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "227647", "standardDeviation": "1641.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "227134", "standardDeviation": "1643.58", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1571.69", "standardDeviation": "1246.65", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "481677", "standardDeviation": "2628.33", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "466577", "standardDeviation": "5088.83", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1721.09", "standardDeviation": "2183.68", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "965316", "standardDeviation": "3450.04", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "932909", "standardDeviation": "8042.73", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1679.01", "standardDeviation": "1911.12", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.27438e+06", "standardDeviation": "32200.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.49781e+06", "standardDeviation": "25919.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1687.88", "standardDeviation": "2013.43", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-amd/upwind_fvops.png b/172462/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..6eee34e Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-amd/upwind_relative.png b/172462/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..0aeaecb Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/172462/neon-cluster-meta-runner-amd/upwind_time.png b/172462/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..ac43d97 Binary files /dev/null and b/172462/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/divOperator.json b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator.json new file mode 100644 index 0000000..61a1588 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "258492", "standardDeviation": "29092.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "267109", "standardDeviation": "3038.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "501808", "standardDeviation": "28994.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "272067", "standardDeviation": "3254.56", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "973605", "standardDeviation": "66477.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "273956", "standardDeviation": "2312.83", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.9102e+06", "standardDeviation": "146542", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "279645", "standardDeviation": "4041.57", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.27197e+06", "standardDeviation": "19012.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "304379", "standardDeviation": "3193.05", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..3675fd7 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..9341dc2 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..405b105 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/field.json b/172462/neon-cluster-meta-runner-nvidia-h100/field.json new file mode 100644 index 0000000..d5f954b --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "211015", "standardDeviation": "7305.32", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40918", "standardDeviation": "1259.32", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "436484", "standardDeviation": "10573.9", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40286.4", "standardDeviation": "1309.97", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "891999", "standardDeviation": "24419.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40986.8", "standardDeviation": "909.177", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.77817e+06", "standardDeviation": "19341.6", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41523.4", "standardDeviation": "967.513", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.58528e+06", "standardDeviation": "15677.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132765", "standardDeviation": "2725.92", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "280861", "standardDeviation": "35643.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34612.2", "standardDeviation": "712.185", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "553345", "standardDeviation": "6743.29", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35290.9", "standardDeviation": "731.858", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.10373e+06", "standardDeviation": "11307.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34973.2", "standardDeviation": "835.446", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.23908e+06", "standardDeviation": "154351", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36749.8", "standardDeviation": "3257.89", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.45247e+06", "standardDeviation": "6340.54", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123986", "standardDeviation": "1804.87", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/field_fvops.png b/172462/neon-cluster-meta-runner-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..bf52a69 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/field_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/field_relative.png b/172462/neon-cluster-meta-runner-nvidia-h100/field_relative.png new file mode 100644 index 0000000..dc78c39 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/field_relative.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/field_time.png b/172462/neon-cluster-meta-runner-nvidia-h100/field_time.png new file mode 100644 index 0000000..e354916 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/field_time.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/linear.json b/172462/neon-cluster-meta-runner-nvidia-h100/linear.json new file mode 100644 index 0000000..b38b87b --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "121235", "standardDeviation": "2700.4", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147779", "standardDeviation": "4200.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2327.66", "standardDeviation": "91.4594", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176048", "standardDeviation": "79457.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295328", "standardDeviation": "8065.47", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2332.88", "standardDeviation": "65.3455", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "336554", "standardDeviation": "6836.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "588487", "standardDeviation": "11025.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2289.03", "standardDeviation": "85.9113", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "680824", "standardDeviation": "58832.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17812e+06", "standardDeviation": "21945.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2460.48", "standardDeviation": "186.525", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34704e+06", "standardDeviation": "18215.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.42032e+06", "standardDeviation": "127423", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2363.13", "standardDeviation": "178.927", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177775", "standardDeviation": "16544.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "178493", "standardDeviation": "16458.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2303.65", "standardDeviation": "108.414", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "244241", "standardDeviation": "40396.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "276160", "standardDeviation": "36923.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2360.6", "standardDeviation": "111.029", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "500019", "standardDeviation": "86292.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "569166", "standardDeviation": "87725.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2288.1", "standardDeviation": "164.345", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.05161e+06", "standardDeviation": "191541", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.13629e+06", "standardDeviation": "196356", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2365.42", "standardDeviation": "209.885", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "4.13506e+06", "standardDeviation": "426204", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "4.14518e+06", "standardDeviation": "388245", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2340.89", "standardDeviation": "365.37", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png b/172462/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..d80f264 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/linear_relative.png b/172462/neon-cluster-meta-runner-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..0e2d067 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/linear_relative.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/linear_time.png b/172462/neon-cluster-meta-runner-nvidia-h100/linear_time.png new file mode 100644 index 0000000..a2959fa Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/linear_time.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json b/172462/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..58f9030 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "254113", "standardDeviation": "2959.24", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277749", "standardDeviation": "3181.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "499191", "standardDeviation": "4684.61", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281570", "standardDeviation": "2182.08", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "964357", "standardDeviation": "6588.49", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "282946", "standardDeviation": "2958.75", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.88714e+06", "standardDeviation": "9234.52", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "288696", "standardDeviation": "3147.71", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.86975e+06", "standardDeviation": "17618.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "315430", "standardDeviation": "4302.78", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/main/field.json b/172462/neon-cluster-meta-runner-nvidia-h100/main/field.json new file mode 100644 index 0000000..0b3f312 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306998", "standardDeviation": "1359.27", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40108.2", "standardDeviation": "775.615", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "632146", "standardDeviation": "1525.57", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40715.3", "standardDeviation": "1463.47", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.28809e+06", "standardDeviation": "1229.68", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49086.4", "standardDeviation": "1483.83", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.56917e+06", "standardDeviation": "1615.16", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "49133.8", "standardDeviation": "893.49", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.12652e+06", "standardDeviation": "16240.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150521", "standardDeviation": "18579.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "358379", "standardDeviation": "1415.58", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33967.1", "standardDeviation": "858.369", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "487274", "standardDeviation": "1416.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36145.8", "standardDeviation": "839.824", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "972101", "standardDeviation": "732.149", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36436.9", "standardDeviation": "591.824", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.94028e+06", "standardDeviation": "2118.56", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37102.4", "standardDeviation": "2133.27", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.88061e+06", "standardDeviation": "1451.64", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "120211", "standardDeviation": "1921.26", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/main/linear.json b/172462/neon-cluster-meta-runner-nvidia-h100/main/linear.json new file mode 100644 index 0000000..611e1f2 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84440.7", "standardDeviation": "2075.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115590", "standardDeviation": "2552.29", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2529.51", "standardDeviation": "117.886", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169147", "standardDeviation": "3653.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230423", "standardDeviation": "4791.26", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2520.24", "standardDeviation": "69.3006", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "367619", "standardDeviation": "130810", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "460927", "standardDeviation": "8495.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2552.36", "standardDeviation": "166.937", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "674810", "standardDeviation": "11677", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "919865", "standardDeviation": "14576.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2523.09", "standardDeviation": "136.714", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.35021e+06", "standardDeviation": "17656.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.84069e+06", "standardDeviation": "21586.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2482.03", "standardDeviation": "131.967", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121806", "standardDeviation": "2692.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150281", "standardDeviation": "4203.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2522.65", "standardDeviation": "111.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "240501", "standardDeviation": "4515.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "300722", "standardDeviation": "6378.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2523.64", "standardDeviation": "151.141", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "488696", "standardDeviation": "5974.38", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "598620", "standardDeviation": "10810.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2444.7", "standardDeviation": "129.723", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "982643", "standardDeviation": "15644.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.196e+06", "standardDeviation": "17127.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2506.97", "standardDeviation": "155.873", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.60138e+06", "standardDeviation": "21744.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.91011e+06", "standardDeviation": "18063.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2461.65", "standardDeviation": "274.395", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/main/upwind.json b/172462/neon-cluster-meta-runner-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..c29b5c4 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "97605.3", "standardDeviation": "2123.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131009", "standardDeviation": "1883.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2724.68", "standardDeviation": "144.65", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196100", "standardDeviation": "3941.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262394", "standardDeviation": "6066.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2720.85", "standardDeviation": "136.069", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "400592", "standardDeviation": "13098.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "649018", "standardDeviation": "22205.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2710.44", "standardDeviation": "525.196", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "782653", "standardDeviation": "13032.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04672e+06", "standardDeviation": "17239.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2682.33", "standardDeviation": "704.179", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56575e+06", "standardDeviation": "19260.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09222e+06", "standardDeviation": "21044", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2759.98", "standardDeviation": "92.8163", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113974", "standardDeviation": "1951.33", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "133869", "standardDeviation": "2401.42", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2650.12", "standardDeviation": "115.346", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "227726", "standardDeviation": "3493.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "268108", "standardDeviation": "5139.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2657.05", "standardDeviation": "96.6621", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "453498", "standardDeviation": "6440", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "535440", "standardDeviation": "9511.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2569.72", "standardDeviation": "74.964", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "911552", "standardDeviation": "10838.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07171e+06", "standardDeviation": "14362", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2634.62", "standardDeviation": "175.964", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.5985e+06", "standardDeviation": "22322.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.40604e+06", "standardDeviation": "23001.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2609.69", "standardDeviation": "362.889", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/system-info.log b/172462/neon-cluster-meta-runner-nvidia-h100/system-info.log new file mode 100644 index 0000000..2ed8464 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Tue Dec 2 15:21:23 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:CA:00.0 Off | 0 | +| N/A 36C P0 61W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/upwind.json b/172462/neon-cluster-meta-runner-nvidia-h100/upwind.json new file mode 100644 index 0000000..f5d2663 --- /dev/null +++ b/172462/neon-cluster-meta-runner-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "85604", "standardDeviation": "10174.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "118956", "standardDeviation": "14003.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2525.29", "standardDeviation": "156.539", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171398", "standardDeviation": "57899.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230897", "standardDeviation": "5924.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2501.11", "standardDeviation": "140.291", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "330650", "standardDeviation": "22188.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "460548", "standardDeviation": "12424", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2438.74", "standardDeviation": "117.143", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "671028", "standardDeviation": "51593.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "924273", "standardDeviation": "31535.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2545.67", "standardDeviation": "201.246", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.35262e+06", "standardDeviation": "104065", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.85398e+06", "standardDeviation": "60454.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2566.92", "standardDeviation": "251.281", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "116498", "standardDeviation": "13580", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137947", "standardDeviation": "13358.6", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2483.66", "standardDeviation": "163.746", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "228060", "standardDeviation": "41958.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "276080", "standardDeviation": "35940.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2487.59", "standardDeviation": "88.4541", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "455217", "standardDeviation": "10921.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "539829", "standardDeviation": "10807.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2523.64", "standardDeviation": "245.78", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "915856", "standardDeviation": "24119.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07317e+06", "standardDeviation": "20219.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.93", "standardDeviation": "122.204", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.60169e+06", "standardDeviation": "29423.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.75998e+06", "standardDeviation": "25263.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2416.17", "standardDeviation": "211.351", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..b127d0d Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..a6cdb45 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png differ diff --git a/172462/neon-cluster-meta-runner-nvidia-h100/upwind_time.png b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..5c0fe92 Binary files /dev/null and b/172462/neon-cluster-meta-runner-nvidia-h100/upwind_time.png differ diff --git a/194976/neon-cluster-meta-runner-amd/divOperator.json b/194976/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..6cac08e --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "242671", "standardDeviation": "5179.02", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "680760", "standardDeviation": "29534.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "542484", "standardDeviation": "37581.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "684494", "standardDeviation": "29092.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "986221", "standardDeviation": "172067", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "802248", "standardDeviation": "225424", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82314e+06", "standardDeviation": "189616", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "813620", "standardDeviation": "30425.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.79651e+06", "standardDeviation": "277896", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "890446", "standardDeviation": "206102", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/divOperator_fvops.png b/194976/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..fb2b301 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/194976/neon-cluster-meta-runner-amd/divOperator_relative.png b/194976/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..8f8be2c Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/194976/neon-cluster-meta-runner-amd/divOperator_time.png b/194976/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..26f91d5 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/194976/neon-cluster-meta-runner-amd/field.json b/194976/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..1db006e --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "109130", "standardDeviation": "7506.46", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99828.3", "standardDeviation": "18074.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "184022", "standardDeviation": "5489.16", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "84294.7", "standardDeviation": "5354.14", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "543213", "standardDeviation": "49391.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127515", "standardDeviation": "15909.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "961468", "standardDeviation": "144135", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "141871", "standardDeviation": "15528.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72887e+06", "standardDeviation": "284749", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "167227", "standardDeviation": "46804.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "59784.7", "standardDeviation": "4166.51", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63743.8", "standardDeviation": "9529.65", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "198715", "standardDeviation": "10555", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "67074.2", "standardDeviation": "6548.19", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "549986", "standardDeviation": "50249.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "97608.8", "standardDeviation": "16381.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "969339", "standardDeviation": "144317", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118981", "standardDeviation": "16907.7", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74454e+06", "standardDeviation": "280436", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142934", "standardDeviation": "10773.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/field_fvops.png b/194976/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..cef1ec5 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/194976/neon-cluster-meta-runner-amd/field_relative.png b/194976/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..f343c4a Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/194976/neon-cluster-meta-runner-amd/field_time.png b/194976/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..929ff1e Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/194976/neon-cluster-meta-runner-amd/linear.json b/194976/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..96719d3 --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "41726.6", "standardDeviation": "3672.29", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "55182.8", "standardDeviation": "1133.74", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1981.98", "standardDeviation": "1275.88", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206239", "standardDeviation": "6772.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "208336", "standardDeviation": "6740.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2017.61", "standardDeviation": "1580.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "393396", "standardDeviation": "41660.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "393723", "standardDeviation": "26796.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1953.66", "standardDeviation": "1824.27", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "709286", "standardDeviation": "82271", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "713703", "standardDeviation": "84912.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2275.27", "standardDeviation": "3305.28", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.23615e+06", "standardDeviation": "210227", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.24622e+06", "standardDeviation": "217859", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2290.46", "standardDeviation": "2512.45", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206918", "standardDeviation": "6878.45", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "210337", "standardDeviation": "6805.86", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1949.67", "standardDeviation": "1474.22", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "384837", "standardDeviation": "26873.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "395373", "standardDeviation": "27178.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1999.68", "standardDeviation": "2706.84", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "706521", "standardDeviation": "82017.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "714523", "standardDeviation": "84304.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2534.09", "standardDeviation": "4343.64", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.23937e+06", "standardDeviation": "209826", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.26772e+06", "standardDeviation": "211474", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2339.87", "standardDeviation": "2685.93", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.55139e+06", "standardDeviation": "315833", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.69051e+06", "standardDeviation": "291390", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1977.19", "standardDeviation": "1984.59", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/linear_fvops.png b/194976/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..39fdaa9 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/194976/neon-cluster-meta-runner-amd/linear_relative.png b/194976/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..80ac398 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/194976/neon-cluster-meta-runner-amd/linear_time.png b/194976/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..f86b3ad Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/194976/neon-cluster-meta-runner-amd/main/divOperator.json b/194976/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..6ea1ea4 --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "253408", "standardDeviation": "7261.81", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "593488", "standardDeviation": "29646.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "536650", "standardDeviation": "38209.9", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "604853", "standardDeviation": "36255.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "992124", "standardDeviation": "231600", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "696104", "standardDeviation": "33081.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82315e+06", "standardDeviation": "189299", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699314", "standardDeviation": "32206.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.77027e+06", "standardDeviation": "264120", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "771847", "standardDeviation": "38025.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/main/field.json b/194976/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..e206d5e --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51294.2", "standardDeviation": "3080.01", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "91159.5", "standardDeviation": "12164", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "198574", "standardDeviation": "6327.56", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99344", "standardDeviation": "9969.8", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "549642", "standardDeviation": "99687.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "116885", "standardDeviation": "9023.17", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "958817", "standardDeviation": "143171", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "134535", "standardDeviation": "9228.57", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71644e+06", "standardDeviation": "275450", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "171338", "standardDeviation": "123770", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "54496.4", "standardDeviation": "3335.02", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63480.4", "standardDeviation": "11724.4", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "207259", "standardDeviation": "6873.78", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "66140.6", "standardDeviation": "9455.86", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547712", "standardDeviation": "50026.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "112571", "standardDeviation": "92027.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "973032", "standardDeviation": "153576", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125704", "standardDeviation": "99938.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.73956e+06", "standardDeviation": "280670", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "153437", "standardDeviation": "83630.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/main/linear.json b/194976/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..dda66a9 --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40450.4", "standardDeviation": "3705.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52323", "standardDeviation": "1092", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2288.37", "standardDeviation": "1411.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177614", "standardDeviation": "6849.32", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "178066", "standardDeviation": "6571.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2487.46", "standardDeviation": "1930.94", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "336417", "standardDeviation": "20829.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "342821", "standardDeviation": "21459.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2094.53", "standardDeviation": "3135.87", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "609874", "standardDeviation": "66811", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "612455", "standardDeviation": "70675.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2199.31", "standardDeviation": "2581.54", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.09655e+06", "standardDeviation": "177685", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08586e+06", "standardDeviation": "181368", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2865.49", "standardDeviation": "2512.38", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177665", "standardDeviation": "5507.09", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "179955", "standardDeviation": "5856.53", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1988.91", "standardDeviation": "1584.01", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "336877", "standardDeviation": "20392.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "337368", "standardDeviation": "22022.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2281.35", "standardDeviation": "1917.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "610296", "standardDeviation": "68719.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "613254", "standardDeviation": "78087.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2680.1", "standardDeviation": "3082.37", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09263e+06", "standardDeviation": "166932", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07992e+06", "standardDeviation": "173682", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2900.67", "standardDeviation": "2321.51", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.65479e+06", "standardDeviation": "235002", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.5987e+06", "standardDeviation": "237771", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3113", "standardDeviation": "2927.89", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/main/upwind.json b/194976/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..bf0e4e0 --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49726.7", "standardDeviation": "2571.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49466.1", "standardDeviation": "2716.37", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2385.51", "standardDeviation": "1424", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182306", "standardDeviation": "5687.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "184296", "standardDeviation": "6171.18", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2321.54", "standardDeviation": "1747.16", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "345973", "standardDeviation": "19748.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "347024", "standardDeviation": "22061.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2364.74", "standardDeviation": "2004.65", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "629352", "standardDeviation": "65877", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "643606", "standardDeviation": "69497.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2870.92", "standardDeviation": "3927.23", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.12096e+06", "standardDeviation": "175371", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.10285e+06", "standardDeviation": "152787", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2687.72", "standardDeviation": "3650.86", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "192890", "standardDeviation": "6445.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "200754", "standardDeviation": "6195.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2333.2", "standardDeviation": "1906.81", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "369089", "standardDeviation": "22722.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "373877", "standardDeviation": "24919.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2254.92", "standardDeviation": "2375.84", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "679104", "standardDeviation": "71995.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "683308", "standardDeviation": "75568.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2692.41", "standardDeviation": "3599.52", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.18806e+06", "standardDeviation": "189144", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.22245e+06", "standardDeviation": "200184", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2881.37", "standardDeviation": "3675.67", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.59213e+06", "standardDeviation": "271981", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.7153e+06", "standardDeviation": "264191", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2622.83", "standardDeviation": "3951.96", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/system-info.log b/194976/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/194976/neon-cluster-meta-runner-amd/upwind.json b/194976/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..fa3499f --- /dev/null +++ b/194976/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33646.8", "standardDeviation": "5298.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44116.7", "standardDeviation": "2974.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2161.99", "standardDeviation": "1578.79", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182131", "standardDeviation": "5784.89", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "185753", "standardDeviation": "5793.15", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3479.05", "standardDeviation": "5365.71", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "348855", "standardDeviation": "28530", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "351712", "standardDeviation": "21252.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4080.86", "standardDeviation": "9634.43", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "636603", "standardDeviation": "66124.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "644510", "standardDeviation": "68897.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "5081.39", "standardDeviation": "17176.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08397e+06", "standardDeviation": "154559", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.13398e+06", "standardDeviation": "178635", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "5538.68", "standardDeviation": "18542.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "194433", "standardDeviation": "6004.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "202554", "standardDeviation": "6185.37", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3882.05", "standardDeviation": "7985.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "372590", "standardDeviation": "22224.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "373207", "standardDeviation": "24403.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4065.26", "standardDeviation": "9029.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "679522", "standardDeviation": "72481.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "693404", "standardDeviation": "75939.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "5139.06", "standardDeviation": "15212", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.19303e+06", "standardDeviation": "187795", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.22916e+06", "standardDeviation": "195758", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "6079", "standardDeviation": "18420.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.42347e+06", "standardDeviation": "285278", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.50212e+06", "standardDeviation": "299065", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "6216.33", "standardDeviation": "18653.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/194976/neon-cluster-meta-runner-amd/upwind_fvops.png b/194976/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..185a744 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/194976/neon-cluster-meta-runner-amd/upwind_relative.png b/194976/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..585828b Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/194976/neon-cluster-meta-runner-amd/upwind_time.png b/194976/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..8372795 Binary files /dev/null and b/194976/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/198223/neon-cluster-meta-runner-amd/divOperator.json b/198223/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..5c55582 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "324103", "standardDeviation": "13155.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "704019", "standardDeviation": "17162.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "685557", "standardDeviation": "58380", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "687748", "standardDeviation": "12733.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29541e+06", "standardDeviation": "176016", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "815930", "standardDeviation": "23482.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.39154e+06", "standardDeviation": "279097", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "868190", "standardDeviation": "20852", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.11127e+06", "standardDeviation": "392146", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "916885", "standardDeviation": "32413.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/divOperator_fvops.png b/198223/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..075463b Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-amd/divOperator_relative.png b/198223/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..d523807 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/198223/neon-cluster-meta-runner-amd/divOperator_time.png b/198223/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..ae00e25 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/198223/neon-cluster-meta-runner-amd/field.json b/198223/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..7153b7f --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53850", "standardDeviation": "2820.87", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "98532.4", "standardDeviation": "8309.89", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "295298", "standardDeviation": "15629.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "80918.8", "standardDeviation": "3634", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "449067", "standardDeviation": "48128.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123731", "standardDeviation": "14439.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "849306", "standardDeviation": "107410", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139607", "standardDeviation": "11421.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54515e+06", "standardDeviation": "202709", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "159864", "standardDeviation": "5749.38", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "53559.4", "standardDeviation": "2411.13", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "65282.3", "standardDeviation": "4531.78", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "175185", "standardDeviation": "4997.52", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "66124.8", "standardDeviation": "4208.89", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "451524", "standardDeviation": "31450.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104173", "standardDeviation": "14312", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "858056", "standardDeviation": "107591", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "115338", "standardDeviation": "17929.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54997e+06", "standardDeviation": "204324", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140927", "standardDeviation": "8932.29", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/field_fvops.png b/198223/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..9604f1d Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-amd/field_relative.png b/198223/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..ad91af2 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/198223/neon-cluster-meta-runner-amd/field_time.png b/198223/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..020ad17 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/198223/neon-cluster-meta-runner-amd/gradOperator.json b/198223/neon-cluster-meta-runner-amd/gradOperator.json new file mode 100644 index 0000000..707f04d --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "1.71327e+06", "standardDeviation": "46723.3", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "690644", "standardDeviation": "15200.9", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.41614e+06", "standardDeviation": "58952.1", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "793570", "standardDeviation": "289031", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "6.79765e+06", "standardDeviation": "79830.7", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "865096", "standardDeviation": "23976.4", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.36597e+07", "standardDeviation": "126764", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "953070", "standardDeviation": "29587.8", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.86272e+07", "standardDeviation": "221837", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "1.11467e+06", "standardDeviation": "28820.4", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/linear.json b/198223/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..9e67552 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50050.9", "standardDeviation": "1515.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50519.8", "standardDeviation": "1025.17", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3446.2", "standardDeviation": "4092.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176943", "standardDeviation": "5763.51", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "165681", "standardDeviation": "5864.91", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1640.59", "standardDeviation": "1925.15", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "336839", "standardDeviation": "20429.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "320614", "standardDeviation": "17697.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1616.1", "standardDeviation": "1727.44", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "613780", "standardDeviation": "68781", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "585283", "standardDeviation": "62186.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1873.03", "standardDeviation": "3053.64", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08155e+06", "standardDeviation": "177709", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.07801e+06", "standardDeviation": "177767", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1912.82", "standardDeviation": "2501.31", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "178336", "standardDeviation": "5358.04", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150665", "standardDeviation": "5771.25", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1557.64", "standardDeviation": "1289.75", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "318592", "standardDeviation": "18231", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "338417", "standardDeviation": "23307.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1684.64", "standardDeviation": "1913.14", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "615765", "standardDeviation": "70438.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "474031", "standardDeviation": "17368.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1902.72", "standardDeviation": "2959.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09464e+06", "standardDeviation": "167972", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08921e+06", "standardDeviation": "179974", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1926.51", "standardDeviation": "3116.03", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.37988e+06", "standardDeviation": "244635", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.42326e+06", "standardDeviation": "236027", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2129.43", "standardDeviation": "3177.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/linear_fvops.png b/198223/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..620cea9 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-amd/linear_relative.png b/198223/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..ac2427e Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/198223/neon-cluster-meta-runner-amd/linear_time.png b/198223/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..9b04cb2 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/198223/neon-cluster-meta-runner-amd/main/divOperator.json b/198223/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..172e0de --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "220129", "standardDeviation": "4099.98", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "563501", "standardDeviation": "29716.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "512104", "standardDeviation": "18372.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "576226", "standardDeviation": "25270.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "863387", "standardDeviation": "8850.16", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "651764", "standardDeviation": "24742.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.76218e+06", "standardDeviation": "105393", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "723289", "standardDeviation": "240860", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.84809e+06", "standardDeviation": "168532", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "724669", "standardDeviation": "29615", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/main/field.json b/198223/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..c1821b4 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "52195.1", "standardDeviation": "2056.9", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72342", "standardDeviation": "8437.05", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "153497", "standardDeviation": "3107.1", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "79111.9", "standardDeviation": "7924.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "463514", "standardDeviation": "38745.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111227", "standardDeviation": "10444.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "813367", "standardDeviation": "86246.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117681", "standardDeviation": "10118.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.51506e+06", "standardDeviation": "166545", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149682", "standardDeviation": "12989", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "53385.7", "standardDeviation": "1918.36", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59012.7", "standardDeviation": "12629.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "178905", "standardDeviation": "4026.15", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63355.7", "standardDeviation": "9482.83", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445607", "standardDeviation": "32142.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123015", "standardDeviation": "201667", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "822307", "standardDeviation": "90520.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119089", "standardDeviation": "152903", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.51791e+06", "standardDeviation": "167834", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149882", "standardDeviation": "130447", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/main/linear.json b/198223/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..fad6013 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51021.3", "standardDeviation": "3559.91", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52915.5", "standardDeviation": "962.486", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1571.2", "standardDeviation": "1169.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "156040", "standardDeviation": "4411.72", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "157905", "standardDeviation": "4142.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1640.72", "standardDeviation": "1854.01", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "304444", "standardDeviation": "33757.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "302233", "standardDeviation": "15372.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1596.87", "standardDeviation": "2636.42", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "559528", "standardDeviation": "50145.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "609005", "standardDeviation": "70443", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1731.46", "standardDeviation": "2384.77", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.01326e+06", "standardDeviation": "121221", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "980721", "standardDeviation": "101619", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1542.73", "standardDeviation": "1740.42", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "154693", "standardDeviation": "4828.58", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "158313", "standardDeviation": "4141.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1475.42", "standardDeviation": "1729.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "265222", "standardDeviation": "9605.96", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "326236", "standardDeviation": "23356.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1625.1", "standardDeviation": "1777.13", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "526162", "standardDeviation": "38507.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "576717", "standardDeviation": "59064.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1760.39", "standardDeviation": "2435.89", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01721e+06", "standardDeviation": "102532", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.01763e+06", "standardDeviation": "120283", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1752.07", "standardDeviation": "2370.68", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.37137e+06", "standardDeviation": "213120", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.59884e+06", "standardDeviation": "246506", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1815.2", "standardDeviation": "2526.87", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/main/upwind.json b/198223/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..b82e599 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39907.8", "standardDeviation": "5531.7", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49784.7", "standardDeviation": "1328.56", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1645.99", "standardDeviation": "1218.4", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "148265", "standardDeviation": "3302.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147169", "standardDeviation": "5110.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1554.86", "standardDeviation": "1299.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "285991", "standardDeviation": "14038.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "282903", "standardDeviation": "14986.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1598.87", "standardDeviation": "1496.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "503176", "standardDeviation": "41230.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "491064", "standardDeviation": "43894", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1814.88", "standardDeviation": "2479", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "901309", "standardDeviation": "104377", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "919158", "standardDeviation": "129548", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1884.8", "standardDeviation": "3680.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155427", "standardDeviation": "3160.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159126", "standardDeviation": "5252.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1659.89", "standardDeviation": "1633.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "301061", "standardDeviation": "11953.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "289547", "standardDeviation": "13353.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1768.17", "standardDeviation": "1734.09", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "586322", "standardDeviation": "45654", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "517471", "standardDeviation": "32265.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1705.16", "standardDeviation": "2087.61", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0622e+06", "standardDeviation": "116061", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "978723", "standardDeviation": "87349.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1618.29", "standardDeviation": "1958.72", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.39458e+06", "standardDeviation": "171814", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.97839e+06", "standardDeviation": "227056", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1990.75", "standardDeviation": "2455.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/system-info.log b/198223/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/198223/neon-cluster-meta-runner-amd/upwind.json b/198223/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..c54240f --- /dev/null +++ b/198223/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43462.1", "standardDeviation": "2388.95", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "43324", "standardDeviation": "1330.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1660.83", "standardDeviation": "1539.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "181830", "standardDeviation": "5746.87", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "183363", "standardDeviation": "6313.24", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1868.49", "standardDeviation": "1673.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "314815", "standardDeviation": "18386.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "302149", "standardDeviation": "14961.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1791.83", "standardDeviation": "2460.02", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "576733", "standardDeviation": "52741.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "566292", "standardDeviation": "49659", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1828.16", "standardDeviation": "3359.32", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.00871e+06", "standardDeviation": "104377", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "880833", "standardDeviation": "102987", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1847.24", "standardDeviation": "2900.36", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163164", "standardDeviation": "4929.97", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "172567", "standardDeviation": "5426.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1704.28", "standardDeviation": "1797.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "299907", "standardDeviation": "12740.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "308151", "standardDeviation": "15412.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1662.28", "standardDeviation": "1515.08", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "610391", "standardDeviation": "52743.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "601083", "standardDeviation": "61540.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1913.5", "standardDeviation": "3120.33", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09613e+06", "standardDeviation": "138714", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.03714e+06", "standardDeviation": "126375", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1791.46", "standardDeviation": "2698.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.26723e+06", "standardDeviation": "258411", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.26893e+06", "standardDeviation": "251196", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1989.96", "standardDeviation": "3156.27", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-amd/upwind_fvops.png b/198223/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..f99a954 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-amd/upwind_relative.png b/198223/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..fc1af40 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/198223/neon-cluster-meta-runner-amd/upwind_time.png b/198223/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..4253990 Binary files /dev/null and b/198223/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/divOperator.json b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator.json new file mode 100644 index 0000000..1d48eec --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "661279", "standardDeviation": "5425.75", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "466927", "standardDeviation": "7696.63", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.29272e+06", "standardDeviation": "9686.07", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "574974", "standardDeviation": "5326.77", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74762e+06", "standardDeviation": "9803.69", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "589124", "standardDeviation": "9462.44", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.47865e+06", "standardDeviation": "12632", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "598083", "standardDeviation": "7382.85", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "7.2487e+06", "standardDeviation": "93413.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "632953", "standardDeviation": "6285.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png new file mode 100644 index 0000000..3a654d6 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png new file mode 100644 index 0000000..5ec465b Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_relative.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png new file mode 100644 index 0000000..43c71f3 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/divOperator_time.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/field.json b/198223/neon-cluster-meta-runner-nvidia-h100/field.json new file mode 100644 index 0000000..886a73e --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210361", "standardDeviation": "3374.29", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126471", "standardDeviation": "4121.6", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "436338", "standardDeviation": "3631.08", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130515", "standardDeviation": "3698.71", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "895305", "standardDeviation": "5748.33", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132499", "standardDeviation": "4192.77", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.81066e+06", "standardDeviation": "237732", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "138662", "standardDeviation": "3669.78", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.59753e+06", "standardDeviation": "15546.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143622", "standardDeviation": "2760.87", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "277420", "standardDeviation": "2675.97", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123262", "standardDeviation": "3379.95", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "550841", "standardDeviation": "2098.27", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124125", "standardDeviation": "3678.68", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.1026e+06", "standardDeviation": "6924.81", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124462", "standardDeviation": "1871.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.21605e+06", "standardDeviation": "13270.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "129811", "standardDeviation": "4332.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.44134e+06", "standardDeviation": "4679.29", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "134898", "standardDeviation": "2744.38", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/field_fvops.png b/198223/neon-cluster-meta-runner-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..26cecc9 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/field_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/field_relative.png b/198223/neon-cluster-meta-runner-nvidia-h100/field_relative.png new file mode 100644 index 0000000..4a85581 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/field_relative.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/field_time.png b/198223/neon-cluster-meta-runner-nvidia-h100/field_time.png new file mode 100644 index 0000000..f02e31b Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/field_time.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/gradOperator.json b/198223/neon-cluster-meta-runner-nvidia-h100/gradOperator.json new file mode 100644 index 0000000..ec2642c --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "2.95141e+06", "standardDeviation": "10538.6", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "582148", "standardDeviation": "6722.83", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.03529e+06", "standardDeviation": "256723", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "607014", "standardDeviation": "8481.6", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "8.02988e+06", "standardDeviation": "23409.5", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "649975", "standardDeviation": "15463.7", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.63213e+07", "standardDeviation": "108473", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "711342", "standardDeviation": "8787.82", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.34995e+07", "standardDeviation": "375818", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor", "mean": "860994", "standardDeviation": "9871.92", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/linear.json b/198223/neon-cluster-meta-runner-nvidia-h100/linear.json new file mode 100644 index 0000000..a3e6001 --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84285.8", "standardDeviation": "2983.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131374", "standardDeviation": "2794.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2502.39", "standardDeviation": "244.251", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169974", "standardDeviation": "3546.61", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "261962", "standardDeviation": "5045.17", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2513.03", "standardDeviation": "134.163", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "352263", "standardDeviation": "120707", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524550", "standardDeviation": "9878.96", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2495.2", "standardDeviation": "103.93", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "681748", "standardDeviation": "12028.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04865e+06", "standardDeviation": "16000.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2496", "standardDeviation": "201.139", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.35721e+06", "standardDeviation": "17846.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09608e+06", "standardDeviation": "23081.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2431.34", "standardDeviation": "89.1816", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "130063", "standardDeviation": "2746.12", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "165726", "standardDeviation": "3838.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2405.68", "standardDeviation": "143.641", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "261170", "standardDeviation": "4664.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "329629", "standardDeviation": "6592.96", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2479.75", "standardDeviation": "177.091", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "508770", "standardDeviation": "7982.91", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "659464", "standardDeviation": "11720.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2429.31", "standardDeviation": "101.479", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03453e+06", "standardDeviation": "20539.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.32064e+06", "standardDeviation": "18196.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2531.11", "standardDeviation": "186.806", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.70299e+06", "standardDeviation": "77866.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.21453e+06", "standardDeviation": "141980", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2410.63", "standardDeviation": "195.853", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png b/198223/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..31f2252 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/linear_relative.png b/198223/neon-cluster-meta-runner-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..748d370 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/linear_relative.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/linear_time.png b/198223/neon-cluster-meta-runner-nvidia-h100/linear_time.png new file mode 100644 index 0000000..786b1f0 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/linear_time.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json b/198223/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..a13177e --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "256997", "standardDeviation": "3261", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280390", "standardDeviation": "4073.31", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "504401", "standardDeviation": "5276.31", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "284791", "standardDeviation": "3897.63", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "976369", "standardDeviation": "8409.42", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285632", "standardDeviation": "3122.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.91381e+06", "standardDeviation": "12535.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "291255", "standardDeviation": "4088.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.05339e+06", "standardDeviation": "92141.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "316257", "standardDeviation": "3117.41", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/main/field.json b/198223/neon-cluster-meta-runner-nvidia-h100/main/field.json new file mode 100644 index 0000000..5210526 --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "213571", "standardDeviation": "26318.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40605", "standardDeviation": "3393.13", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "437267", "standardDeviation": "3558.82", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42272.1", "standardDeviation": "857.013", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "895935", "standardDeviation": "5568.85", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42980.1", "standardDeviation": "767.528", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80907e+06", "standardDeviation": "220452", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43970.6", "standardDeviation": "1130.43", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.57888e+06", "standardDeviation": "11801", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "136749", "standardDeviation": "2551.08", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "281567", "standardDeviation": "40151.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35500.5", "standardDeviation": "2175.32", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "553165", "standardDeviation": "4549.27", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36261.1", "standardDeviation": "1058.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.10339e+06", "standardDeviation": "6912.66", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36500.1", "standardDeviation": "870.805", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.22803e+06", "standardDeviation": "167027", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "36978.1", "standardDeviation": "1880.49", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.42108e+06", "standardDeviation": "3473.53", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127589", "standardDeviation": "2558.49", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/main/linear.json b/198223/neon-cluster-meta-runner-nvidia-h100/main/linear.json new file mode 100644 index 0000000..4e219de --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84045.9", "standardDeviation": "2844.44", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147568", "standardDeviation": "3184.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2603.67", "standardDeviation": "158.803", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168964", "standardDeviation": "3927.97", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295210", "standardDeviation": "6097.12", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2588.25", "standardDeviation": "152.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "351553", "standardDeviation": "130997", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589230", "standardDeviation": "10991.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2624.43", "standardDeviation": "156.936", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "674357", "standardDeviation": "12227.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17743e+06", "standardDeviation": "18532", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2544.7", "standardDeviation": "100.309", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34641e+06", "standardDeviation": "17779", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35334e+06", "standardDeviation": "20836.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2664.07", "standardDeviation": "110.952", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "126053", "standardDeviation": "2506.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141318", "standardDeviation": "2743.62", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2605.72", "standardDeviation": "102.103", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "252072", "standardDeviation": "5309.34", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "271874", "standardDeviation": "6311.78", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2583.98", "standardDeviation": "117.331", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "517705", "standardDeviation": "7677.05", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "561490", "standardDeviation": "8619.51", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2650.13", "standardDeviation": "188.686", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01371e+06", "standardDeviation": "13234", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12304e+06", "standardDeviation": "14921.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2565.72", "standardDeviation": "133.971", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.69385e+06", "standardDeviation": "94874.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.0404e+06", "standardDeviation": "95059.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2546.14", "standardDeviation": "201.454", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/main/upwind.json b/198223/neon-cluster-meta-runner-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..161d202 --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82438.8", "standardDeviation": "2880.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "114935", "standardDeviation": "2161.06", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2852.95", "standardDeviation": "170.797", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166394", "standardDeviation": "4260.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "242621", "standardDeviation": "11862.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2681.43", "standardDeviation": "202.586", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "334034", "standardDeviation": "63149.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "460008", "standardDeviation": "8090.98", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2640.83", "standardDeviation": "128.233", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "657458", "standardDeviation": "11837.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "920215", "standardDeviation": "13292.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2656.43", "standardDeviation": "136.714", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.31859e+06", "standardDeviation": "18456.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.83798e+06", "standardDeviation": "19977.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2672.4", "standardDeviation": "315.872", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "112071", "standardDeviation": "4209.79", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135344", "standardDeviation": "5136.85", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2748.63", "standardDeviation": "129.959", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "225399", "standardDeviation": "2892.63", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "269604", "standardDeviation": "4544.15", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2625.77", "standardDeviation": "63.7909", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "454394", "standardDeviation": "16394.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "536999", "standardDeviation": "8446.15", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2560.99", "standardDeviation": "247.624", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "917214", "standardDeviation": "39341.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07976e+06", "standardDeviation": "14288.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2679.74", "standardDeviation": "306.445", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.51885e+06", "standardDeviation": "138386", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.88442e+06", "standardDeviation": "49654.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2630.49", "standardDeviation": "159.769", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/system-info.log b/198223/neon-cluster-meta-runner-nvidia-h100/system-info.log new file mode 100644 index 0000000..a54d5f9 --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Jan 7 12:21:25 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:61:00.0 Off | 0 | +| N/A 28C P0 59W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/upwind.json b/198223/neon-cluster-meta-runner-nvidia-h100/upwind.json new file mode 100644 index 0000000..057f1c8 --- /dev/null +++ b/198223/neon-cluster-meta-runner-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "67284.1", "standardDeviation": "3045.97", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "98829.2", "standardDeviation": "1609.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2632.53", "standardDeviation": "124.649", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "141867", "standardDeviation": "8377.14", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "199155", "standardDeviation": "4878.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2648.71", "standardDeviation": "98.7815", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "287751", "standardDeviation": "116844", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "395945", "standardDeviation": "5384.47", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2580.81", "standardDeviation": "102.079", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "568309", "standardDeviation": "5441.08", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "791453", "standardDeviation": "9361.89", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2563.71", "standardDeviation": "162.868", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.15581e+06", "standardDeviation": "17805.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.58362e+06", "standardDeviation": "14347.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2589.98", "standardDeviation": "305.653", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "126821", "standardDeviation": "2102.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "123537", "standardDeviation": "2014.77", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2503.05", "standardDeviation": "172.831", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "234407", "standardDeviation": "5733.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "260025", "standardDeviation": "9391.84", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2536.62", "standardDeviation": "117.547", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "498682", "standardDeviation": "16178.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "485102", "standardDeviation": "8392.02", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2566.49", "standardDeviation": "100.089", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "991094", "standardDeviation": "8480.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.04129e+06", "standardDeviation": "14764.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2582.88", "standardDeviation": "290.786", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.49766e+06", "standardDeviation": "205201", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.69975e+06", "standardDeviation": "210666", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2563.84", "standardDeviation": "995.838", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..f6ba1c7 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..cb9e409 Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png differ diff --git a/198223/neon-cluster-meta-runner-nvidia-h100/upwind_time.png b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..92d406b Binary files /dev/null and b/198223/neon-cluster-meta-runner-nvidia-h100/upwind_time.png differ diff --git a/199938/neon-cluster-meta-runner-amd/field.json b/199938/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..eee86b9 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "95904.7", "standardDeviation": "4994.44", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92374.1", "standardDeviation": "4513.33", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "244239", "standardDeviation": "3654.99", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81340.7", "standardDeviation": "4826.09", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "496936", "standardDeviation": "37814.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118903", "standardDeviation": "22728.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "784561", "standardDeviation": "68809.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130982", "standardDeviation": "65043.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50449e+06", "standardDeviation": "153870", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "155007", "standardDeviation": "97253.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46619.8", "standardDeviation": "1982.07", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58697.1", "standardDeviation": "4286.83", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "184822", "standardDeviation": "4375.1", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59580", "standardDeviation": "4807.94", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "448086", "standardDeviation": "32580.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89858.7", "standardDeviation": "16933", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "794233", "standardDeviation": "75127.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103524", "standardDeviation": "48194.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.48505e+06", "standardDeviation": "128658", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132624", "standardDeviation": "48377.1", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/field_fvops.png b/199938/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..b58b01c Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-amd/field_relative.png b/199938/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..ebc1135 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/199938/neon-cluster-meta-runner-amd/field_time.png b/199938/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..d215f32 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/199938/neon-cluster-meta-runner-amd/gradOperator.json b/199938/neon-cluster-meta-runner-amd/gradOperator.json new file mode 100644 index 0000000..6e8c8f7 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_explicit", "mean": "1.79521e+06", "standardDeviation": "25206.4", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "706543", "standardDeviation": "12930.6", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.58814e+06", "standardDeviation": "40617.7", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "800947", "standardDeviation": "268247", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "7.15592e+06", "standardDeviation": "77606.9", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "900544", "standardDeviation": "24871.6", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "1.45221e+07", "standardDeviation": "339969", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "994806", "standardDeviation": "246595", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.08517e+07", "standardDeviation": "208036", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "1.1392e+06", "standardDeviation": "23692.3", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/linear.json b/199938/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..e438117 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39693.7", "standardDeviation": "2199.4", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50286.3", "standardDeviation": "702.563", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3354.72", "standardDeviation": "2554.96", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182077", "standardDeviation": "6311.42", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "150366", "standardDeviation": "4856.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1616.21", "standardDeviation": "1406.11", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "330353", "standardDeviation": "16438.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "321474", "standardDeviation": "15260.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1623.29", "standardDeviation": "1797.94", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "537246", "standardDeviation": "50385.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "528565", "standardDeviation": "43785.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1913.38", "standardDeviation": "3153.58", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.04329e+06", "standardDeviation": "148218", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "940265", "standardDeviation": "68926.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1848.84", "standardDeviation": "2374.89", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155333", "standardDeviation": "3467.06", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "167549", "standardDeviation": "5017.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1521.28", "standardDeviation": "1352.42", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "284781", "standardDeviation": "18787.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "257216", "standardDeviation": "8941.15", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1555.23", "standardDeviation": "1559.83", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "605603", "standardDeviation": "67524.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "584130", "standardDeviation": "69080.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1806.4", "standardDeviation": "2693.69", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.13079e+06", "standardDeviation": "151296", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.05606e+06", "standardDeviation": "149500", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1727.25", "standardDeviation": "2245.31", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.43009e+06", "standardDeviation": "162211", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.60146e+06", "standardDeviation": "109805", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1890.14", "standardDeviation": "2822.94", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/linear_fvops.png b/199938/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..7adac5d Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-amd/linear_relative.png b/199938/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..a21641f Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/199938/neon-cluster-meta-runner-amd/linear_time.png b/199938/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..3436828 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/199938/neon-cluster-meta-runner-amd/main/divOperator.json b/199938/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..4d7ed03 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "257055", "standardDeviation": "6846.68", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "559216", "standardDeviation": "32006.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "574285", "standardDeviation": "32654", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "553359", "standardDeviation": "28223.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.0478e+06", "standardDeviation": "115483", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "649282", "standardDeviation": "31091.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82334e+06", "standardDeviation": "2426.77", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "708292", "standardDeviation": "368749", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.87076e+06", "standardDeviation": "202575", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "716136", "standardDeviation": "36336.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/main/field.json b/199938/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..f1d5a5d --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "47896.7", "standardDeviation": "2752.35", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72632.7", "standardDeviation": "8034.93", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "160059", "standardDeviation": "4821.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81722.9", "standardDeviation": "8638.07", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "467405", "standardDeviation": "37958.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111085", "standardDeviation": "5031.08", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "849248", "standardDeviation": "106006", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "129457", "standardDeviation": "85548.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.51385e+06", "standardDeviation": "165890", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152306", "standardDeviation": "86359.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "51706.8", "standardDeviation": "1563.31", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "57221", "standardDeviation": "9306.15", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "182752", "standardDeviation": "4300.71", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63818.4", "standardDeviation": "9445.69", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "426078", "standardDeviation": "26899.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99381.6", "standardDeviation": "48467.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "791745", "standardDeviation": "74084.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "120788", "standardDeviation": "92254.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54236e+06", "standardDeviation": "197948", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143750", "standardDeviation": "101587", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/main/linear.json b/199938/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..0eb3815 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43443.8", "standardDeviation": "2478.61", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50979.5", "standardDeviation": "655.879", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1568.98", "standardDeviation": "1542.8", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "157625", "standardDeviation": "3867.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147265", "standardDeviation": "4500.68", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1658.83", "standardDeviation": "1898.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "266707", "standardDeviation": "11528.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "301682", "standardDeviation": "15997.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1590.65", "standardDeviation": "1473.67", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "615329", "standardDeviation": "68777", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "521407", "standardDeviation": "42730.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1699.74", "standardDeviation": "2458.14", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "989890", "standardDeviation": "96113.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.01369e+06", "standardDeviation": "125802", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1671.48", "standardDeviation": "1950.42", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155378", "standardDeviation": "3805.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156533", "standardDeviation": "4066.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1559.09", "standardDeviation": "1618.11", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "311855", "standardDeviation": "17119.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "296320", "standardDeviation": "15854.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1731.03", "standardDeviation": "3338.15", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "632322", "standardDeviation": "60796.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "659153", "standardDeviation": "66341.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1828.22", "standardDeviation": "3008.11", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.24098e+06", "standardDeviation": "215123", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.17632e+06", "standardDeviation": "155342", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1438.82", "standardDeviation": "1585.61", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.56282e+06", "standardDeviation": "210367", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.47485e+06", "standardDeviation": "198564", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1697.26", "standardDeviation": "2416.91", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/main/upwind.json b/199938/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..0396e97 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33462.5", "standardDeviation": "3786.64", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49364.4", "standardDeviation": "1173.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1534.49", "standardDeviation": "1646.34", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "139133", "standardDeviation": "2544.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "137468", "standardDeviation": "4338.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1561.49", "standardDeviation": "1210.31", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "269283", "standardDeviation": "12381", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "260353", "standardDeviation": "12789.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1544.99", "standardDeviation": "1350.65", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "473004", "standardDeviation": "35248", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "470001", "standardDeviation": "37097.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1677.39", "standardDeviation": "2291.86", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "904204", "standardDeviation": "104094", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "944869", "standardDeviation": "137805", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1762.92", "standardDeviation": "3222.81", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "174595", "standardDeviation": "4692.37", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "172669", "standardDeviation": "5239.59", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1602.76", "standardDeviation": "1558.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "315665", "standardDeviation": "14829.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "324701", "standardDeviation": "19385.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1565.9", "standardDeviation": "1367.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "573863", "standardDeviation": "36941.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "514732", "standardDeviation": "33486.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1633.2", "standardDeviation": "1991.86", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07655e+06", "standardDeviation": "117203", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.00663e+06", "standardDeviation": "97889", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1661.84", "standardDeviation": "1870.27", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.2609e+06", "standardDeviation": "201093", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.26438e+06", "standardDeviation": "159560", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1809.71", "standardDeviation": "1963.53", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/system-info.log b/199938/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/199938/neon-cluster-meta-runner-amd/upwind.json b/199938/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..e86048b --- /dev/null +++ b/199938/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49987.4", "standardDeviation": "5337.56", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "43233.9", "standardDeviation": "916.695", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1596.84", "standardDeviation": "1408.16", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "149498", "standardDeviation": "3186.84", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131710", "standardDeviation": "1101.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1675.7", "standardDeviation": "1513.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "310635", "standardDeviation": "84762.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "254747", "standardDeviation": "10555.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1754.93", "standardDeviation": "1937.28", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "469502", "standardDeviation": "37755.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "496051", "standardDeviation": "42843.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1849.08", "standardDeviation": "3088.85", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "986238", "standardDeviation": "157869", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "868711", "standardDeviation": "89175.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1817.96", "standardDeviation": "2721.57", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164482", "standardDeviation": "3653.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "145166", "standardDeviation": "1969.54", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1675.78", "standardDeviation": "1507.47", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "299154", "standardDeviation": "12321.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "275784", "standardDeviation": "11228.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1831.35", "standardDeviation": "2418.02", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "621161", "standardDeviation": "52168.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "545066", "standardDeviation": "42717.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1847.05", "standardDeviation": "2537.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10744e+06", "standardDeviation": "37537.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.1209e+06", "standardDeviation": "55672.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2049.5", "standardDeviation": "3744.31", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.22031e+06", "standardDeviation": "244133", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.58845e+06", "standardDeviation": "179855", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1917.67", "standardDeviation": "2757.01", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-amd/upwind_fvops.png b/199938/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..c9d9d72 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-amd/upwind_relative.png b/199938/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..0441e72 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/199938/neon-cluster-meta-runner-amd/upwind_time.png b/199938/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..2d79336 Binary files /dev/null and b/199938/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/field.json b/199938/neon-cluster-meta-runner-nvidia-h100/field.json new file mode 100644 index 0000000..7e341cf --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "210126", "standardDeviation": "3527.83", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143415", "standardDeviation": "3036.97", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "439336", "standardDeviation": "4896.87", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131381", "standardDeviation": "18109.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "921405", "standardDeviation": "16808.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "138059", "standardDeviation": "2943.85", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80148e+06", "standardDeviation": "27205.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "154170", "standardDeviation": "2821.58", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.58263e+06", "standardDeviation": "15763.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143538", "standardDeviation": "1938.15", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "281256", "standardDeviation": "35812", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123081", "standardDeviation": "2312.53", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "561212", "standardDeviation": "7352.34", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122127", "standardDeviation": "2118.69", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.12016e+06", "standardDeviation": "12054.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122872", "standardDeviation": "2359.12", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.21918e+06", "standardDeviation": "162602", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124624", "standardDeviation": "3329.19", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.47935e+06", "standardDeviation": "21780.4", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "135427", "standardDeviation": "2911.53", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/field_fvops.png b/199938/neon-cluster-meta-runner-nvidia-h100/field_fvops.png new file mode 100644 index 0000000..aeb9b34 Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/field_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/field_relative.png b/199938/neon-cluster-meta-runner-nvidia-h100/field_relative.png new file mode 100644 index 0000000..fde05fc Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/field_relative.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/field_time.png b/199938/neon-cluster-meta-runner-nvidia-h100/field_time.png new file mode 100644 index 0000000..a05dcbf Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/field_time.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/gradOperator.json b/199938/neon-cluster-meta-runner-nvidia-h100/gradOperator.json new file mode 100644 index 0000000..bdc5fde --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_explicit", "mean": "2.08719e+06", "standardDeviation": "37654.7", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "496139", "standardDeviation": "7361.62", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "4.17069e+06", "standardDeviation": "25252.6", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "619249", "standardDeviation": "13535.5", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "8.32999e+06", "standardDeviation": "394962", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "637338", "standardDeviation": "9180.55", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "1.67783e+07", "standardDeviation": "108600", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "701477", "standardDeviation": "7208.89", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.60662e+07", "standardDeviation": "336080", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "912919", "standardDeviation": "10160", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/linear.json b/199938/neon-cluster-meta-runner-nvidia-h100/linear.json new file mode 100644 index 0000000..8aa14be --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84222.2", "standardDeviation": "2182.33", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131307", "standardDeviation": "2722.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2183.72", "standardDeviation": "118.476", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168159", "standardDeviation": "3653.38", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "262482", "standardDeviation": "5554.05", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2213.18", "standardDeviation": "79.5041", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "350472", "standardDeviation": "129108", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "524609", "standardDeviation": "10019.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2232.31", "standardDeviation": "110.426", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "673815", "standardDeviation": "12525.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04752e+06", "standardDeviation": "16193.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2236.43", "standardDeviation": "111.205", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.35205e+06", "standardDeviation": "18250", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.09455e+06", "standardDeviation": "20066.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2238.77", "standardDeviation": "173.243", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "125112", "standardDeviation": "2670.55", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139677", "standardDeviation": "3646.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2224.68", "standardDeviation": "152.319", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "240941", "standardDeviation": "5189.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "271020", "standardDeviation": "5870.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2252.83", "standardDeviation": "143.208", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "494789", "standardDeviation": "5895.89", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "549446", "standardDeviation": "10445.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2525.76", "standardDeviation": "201.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00553e+06", "standardDeviation": "21083.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.10058e+06", "standardDeviation": "15552.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2242.65", "standardDeviation": "134.331", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.64407e+06", "standardDeviation": "16658.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.76384e+06", "standardDeviation": "41586", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2216.05", "standardDeviation": "155.638", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png b/199938/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png new file mode 100644 index 0000000..e171bac Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/linear_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/linear_relative.png b/199938/neon-cluster-meta-runner-nvidia-h100/linear_relative.png new file mode 100644 index 0000000..3ffc4cf Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/linear_relative.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/linear_time.png b/199938/neon-cluster-meta-runner-nvidia-h100/linear_time.png new file mode 100644 index 0000000..ae03cae Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/linear_time.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json b/199938/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json new file mode 100644 index 0000000..3578d8d --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "257801", "standardDeviation": "23990.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286803", "standardDeviation": "3803.01", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "586174", "standardDeviation": "34465.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "273678", "standardDeviation": "2778.79", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05756e+06", "standardDeviation": "67834.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280373", "standardDeviation": "5797.73", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.9069e+06", "standardDeviation": "13679.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281018", "standardDeviation": "4230.23", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.94416e+06", "standardDeviation": "37626.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "305565", "standardDeviation": "2698.36", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/main/field.json b/199938/neon-cluster-meta-runner-nvidia-h100/main/field.json new file mode 100644 index 0000000..4c1f2c7 --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "306416", "standardDeviation": "1923.73", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38752.7", "standardDeviation": "1098.58", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "632296", "standardDeviation": "6620.46", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41824.3", "standardDeviation": "3922.94", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.31123e+06", "standardDeviation": "201276", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "47331.3", "standardDeviation": "903.919", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.60482e+06", "standardDeviation": "285634", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41558.3", "standardDeviation": "895.188", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.5544e+06", "standardDeviation": "3439.31", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132871", "standardDeviation": "1527.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "279000", "standardDeviation": "3410.75", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30756", "standardDeviation": "2781.49", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "553137", "standardDeviation": "4988.83", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37260.1", "standardDeviation": "1172.91", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.10634e+06", "standardDeviation": "8282.22", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35353.8", "standardDeviation": "862.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.23203e+06", "standardDeviation": "144331", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37711.8", "standardDeviation": "1174.14", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.43401e+06", "standardDeviation": "14427.4", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128267", "standardDeviation": "3795.28", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/main/linear.json b/199938/neon-cluster-meta-runner-nvidia-h100/main/linear.json new file mode 100644 index 0000000..e29ae95 --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84166", "standardDeviation": "2200.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "147883", "standardDeviation": "3452.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2366.8", "standardDeviation": "72.4336", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "169214", "standardDeviation": "3820.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "295135", "standardDeviation": "5767.19", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2313.27", "standardDeviation": "152.802", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "350842", "standardDeviation": "123085", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "589005", "standardDeviation": "9976.38", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2403.2", "standardDeviation": "98.3379", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "676325", "standardDeviation": "12177.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17802e+06", "standardDeviation": "18380.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2393.17", "standardDeviation": "115.265", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34283e+06", "standardDeviation": "18872", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.35409e+06", "standardDeviation": "20162.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2388.77", "standardDeviation": "293.003", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "126527", "standardDeviation": "2457.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "141098", "standardDeviation": "2884.19", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2294.17", "standardDeviation": "89.068", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "251850", "standardDeviation": "4455.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "274080", "standardDeviation": "5269.83", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2342.68", "standardDeviation": "168.828", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "503612", "standardDeviation": "7529.33", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "551268", "standardDeviation": "9621.38", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2357.68", "standardDeviation": "165.49", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01891e+06", "standardDeviation": "11717.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11848e+06", "standardDeviation": "14526.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2389.62", "standardDeviation": "678.687", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.74259e+06", "standardDeviation": "18404.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.17175e+06", "standardDeviation": "17390.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2340.69", "standardDeviation": "166.637", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/main/upwind.json b/199938/neon-cluster-meta-runner-nvidia-h100/main/upwind.json new file mode 100644 index 0000000..2664a04 --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "82193.7", "standardDeviation": "2516.76", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "115761", "standardDeviation": "2496.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2528.93", "standardDeviation": "138.09", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "164274", "standardDeviation": "3403.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230987", "standardDeviation": "5035.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2451.43", "standardDeviation": "204.801", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "335155", "standardDeviation": "68156.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "459580", "standardDeviation": "8314.39", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2474.26", "standardDeviation": "113.708", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "657043", "standardDeviation": "11433.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "919019", "standardDeviation": "15213.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2469.01", "standardDeviation": "194.341", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.31033e+06", "standardDeviation": "19806", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.83753e+06", "standardDeviation": "20267.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2466.01", "standardDeviation": "263.024", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "114149", "standardDeviation": "2139.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "135178", "standardDeviation": "2605.03", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.91", "standardDeviation": "149.928", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "228040", "standardDeviation": "3566.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "268668", "standardDeviation": "5056.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2480.12", "standardDeviation": "102.852", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "450370", "standardDeviation": "6542.28", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "535702", "standardDeviation": "9611.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2431.64", "standardDeviation": "145.173", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "902920", "standardDeviation": "10629.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07883e+06", "standardDeviation": "14633.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2479.26", "standardDeviation": "336.522", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.68967e+06", "standardDeviation": "21947.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.55518e+06", "standardDeviation": "14359.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2510.93", "standardDeviation": "205.629", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/system-info.log b/199938/neon-cluster-meta-runner-nvidia-h100/system-info.log new file mode 100644 index 0000000..cd5d40e --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Fri Jan 9 17:14:08 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:CA:00.0 Off | 0 | +| N/A 37C P0 61W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/upwind.json b/199938/neon-cluster-meta-runner-nvidia-h100/upwind.json new file mode 100644 index 0000000..c3d634d --- /dev/null +++ b/199938/neon-cluster-meta-runner-nvidia-h100/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "67773.8", "standardDeviation": "1856.97", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "99841.4", "standardDeviation": "2434.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2378.17", "standardDeviation": "144.136", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "140569", "standardDeviation": "8423.23", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "199001", "standardDeviation": "4540.97", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2391.11", "standardDeviation": "139.848", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "286822", "standardDeviation": "107407", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "397469", "standardDeviation": "7873.61", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2376.37", "standardDeviation": "155.754", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "587915", "standardDeviation": "24769.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "793737", "standardDeviation": "14359.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2329.12", "standardDeviation": "187.121", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.11928e+06", "standardDeviation": "15979", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.5901e+06", "standardDeviation": "19901.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2334.24", "standardDeviation": "196.163", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113117", "standardDeviation": "2189.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "120348", "standardDeviation": "2737", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2287.4", "standardDeviation": "144.545", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "223264", "standardDeviation": "4122.11", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "239937", "standardDeviation": "5288.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2275.57", "standardDeviation": "172.051", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "452812", "standardDeviation": "6384.89", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "476238", "standardDeviation": "8609.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2255.98", "standardDeviation": "129.724", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "910114", "standardDeviation": "11115.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "974611", "standardDeviation": "15613.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2210.72", "standardDeviation": "107.098", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34158e+06", "standardDeviation": "19444.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.29609e+06", "standardDeviation": "23988.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2261.22", "standardDeviation": "323.603", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png new file mode 100644 index 0000000..3fd5ffa Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_fvops.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png new file mode 100644 index 0000000..6ffe7f6 Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_relative.png differ diff --git a/199938/neon-cluster-meta-runner-nvidia-h100/upwind_time.png b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_time.png new file mode 100644 index 0000000..22178e7 Binary files /dev/null and b/199938/neon-cluster-meta-runner-nvidia-h100/upwind_time.png differ diff --git a/221152/neon-cluster-meta-runner-amd/divOperator.json b/221152/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..b71e486 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "212066", "standardDeviation": "8626.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "645026", "standardDeviation": "22768.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "435347", "standardDeviation": "15715", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "648907", "standardDeviation": "14052.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "875253", "standardDeviation": "142826", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "750394", "standardDeviation": "21019.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.73612e+06", "standardDeviation": "75954.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "776420", "standardDeviation": "19339.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.21912e+06", "standardDeviation": "61575.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "824614", "standardDeviation": "11485.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/divOperator_fvops.png b/221152/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..add723e Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/221152/neon-cluster-meta-runner-amd/divOperator_relative.png b/221152/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..81ee045 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/221152/neon-cluster-meta-runner-amd/divOperator_time.png b/221152/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..6b89328 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/221152/neon-cluster-meta-runner-amd/field.json b/221152/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..0ec0a13 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "93719.9", "standardDeviation": "5392.24", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81695.5", "standardDeviation": "10967.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "131467", "standardDeviation": "14541.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "76442.3", "standardDeviation": "7001.93", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "356900", "standardDeviation": "24878.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111128", "standardDeviation": "24569.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "710916", "standardDeviation": "61859.3", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131765", "standardDeviation": "110499", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.48506e+06", "standardDeviation": "116994", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "167159", "standardDeviation": "181794", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "49216.2", "standardDeviation": "6682.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60049.8", "standardDeviation": "13684.4", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "140578", "standardDeviation": "14953.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59966.5", "standardDeviation": "12849.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "361738", "standardDeviation": "86328.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "97157.4", "standardDeviation": "58338.1", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "705698", "standardDeviation": "57118.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113072", "standardDeviation": "117479", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50106e+06", "standardDeviation": "126093", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137884", "standardDeviation": "98405", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/field_fvops.png b/221152/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..ac9e4dd Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/221152/neon-cluster-meta-runner-amd/field_relative.png b/221152/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..6de3dd6 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/221152/neon-cluster-meta-runner-amd/field_time.png b/221152/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..8338b98 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/221152/neon-cluster-meta-runner-amd/linear.json b/221152/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..56d7381 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39612.4", "standardDeviation": "4146.34", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "51211.1", "standardDeviation": "8828.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2055.35", "standardDeviation": "3663.03", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "112501", "standardDeviation": "5781.18", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "111361", "standardDeviation": "7159.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2270.51", "standardDeviation": "5355.35", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "225583", "standardDeviation": "15425.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "223200", "standardDeviation": "18010.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2247.24", "standardDeviation": "4339.36", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "451617", "standardDeviation": "33341.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "445665", "standardDeviation": "33331.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3032.16", "standardDeviation": "10540.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "957494", "standardDeviation": "109890", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.00734e+06", "standardDeviation": "119545", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3088.33", "standardDeviation": "10030.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "115881", "standardDeviation": "7106.92", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "113549", "standardDeviation": "7751.73", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2055.19", "standardDeviation": "3405.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "231233", "standardDeviation": "15161.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "226879", "standardDeviation": "17648.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2826.7", "standardDeviation": "8456.45", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "477868", "standardDeviation": "41349.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "456391", "standardDeviation": "42597.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2781.61", "standardDeviation": "7710.16", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "981017", "standardDeviation": "73091.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "931493", "standardDeviation": "86395.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2850.1", "standardDeviation": "8083.94", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.92233e+06", "standardDeviation": "59272.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.0505e+06", "standardDeviation": "88318.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2701.5", "standardDeviation": "7180.02", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/linear_fvops.png b/221152/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..8d787f1 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/221152/neon-cluster-meta-runner-amd/linear_relative.png b/221152/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..ac6fd48 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/221152/neon-cluster-meta-runner-amd/linear_time.png b/221152/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..d8d9ab5 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/221152/neon-cluster-meta-runner-amd/main/divOperator.json b/221152/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..bcd6b53 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "236844", "standardDeviation": "6799.97", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "564197", "standardDeviation": "21593.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "432795", "standardDeviation": "2677.78", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "569573", "standardDeviation": "18799.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "861910", "standardDeviation": "37337.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "657053", "standardDeviation": "20620", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.6981e+06", "standardDeviation": "10674.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "692088", "standardDeviation": "20941.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.63766e+06", "standardDeviation": "26926.6", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "761204", "standardDeviation": "27094.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/main/field.json b/221152/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..0b610ef --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "48365.8", "standardDeviation": "2580.67", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88436", "standardDeviation": "11016.4", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "153935", "standardDeviation": "10430.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "90904.4", "standardDeviation": "8591.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "352776", "standardDeviation": "1202.14", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "148633", "standardDeviation": "21391.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "697707", "standardDeviation": "4473.75", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "138054", "standardDeviation": "12320.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.42716e+06", "standardDeviation": "117764", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161009", "standardDeviation": "21185.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46747.8", "standardDeviation": "2778.32", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "70815.4", "standardDeviation": "14647.9", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "167139", "standardDeviation": "1927.26", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "75121.9", "standardDeviation": "14203.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "352093", "standardDeviation": "3441.21", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "108546", "standardDeviation": "44601.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "696075", "standardDeviation": "3794.18", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "132007", "standardDeviation": "123604", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.47938e+06", "standardDeviation": "127640", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "148628", "standardDeviation": "67563.4", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/main/linear.json b/221152/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..b9a784c --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40296", "standardDeviation": "1684.11", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49960.2", "standardDeviation": "678.223", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1655.75", "standardDeviation": "1036.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "113528", "standardDeviation": "858.533", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "114129", "standardDeviation": "904.853", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1720.93", "standardDeviation": "1419.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "228884", "standardDeviation": "2987.63", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "230900", "standardDeviation": "2943.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1703.19", "standardDeviation": "1288.83", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "487403", "standardDeviation": "27860.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "602237", "standardDeviation": "68792.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2003.33", "standardDeviation": "2555.19", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "904090", "standardDeviation": "6074.37", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "899376", "standardDeviation": "3812.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1957.66", "standardDeviation": "2108.46", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147375", "standardDeviation": "2967", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "116209", "standardDeviation": "1113.71", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1761.81", "standardDeviation": "1493.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "235464", "standardDeviation": "2869.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "340666", "standardDeviation": "22065.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1733.35", "standardDeviation": "1198.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "465346", "standardDeviation": "2388.41", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "454531", "standardDeviation": "2995.06", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1791.76", "standardDeviation": "1943.99", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "927339", "standardDeviation": "1207.24", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "910226", "standardDeviation": "6435", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1727.05", "standardDeviation": "1639.59", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.54104e+06", "standardDeviation": "14197.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.63132e+06", "standardDeviation": "246723", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2061.99", "standardDeviation": "2586.34", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/main/upwind.json b/221152/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..2f8525f --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33352.6", "standardDeviation": "2627.3", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49214.8", "standardDeviation": "1632.71", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1786.68", "standardDeviation": "1359.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "98798.5", "standardDeviation": "1109.52", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "97556.8", "standardDeviation": "1241.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1773.01", "standardDeviation": "875.966", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "200266", "standardDeviation": "1677.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "194076", "standardDeviation": "966.753", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1760.38", "standardDeviation": "1397.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "397150", "standardDeviation": "5067.56", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "437673", "standardDeviation": "26232.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1916.25", "standardDeviation": "2109.37", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "788257", "standardDeviation": "4155.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "790494", "standardDeviation": "8933.89", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1909.22", "standardDeviation": "1965.75", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "118881", "standardDeviation": "1611.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "113045", "standardDeviation": "980.764", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1773.47", "standardDeviation": "1464.68", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "237456", "standardDeviation": "2046.11", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "224431", "standardDeviation": "1471.91", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1814.63", "standardDeviation": "1817.65", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "476965", "standardDeviation": "5166.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "455445", "standardDeviation": "4060.11", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1881.52", "standardDeviation": "1721.62", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "970655", "standardDeviation": "28037.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "966614", "standardDeviation": "57773.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1829.82", "standardDeviation": "1665.28", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.16824e+06", "standardDeviation": "16941", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.11807e+06", "standardDeviation": "29168.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1943.77", "standardDeviation": "2179.26", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/system-info.log b/221152/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..32c2808 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 3 +GPU[0] : GUID: 42924 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/221152/neon-cluster-meta-runner-amd/upwind.json b/221152/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..147a952 --- /dev/null +++ b/221152/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "39768.8", "standardDeviation": "30375.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45755.3", "standardDeviation": "9998.55", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2487.21", "standardDeviation": "4024.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "100800", "standardDeviation": "6467.92", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "98734.3", "standardDeviation": "6576.94", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2923.44", "standardDeviation": "4350.71", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199431", "standardDeviation": "14758.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "197546", "standardDeviation": "18134.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2715.95", "standardDeviation": "5252.08", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "400191", "standardDeviation": "32862.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "398068", "standardDeviation": "34764", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2527.9", "standardDeviation": "8121.36", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "802122", "standardDeviation": "68030.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "796028", "standardDeviation": "73429", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3003.48", "standardDeviation": "7070.62", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121556", "standardDeviation": "7464.45", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "114712", "standardDeviation": "7923.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2657.87", "standardDeviation": "4490.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "237854", "standardDeviation": "24093.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "227918", "standardDeviation": "20879.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2516.76", "standardDeviation": "4834.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "483678", "standardDeviation": "39932.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "456860", "standardDeviation": "39579.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3646.39", "standardDeviation": "9883.07", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "978787", "standardDeviation": "103640", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.03266e+06", "standardDeviation": "83975.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2995.93", "standardDeviation": "6752.48", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.88825e+06", "standardDeviation": "83510.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.96469e+06", "standardDeviation": "77004.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3238.09", "standardDeviation": "7717.42", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221152/neon-cluster-meta-runner-amd/upwind_fvops.png b/221152/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..beebb69 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/221152/neon-cluster-meta-runner-amd/upwind_relative.png b/221152/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..e7235b2 Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/221152/neon-cluster-meta-runner-amd/upwind_time.png b/221152/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..6665b5b Binary files /dev/null and b/221152/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/221165/neon-cluster-meta-runner-amd/divOperator.json b/221165/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..2a759a9 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "283975", "standardDeviation": "10674.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "640415", "standardDeviation": "16703.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "601202", "standardDeviation": "47208.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "754040", "standardDeviation": "21797.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.11072e+06", "standardDeviation": "195161", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "734201", "standardDeviation": "16082.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.00182e+06", "standardDeviation": "116441", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "733008", "standardDeviation": "18794.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.02203e+06", "standardDeviation": "377287", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "793419", "standardDeviation": "20689.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/divOperator_fvops.png b/221165/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..f0e32c7 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/221165/neon-cluster-meta-runner-amd/divOperator_relative.png b/221165/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..a9c2cef Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/221165/neon-cluster-meta-runner-amd/divOperator_time.png b/221165/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..4caa3b8 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/221165/neon-cluster-meta-runner-amd/field.json b/221165/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..63dae48 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "92858.1", "standardDeviation": "2288.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81602.8", "standardDeviation": "2389.76", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "132426", "standardDeviation": "1921.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78283.7", "standardDeviation": "6809.37", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "358748", "standardDeviation": "3397.28", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121180", "standardDeviation": "60547.7", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "710937", "standardDeviation": "5408.53", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139125", "standardDeviation": "138983", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.41068e+06", "standardDeviation": "10743.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160331", "standardDeviation": "139081", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47486", "standardDeviation": "2659.51", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "59053.1", "standardDeviation": "5945.37", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "141587", "standardDeviation": "2491.94", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60023.9", "standardDeviation": "4349.81", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "355694", "standardDeviation": "3015.43", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "101063", "standardDeviation": "89041.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "707160", "standardDeviation": "5482.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117961", "standardDeviation": "143509", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.4078e+06", "standardDeviation": "7386.57", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147190", "standardDeviation": "147413", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/field_fvops.png b/221165/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..97d0665 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/221165/neon-cluster-meta-runner-amd/field_relative.png b/221165/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..38455f0 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/221165/neon-cluster-meta-runner-amd/field_time.png b/221165/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..5fc0d40 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/221165/neon-cluster-meta-runner-amd/linear.json b/221165/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..5733162 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49125.3", "standardDeviation": "3780.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50633.1", "standardDeviation": "683.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1481.16", "standardDeviation": "1288.36", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147799", "standardDeviation": "3005.27", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "139775", "standardDeviation": "1607.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1560.33", "standardDeviation": "1440.96", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "317328", "standardDeviation": "16777.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "318726", "standardDeviation": "17600.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1650.05", "standardDeviation": "2142.44", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "526532", "standardDeviation": "42129.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "529804", "standardDeviation": "44107.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1788.2", "standardDeviation": "2676.22", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "993828", "standardDeviation": "92862.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "971642", "standardDeviation": "93029.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1861.78", "standardDeviation": "2970.49", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "230736", "standardDeviation": "8485.05", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "221584", "standardDeviation": "7133.64", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1750.73", "standardDeviation": "1847.72", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "372665", "standardDeviation": "23262.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "382834", "standardDeviation": "23660.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1700.82", "standardDeviation": "1934.13", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "712797", "standardDeviation": "81981.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "737313", "standardDeviation": "86438.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1957.57", "standardDeviation": "3619.51", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.25599e+06", "standardDeviation": "200450", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.30704e+06", "standardDeviation": "208133", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2001.84", "standardDeviation": "3548.27", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.81983e+06", "standardDeviation": "557983", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.35482e+06", "standardDeviation": "106168", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1772.31", "standardDeviation": "2360.12", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/linear_fvops.png b/221165/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..73e0174 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/221165/neon-cluster-meta-runner-amd/linear_relative.png b/221165/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..614ba38 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/221165/neon-cluster-meta-runner-amd/linear_time.png b/221165/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..749f435 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/221165/neon-cluster-meta-runner-amd/main/divOperator.json b/221165/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..c101b7a --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "410913", "standardDeviation": "11903.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "597291", "standardDeviation": "33750.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "472118", "standardDeviation": "17631.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "538719", "standardDeviation": "46838.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "927998", "standardDeviation": "37616.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "621490", "standardDeviation": "32764.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.90131e+06", "standardDeviation": "75599", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "664140", "standardDeviation": "34875.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.70299e+06", "standardDeviation": "71155.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "711252", "standardDeviation": "37139.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/main/field.json b/221165/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..b5703b5 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "47217.6", "standardDeviation": "6257.72", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "82081.7", "standardDeviation": "11215", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "131701", "standardDeviation": "13536.9", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88040.8", "standardDeviation": "11164.1", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "361698", "standardDeviation": "26917.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "115195", "standardDeviation": "12268.3", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "718473", "standardDeviation": "54485.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127103", "standardDeviation": "10810.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.44624e+06", "standardDeviation": "126212", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150832", "standardDeviation": "11318.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48358.3", "standardDeviation": "6504.7", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "66786", "standardDeviation": "12618.1", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "142539", "standardDeviation": "14252.5", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "69167.7", "standardDeviation": "12336.6", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "619856", "standardDeviation": "25976.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111206", "standardDeviation": "14536.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.2379e+06", "standardDeviation": "40100.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124035", "standardDeviation": "20023.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.63405e+06", "standardDeviation": "133045", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "139818", "standardDeviation": "26635.2", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/main/linear.json b/221165/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..0e030e6 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50711.2", "standardDeviation": "4711.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "54136.1", "standardDeviation": "20814.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2460.23", "standardDeviation": "3267.45", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "131724", "standardDeviation": "20271.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "131289", "standardDeviation": "6555.36", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2603.13", "standardDeviation": "4387.87", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "260424", "standardDeviation": "14724.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "264329", "standardDeviation": "15543.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2658.05", "standardDeviation": "5020.65", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "528442", "standardDeviation": "31758.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "534653", "standardDeviation": "32053.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3700.64", "standardDeviation": "9273.97", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.05009e+06", "standardDeviation": "68371.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05339e+06", "standardDeviation": "74446.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3398.34", "standardDeviation": "9925.63", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "134427", "standardDeviation": "6588.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138448", "standardDeviation": "4651.54", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1730.56", "standardDeviation": "1396.22", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "260911", "standardDeviation": "2235.27", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "260294", "standardDeviation": "2036.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1743.19", "standardDeviation": "1410.52", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "538609", "standardDeviation": "33140", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "550013", "standardDeviation": "37944.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3645.86", "standardDeviation": "9431.46", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07728e+06", "standardDeviation": "73379.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.10804e+06", "standardDeviation": "82256.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3278.29", "standardDeviation": "9089.49", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.66331e+06", "standardDeviation": "102707", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.93021e+06", "standardDeviation": "131497", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3734.18", "standardDeviation": "7617.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/main/upwind.json b/221165/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..a088dc9 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33790", "standardDeviation": "2327.91", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49806.2", "standardDeviation": "1222.83", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2340.21", "standardDeviation": "4113.79", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "102518", "standardDeviation": "1016.47", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "101222", "standardDeviation": "929.279", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2984.08", "standardDeviation": "6320.24", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "304393", "standardDeviation": "15674.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "307118", "standardDeviation": "17917.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2410.81", "standardDeviation": "4971.94", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "399873", "standardDeviation": "2474.25", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "400403", "standardDeviation": "7675.77", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3508.5", "standardDeviation": "11076.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "986064", "standardDeviation": "154692", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "792545", "standardDeviation": "5547.51", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2886.8", "standardDeviation": "12123.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "138081", "standardDeviation": "2946.88", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "162744", "standardDeviation": "5029.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3284.01", "standardDeviation": "7738.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "335622", "standardDeviation": "16417.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "262020", "standardDeviation": "9565.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2638.18", "standardDeviation": "5639.42", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "625689", "standardDeviation": "54665.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "533214", "standardDeviation": "33584.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3447.72", "standardDeviation": "9370.56", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "974037", "standardDeviation": "34648", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.04289e+06", "standardDeviation": "128182", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2924.41", "standardDeviation": "7262.38", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.30006e+06", "standardDeviation": "254921", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.3231e+06", "standardDeviation": "84038.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3110.18", "standardDeviation": "10177.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/system-info.log b/221165/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/221165/neon-cluster-meta-runner-amd/upwind.json b/221165/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..bdbc46a --- /dev/null +++ b/221165/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44464.5", "standardDeviation": "7563.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "48929.8", "standardDeviation": "2340.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1644.34", "standardDeviation": "1486.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155890", "standardDeviation": "5375.75", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "100665", "standardDeviation": "2013.39", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2493.45", "standardDeviation": "6329.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "220183", "standardDeviation": "140307", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "197832", "standardDeviation": "2733.91", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2688.64", "standardDeviation": "6454.02", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "397595", "standardDeviation": "2076.53", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "396778", "standardDeviation": "3841.26", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2715.9", "standardDeviation": "7434.31", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "796404", "standardDeviation": "6630.49", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "801724", "standardDeviation": "29461.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2010.73", "standardDeviation": "5103.95", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "122059", "standardDeviation": "2262.79", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "116216", "standardDeviation": "2157.05", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2682.99", "standardDeviation": "5360.67", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "237989", "standardDeviation": "1778.79", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "232938", "standardDeviation": "9746.49", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2268.93", "standardDeviation": "4626.12", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "485237", "standardDeviation": "11437.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "460500", "standardDeviation": "2687.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3847.35", "standardDeviation": "11505.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "953362", "standardDeviation": "20308.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "913888", "standardDeviation": "22489.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3208.02", "standardDeviation": "7660.41", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.26284e+06", "standardDeviation": "91539.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.68263e+06", "standardDeviation": "15614.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2420.53", "standardDeviation": "7001.51", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/221165/neon-cluster-meta-runner-amd/upwind_fvops.png b/221165/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..ea0f1cb Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/221165/neon-cluster-meta-runner-amd/upwind_relative.png b/221165/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..5924288 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/221165/neon-cluster-meta-runner-amd/upwind_time.png b/221165/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..c741de5 Binary files /dev/null and b/221165/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/225249/neon-cluster-meta-runner-amd/divOperator.json b/225249/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..4503ec2 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "249654", "standardDeviation": "6043.2", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "678197", "standardDeviation": "20169.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540636", "standardDeviation": "39098.9", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "698408", "standardDeviation": "26283.1", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.7827e+06", "standardDeviation": "183724", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "806199", "standardDeviation": "35344.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.97135e+06", "standardDeviation": "162348", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "806589", "standardDeviation": "25212", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.74644e+06", "standardDeviation": "281325", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "858282", "standardDeviation": "28366.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/divOperator_fvops.png b/225249/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..de62d63 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-amd/divOperator_relative.png b/225249/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..91c9d40 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/225249/neon-cluster-meta-runner-amd/divOperator_time.png b/225249/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..23116e4 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/225249/neon-cluster-meta-runner-amd/field.json b/225249/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..a0d1088 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "104115", "standardDeviation": "6584.4", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "98104.5", "standardDeviation": "6275.9", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "199362", "standardDeviation": "6188.05", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "84105.2", "standardDeviation": "3853.42", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540197", "standardDeviation": "49412.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125090", "standardDeviation": "9287.84", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "962238", "standardDeviation": "143289", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133737", "standardDeviation": "12019.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71251e+06", "standardDeviation": "270286", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "162842", "standardDeviation": "8610.45", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "55580.9", "standardDeviation": "3266.25", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62900.5", "standardDeviation": "3414.61", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "208417", "standardDeviation": "6025.72", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "87221.4", "standardDeviation": "10639.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "548179", "standardDeviation": "50219.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104622", "standardDeviation": "11221.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "973374", "standardDeviation": "145269", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117017", "standardDeviation": "14042.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.75503e+06", "standardDeviation": "322551", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142367", "standardDeviation": "13026.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/field_fvops.png b/225249/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..c694521 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-amd/field_relative.png b/225249/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..4d63c80 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/225249/neon-cluster-meta-runner-amd/field_time.png b/225249/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..731e65f Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/225249/neon-cluster-meta-runner-amd/linear.json b/225249/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..1ec9875 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51719.9", "standardDeviation": "4094.77", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50406.3", "standardDeviation": "1135.12", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1980.71", "standardDeviation": "1227.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176972", "standardDeviation": "5574.27", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "178482", "standardDeviation": "6009.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2095.53", "standardDeviation": "1565.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "333130", "standardDeviation": "20787.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "341943", "standardDeviation": "21691.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2061.04", "standardDeviation": "1726.22", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "614490", "standardDeviation": "68176.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "617982", "standardDeviation": "71381.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2268.85", "standardDeviation": "3823.23", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08983e+06", "standardDeviation": "178156", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.09255e+06", "standardDeviation": "185323", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1957.05", "standardDeviation": "1527.98", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177620", "standardDeviation": "5642.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "177935", "standardDeviation": "6611.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2070.5", "standardDeviation": "1451.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "338430", "standardDeviation": "20678.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "343930", "standardDeviation": "22204.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2100.27", "standardDeviation": "2269.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "603278", "standardDeviation": "67903.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "765466", "standardDeviation": "83462.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2690.17", "standardDeviation": "5847.11", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.24539e+06", "standardDeviation": "214805", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.27033e+06", "standardDeviation": "210368", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2347.19", "standardDeviation": "3259.36", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.59531e+06", "standardDeviation": "309281", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.60289e+06", "standardDeviation": "242293", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2423.75", "standardDeviation": "3011.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/linear_fvops.png b/225249/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..66b771e Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-amd/linear_relative.png b/225249/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..675715c Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/225249/neon-cluster-meta-runner-amd/linear_time.png b/225249/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..00bfcca Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/225249/neon-cluster-meta-runner-amd/main/divOperator.json b/225249/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..8979110 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "246261", "standardDeviation": "6288.59", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "761190", "standardDeviation": "61747.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "538646", "standardDeviation": "38615.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "771955", "standardDeviation": "55336", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.80613e+06", "standardDeviation": "254701", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "717558", "standardDeviation": "39078.6", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.96208e+06", "standardDeviation": "149484", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "732368", "standardDeviation": "37309", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.84028e+06", "standardDeviation": "207228", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "788076", "standardDeviation": "34257", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/main/field.json b/225249/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..149f66d --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53421.2", "standardDeviation": "3150.73", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78838.1", "standardDeviation": "8956.8", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "166068", "standardDeviation": "5186.72", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "83668.4", "standardDeviation": "7901.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "470260", "standardDeviation": "38357.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119142", "standardDeviation": "22223.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "814507", "standardDeviation": "86454.1", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140078", "standardDeviation": "72623.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54104e+06", "standardDeviation": "201970", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "165888", "standardDeviation": "88556", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "53733", "standardDeviation": "2241.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63336.2", "standardDeviation": "10712.6", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "174527", "standardDeviation": "5254.82", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "65255.9", "standardDeviation": "9151.12", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "466360", "standardDeviation": "39116.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "110661", "standardDeviation": "55254.5", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "845967", "standardDeviation": "105337", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119575", "standardDeviation": "106468", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55464e+06", "standardDeviation": "208897", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "148661", "standardDeviation": "69127.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/main/linear.json b/225249/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..5f92bf7 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53454", "standardDeviation": "3450.25", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "55228.7", "standardDeviation": "2008.42", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2266.88", "standardDeviation": "1385.87", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "208487", "standardDeviation": "6786.25", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "213786", "standardDeviation": "7263.94", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2200.12", "standardDeviation": "1753.64", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "388766", "standardDeviation": "26726.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "397564", "standardDeviation": "27036", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2050.03", "standardDeviation": "3091.52", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "710711", "standardDeviation": "84332.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "719039", "standardDeviation": "85403.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2532.17", "standardDeviation": "3663.87", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24625e+06", "standardDeviation": "211147", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.24022e+06", "standardDeviation": "218639", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2483.38", "standardDeviation": "3741.27", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "207674", "standardDeviation": "6772.1", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "209345", "standardDeviation": "6728.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2128.96", "standardDeviation": "2307.75", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "394690", "standardDeviation": "26274.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "395817", "standardDeviation": "26971", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2175.94", "standardDeviation": "2789.25", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "720961", "standardDeviation": "82812.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "602015", "standardDeviation": "69575.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2413.46", "standardDeviation": "2966.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09312e+06", "standardDeviation": "170170", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08908e+06", "standardDeviation": "179891", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3361.79", "standardDeviation": "5273.14", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.37544e+06", "standardDeviation": "257840", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.01707e+06", "standardDeviation": "260812", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3480.35", "standardDeviation": "5838.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/main/upwind.json b/225249/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..676a133 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "33356.6", "standardDeviation": "3328", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45694.2", "standardDeviation": "2269.98", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2090.84", "standardDeviation": "1837.75", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182110", "standardDeviation": "5564.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "184565", "standardDeviation": "5613.95", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2069.12", "standardDeviation": "1243.63", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "412850", "standardDeviation": "32378.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "305098", "standardDeviation": "17592.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2890.99", "standardDeviation": "1757.97", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "557636", "standardDeviation": "53050.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "551544", "standardDeviation": "60785.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3196.4", "standardDeviation": "3182.28", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "995015", "standardDeviation": "153207", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "982375", "standardDeviation": "160745", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2807.97", "standardDeviation": "3431.81", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172096", "standardDeviation": "4388.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "173471", "standardDeviation": "5968.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2615.87", "standardDeviation": "1737.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "300973", "standardDeviation": "12324.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "325554", "standardDeviation": "20366.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2693.21", "standardDeviation": "1989.21", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "613594", "standardDeviation": "54679.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "614843", "standardDeviation": "62279.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2881.83", "standardDeviation": "2693.18", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12048e+06", "standardDeviation": "142130", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09871e+06", "standardDeviation": "154549", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2926.55", "standardDeviation": "2432.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.72539e+06", "standardDeviation": "240307", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.8332e+06", "standardDeviation": "287570", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2887.95", "standardDeviation": "3513.91", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/system-info.log b/225249/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/225249/neon-cluster-meta-runner-amd/upwind.json b/225249/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..a06d2e6 --- /dev/null +++ b/225249/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49838.5", "standardDeviation": "3232.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49057.4", "standardDeviation": "1832.93", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1985.47", "standardDeviation": "1688.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "181370", "standardDeviation": "5434.96", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "184121", "standardDeviation": "5478.78", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2282.11", "standardDeviation": "1366.82", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "410724", "standardDeviation": "79116.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "329083", "standardDeviation": "17257.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1995.1", "standardDeviation": "1636.52", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "643172", "standardDeviation": "67111.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "646111", "standardDeviation": "68378.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2276", "standardDeviation": "4412.36", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.15165e+06", "standardDeviation": "173176", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "861253", "standardDeviation": "89380.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2261.26", "standardDeviation": "2761.81", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172667", "standardDeviation": "4968.39", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "171459", "standardDeviation": "5801.91", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2211.72", "standardDeviation": "1716.49", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "331144", "standardDeviation": "16834.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "308107", "standardDeviation": "15902", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2250.41", "standardDeviation": "1918.09", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "618219", "standardDeviation": "54875.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "599479", "standardDeviation": "62788.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2922.79", "standardDeviation": "5196.92", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10606e+06", "standardDeviation": "143816", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0746e+06", "standardDeviation": "160827", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2454.95", "standardDeviation": "2695.74", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.25363e+06", "standardDeviation": "255622", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.23971e+06", "standardDeviation": "254329", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2732.49", "standardDeviation": "2878.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-amd/upwind_fvops.png b/225249/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..7071c89 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-amd/upwind_relative.png b/225249/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..d287fd2 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/225249/neon-cluster-meta-runner-amd/upwind_time.png b/225249/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..f8b1120 Binary files /dev/null and b/225249/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/divOperator.json b/225249/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..e7d5c04 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "512483", "standardDeviation": "7522.83", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "253787", "standardDeviation": "7166.05", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "511761", "standardDeviation": "16553.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "320130", "standardDeviation": "8116.63", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "995977", "standardDeviation": "16889.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "435515", "standardDeviation": "5503.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98301e+06", "standardDeviation": "69105.1", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "513784", "standardDeviation": "5109.89", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.39285e+06", "standardDeviation": "61961.5", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "676294", "standardDeviation": "7421", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/225249/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..c840178 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/225249/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..7db4072 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/divOperator_time.png b/225249/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..ba33a05 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/field.json b/225249/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..eb884f2 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "431049", "standardDeviation": "18876.2", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41208.8", "standardDeviation": "1466.01", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "444887", "standardDeviation": "6490.84", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104286", "standardDeviation": "4168.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "909439", "standardDeviation": "5669.45", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150739", "standardDeviation": "1958.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83972e+06", "standardDeviation": "253217", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "191183", "standardDeviation": "5579.36", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.65787e+06", "standardDeviation": "25165.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "271397", "standardDeviation": "15094.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "286653", "standardDeviation": "38318.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23897.9", "standardDeviation": "756.651", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "565459", "standardDeviation": "2455.38", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "98611.3", "standardDeviation": "4524.4", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.12726e+06", "standardDeviation": "4275.82", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144217", "standardDeviation": "2991.92", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.27959e+06", "standardDeviation": "241992", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "183565", "standardDeviation": "6150.52", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.63644e+06", "standardDeviation": "56374.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "270609", "standardDeviation": "12358.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/field_fvops.png b/225249/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..83a6839 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/field_relative.png b/225249/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..6b710c5 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/field_time.png b/225249/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..ea4ba62 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/linear.json b/225249/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..75ea882 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "85252.4", "standardDeviation": "2264", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117151", "standardDeviation": "1451.09", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2421.77", "standardDeviation": "156.566", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171246", "standardDeviation": "5810.55", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "234260", "standardDeviation": "3542.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2407.53", "standardDeviation": "225.293", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "453454", "standardDeviation": "176668", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "549945", "standardDeviation": "6238.73", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2424.44", "standardDeviation": "251.227", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "684285", "standardDeviation": "27012.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "934671", "standardDeviation": "12544.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2434.04", "standardDeviation": "197.989", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.37851e+06", "standardDeviation": "61746.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.8713e+06", "standardDeviation": "23213.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2384.27", "standardDeviation": "170.68", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "128009", "standardDeviation": "7374.01", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138676", "standardDeviation": "5630.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2434.12", "standardDeviation": "165.696", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "258067", "standardDeviation": "12471.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "279438", "standardDeviation": "11733.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2457.5", "standardDeviation": "324.623", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "514923", "standardDeviation": "28158.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "579396", "standardDeviation": "24327.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2453.7", "standardDeviation": "312.529", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.05393e+06", "standardDeviation": "54036.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.16404e+06", "standardDeviation": "56923.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2406.45", "standardDeviation": "302.466", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.122e+06", "standardDeviation": "35934.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.48284e+06", "standardDeviation": "114260", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2442.07", "standardDeviation": "579.163", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/linear_fvops.png b/225249/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..d55ea78 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/linear_relative.png b/225249/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..87e7b34 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/linear_time.png b/225249/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..838f021 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/main/divOperator.json b/225249/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..28042c1 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "261759", "standardDeviation": "4965.08", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "265363", "standardDeviation": "5429.91", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "517506", "standardDeviation": "17514.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "265882", "standardDeviation": "3973.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.0057e+06", "standardDeviation": "32790.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "271058", "standardDeviation": "7008.87", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.99499e+06", "standardDeviation": "72324.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "283587", "standardDeviation": "4374.07", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.52678e+06", "standardDeviation": "64602.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "306792", "standardDeviation": "4444.71", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/main/field.json b/225249/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..f132e5d --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "214497", "standardDeviation": "2210.54", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31066.4", "standardDeviation": "820.901", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445089", "standardDeviation": "7151.51", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31071.9", "standardDeviation": "1510.88", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "926225", "standardDeviation": "171972", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39839.2", "standardDeviation": "1606.89", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.84473e+06", "standardDeviation": "177793", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40960.2", "standardDeviation": "879.038", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.79889e+06", "standardDeviation": "57956.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700878", "standardDeviation": "57072.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "283091", "standardDeviation": "2118.29", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25918.8", "standardDeviation": "877.981", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "564480", "standardDeviation": "2273.86", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30384.6", "standardDeviation": "4041.52", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.12668e+06", "standardDeviation": "3792.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34195.9", "standardDeviation": "1014.44", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.25749e+06", "standardDeviation": "25659", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34084.5", "standardDeviation": "1000.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.62046e+06", "standardDeviation": "46390.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699705", "standardDeviation": "55416.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/main/linear.json b/225249/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..86298a4 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "101028", "standardDeviation": "3007.51", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149587", "standardDeviation": "1145.86", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2533.9", "standardDeviation": "160.967", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171914", "standardDeviation": "5271.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "298811", "standardDeviation": "1889.98", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2545.57", "standardDeviation": "94.218", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "343526", "standardDeviation": "12839.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597389", "standardDeviation": "2764.99", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2480.07", "standardDeviation": "110.723", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "688720", "standardDeviation": "28723", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19319e+06", "standardDeviation": "2825.19", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2539.58", "standardDeviation": "270.885", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.37723e+06", "standardDeviation": "21851.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38826e+06", "standardDeviation": "3087.25", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2495.66", "standardDeviation": "188.965", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "128389", "standardDeviation": "6275.93", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139089", "standardDeviation": "4775.77", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2492.95", "standardDeviation": "70.6842", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "254690", "standardDeviation": "12444.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "282658", "standardDeviation": "11176.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2494.96", "standardDeviation": "252.967", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "569272", "standardDeviation": "49188.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "578719", "standardDeviation": "48296", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2531.04", "standardDeviation": "134.773", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09203e+06", "standardDeviation": "98722.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.26853e+06", "standardDeviation": "107301", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2539.28", "standardDeviation": "229.805", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.32768e+06", "standardDeviation": "105340", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.36452e+06", "standardDeviation": "225625", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2608.77", "standardDeviation": "827.192", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/main/upwind.json b/225249/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..eea65dc --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83406.6", "standardDeviation": "1991.57", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117130", "standardDeviation": "1712.55", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2706.5", "standardDeviation": "152.235", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167135", "standardDeviation": "3819.87", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233647", "standardDeviation": "2430.57", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2669.82", "standardDeviation": "141.337", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "335668", "standardDeviation": "10337.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "467382", "standardDeviation": "4939.54", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2719", "standardDeviation": "259.48", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "669900", "standardDeviation": "24183", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "933402", "standardDeviation": "11591.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2660.61", "standardDeviation": "319.47", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.34431e+06", "standardDeviation": "50313.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86596e+06", "standardDeviation": "22726.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2597.3", "standardDeviation": "141.359", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "120237", "standardDeviation": "8486.52", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "137326", "standardDeviation": "8868.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2783.17", "standardDeviation": "177.211", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "242376", "standardDeviation": "15907.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "517306", "standardDeviation": "26080.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2644.23", "standardDeviation": "248.844", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "488861", "standardDeviation": "45403.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "544511", "standardDeviation": "39461.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2694.74", "standardDeviation": "383.526", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "975693", "standardDeviation": "101041", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11344e+06", "standardDeviation": "99070", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2649.72", "standardDeviation": "106.956", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.03598e+06", "standardDeviation": "55121.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.01173e+06", "standardDeviation": "160622", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2610.63", "standardDeviation": "432.035", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/system-info.log b/225249/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..eeac169 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Feb 18 14:17:00 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA L40S On | 00000000:61:00.0 Off | 0 | +| N/A 27C P8 33W / 350W | 0MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/225249/neon-cluster-meta-runner-nvidia/upwind.json b/225249/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..2953d69 --- /dev/null +++ b/225249/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99491.9", "standardDeviation": "1692.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117076", "standardDeviation": "1016.35", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2597.74", "standardDeviation": "435.189", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "198996", "standardDeviation": "1200.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "238486", "standardDeviation": "49069.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2567.18", "standardDeviation": "176.596", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "398059", "standardDeviation": "7258.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "466576", "standardDeviation": "4861.86", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2528.65", "standardDeviation": "174.491", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "795998", "standardDeviation": "16692.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "930064", "standardDeviation": "1629.62", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2607.49", "standardDeviation": "758.458", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.56058e+06", "standardDeviation": "72196.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86303e+06", "standardDeviation": "19889.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2503.94", "standardDeviation": "135.834", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "117934", "standardDeviation": "8360.18", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136182", "standardDeviation": "6915.75", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2529.34", "standardDeviation": "459.395", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "240169", "standardDeviation": "21968.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272892", "standardDeviation": "17654.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2528.32", "standardDeviation": "220.008", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "475451", "standardDeviation": "49192.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "545561", "standardDeviation": "41378.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2474.2", "standardDeviation": "250.077", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "982639", "standardDeviation": "101401", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09434e+06", "standardDeviation": "85553.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2470.45", "standardDeviation": "171.531", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "4.78498e+06", "standardDeviation": "642604", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.12566e+06", "standardDeviation": "55049.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2487.84", "standardDeviation": "259.829", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225249/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/225249/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..4f6e9cb Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/upwind_relative.png b/225249/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..570f20a Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/225249/neon-cluster-meta-runner-nvidia/upwind_time.png b/225249/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..6b6e1a8 Binary files /dev/null and b/225249/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/225267/neon-cluster-meta-runner-amd/divOperator.json b/225267/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..266f0a5 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "280423", "standardDeviation": "10825.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "685756", "standardDeviation": "33882.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "606909", "standardDeviation": "47519.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "687265", "standardDeviation": "34061.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.04338e+06", "standardDeviation": "91924.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "783128", "standardDeviation": "23713.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.81847e+06", "standardDeviation": "176874", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "833947", "standardDeviation": "133969", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.82595e+06", "standardDeviation": "263522", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "864483", "standardDeviation": "30257.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/divOperator_fvops.png b/225267/neon-cluster-meta-runner-amd/divOperator_fvops.png new file mode 100644 index 0000000..7a53e2c Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/divOperator_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-amd/divOperator_relative.png b/225267/neon-cluster-meta-runner-amd/divOperator_relative.png new file mode 100644 index 0000000..e26dc7f Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/divOperator_relative.png differ diff --git a/225267/neon-cluster-meta-runner-amd/divOperator_time.png b/225267/neon-cluster-meta-runner-amd/divOperator_time.png new file mode 100644 index 0000000..132c1cc Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/divOperator_time.png differ diff --git a/225267/neon-cluster-meta-runner-amd/field.json b/225267/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..9820167 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "94755.8", "standardDeviation": "8002.82", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "90200.8", "standardDeviation": "3275.26", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "294963", "standardDeviation": "22785.8", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "100537", "standardDeviation": "8868.51", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "448502", "standardDeviation": "31915.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140083", "standardDeviation": "27248.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "847004", "standardDeviation": "103548", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "163844", "standardDeviation": "68085.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54982e+06", "standardDeviation": "198436", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "187893", "standardDeviation": "76417.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "48766.2", "standardDeviation": "2425.79", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78600.9", "standardDeviation": "10296.1", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "189574", "standardDeviation": "5407.28", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "86949.6", "standardDeviation": "11341.3", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "479415", "standardDeviation": "38483.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143070", "standardDeviation": "32784.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "860595", "standardDeviation": "108430", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "164184", "standardDeviation": "221003", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.56291e+06", "standardDeviation": "207469", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "181691", "standardDeviation": "115651", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/field_fvops.png b/225267/neon-cluster-meta-runner-amd/field_fvops.png new file mode 100644 index 0000000..8714a89 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/field_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-amd/field_relative.png b/225267/neon-cluster-meta-runner-amd/field_relative.png new file mode 100644 index 0000000..6e7a8b6 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/field_relative.png differ diff --git a/225267/neon-cluster-meta-runner-amd/field_time.png b/225267/neon-cluster-meta-runner-amd/field_time.png new file mode 100644 index 0000000..00fa49e Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/field_time.png differ diff --git a/225267/neon-cluster-meta-runner-amd/linear.json b/225267/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..c3694d8 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43811.9", "standardDeviation": "4814.94", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52672.2", "standardDeviation": "1461.57", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2015.44", "standardDeviation": "1502.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206618", "standardDeviation": "7959.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "208810", "standardDeviation": "7079.06", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1963.95", "standardDeviation": "2020.66", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "388123", "standardDeviation": "26995.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "396004", "standardDeviation": "26836.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2173.61", "standardDeviation": "2534.12", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "709850", "standardDeviation": "82757.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "715977", "standardDeviation": "86484.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2471.64", "standardDeviation": "3535.96", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24427e+06", "standardDeviation": "213200", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.23644e+06", "standardDeviation": "218989", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1989.11", "standardDeviation": "1540.95", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "209362", "standardDeviation": "6891.77", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "214302", "standardDeviation": "7027.33", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2020.84", "standardDeviation": "1436.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "395523", "standardDeviation": "27471.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "403043", "standardDeviation": "27560.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2026.33", "standardDeviation": "1920.78", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "863043", "standardDeviation": "37411.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "711883", "standardDeviation": "83895.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2213.57", "standardDeviation": "3269.74", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.30821e+06", "standardDeviation": "205542", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.35887e+06", "standardDeviation": "186014", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2752.75", "standardDeviation": "5732.07", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.55921e+06", "standardDeviation": "318045", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.80096e+06", "standardDeviation": "280340", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2164.79", "standardDeviation": "2897.94", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/linear_fvops.png b/225267/neon-cluster-meta-runner-amd/linear_fvops.png new file mode 100644 index 0000000..eb93150 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/linear_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-amd/linear_relative.png b/225267/neon-cluster-meta-runner-amd/linear_relative.png new file mode 100644 index 0000000..4e3ca4e Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/linear_relative.png differ diff --git a/225267/neon-cluster-meta-runner-amd/linear_time.png b/225267/neon-cluster-meta-runner-amd/linear_time.png new file mode 100644 index 0000000..8c46313 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/linear_time.png differ diff --git a/225267/neon-cluster-meta-runner-amd/main/divOperator.json b/225267/neon-cluster-meta-runner-amd/main/divOperator.json new file mode 100644 index 0000000..ea1b41a --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "272457", "standardDeviation": "9237.19", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "834971", "standardDeviation": "63454", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "605109", "standardDeviation": "49353.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "606850", "standardDeviation": "36248.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.08065e+06", "standardDeviation": "133627", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "712109", "standardDeviation": "40845", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.00224e+06", "standardDeviation": "247895", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "731819", "standardDeviation": "36197.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.01784e+06", "standardDeviation": "191783", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "782934", "standardDeviation": "39210.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/main/field.json b/225267/neon-cluster-meta-runner-amd/main/field.json new file mode 100644 index 0000000..c985f39 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53073.5", "standardDeviation": "3388.92", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "96149.4", "standardDeviation": "11189.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "175570", "standardDeviation": "4277.81", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "100643", "standardDeviation": "10643.3", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "475848", "standardDeviation": "37723.6", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "118124", "standardDeviation": "5519.47", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "848053", "standardDeviation": "104084", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143134", "standardDeviation": "46982.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55609e+06", "standardDeviation": "206324", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "166429", "standardDeviation": "62548.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "53590.4", "standardDeviation": "1914.52", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61486.7", "standardDeviation": "10159.8", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "176587", "standardDeviation": "4360.23", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "65348.3", "standardDeviation": "9702.03", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "476342", "standardDeviation": "38241.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104842", "standardDeviation": "10331", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "850023", "standardDeviation": "104774", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "114475", "standardDeviation": "24998.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.56914e+06", "standardDeviation": "211756", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145325", "standardDeviation": "40614.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/main/linear.json b/225267/neon-cluster-meta-runner-amd/main/linear.json new file mode 100644 index 0000000..7b34182 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "49595.6", "standardDeviation": "3441.09", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "53937.3", "standardDeviation": "1152.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1885.81", "standardDeviation": "1281.92", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206426", "standardDeviation": "6816.35", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "209030", "standardDeviation": "6840.04", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2789", "standardDeviation": "2096.28", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "337354", "standardDeviation": "20158.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "342714", "standardDeviation": "20414.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2106.86", "standardDeviation": "2263.72", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "617354", "standardDeviation": "68429.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "623568", "standardDeviation": "72603.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3047.27", "standardDeviation": "3203.72", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08436e+06", "standardDeviation": "175074", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.24608e+06", "standardDeviation": "215440", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2112.19", "standardDeviation": "2521.63", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "205543", "standardDeviation": "6990.53", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "208574", "standardDeviation": "6824.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1952.26", "standardDeviation": "1372.22", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "388576", "standardDeviation": "26724.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "394288", "standardDeviation": "26789.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1983.21", "standardDeviation": "1674.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "707719", "standardDeviation": "82853.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "711306", "standardDeviation": "83035.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2457.64", "standardDeviation": "3044.39", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.24006e+06", "standardDeviation": "210719", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.25107e+06", "standardDeviation": "207686", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2140.72", "standardDeviation": "2532.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.75486e+06", "standardDeviation": "281001", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.41188e+06", "standardDeviation": "258017", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2737.9", "standardDeviation": "2787.48", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/main/upwind.json b/225267/neon-cluster-meta-runner-amd/main/upwind.json new file mode 100644 index 0000000..cb8643a --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "43620.1", "standardDeviation": "8926.28", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49407.5", "standardDeviation": "2715.85", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2538.82", "standardDeviation": "1921.31", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "182060", "standardDeviation": "5958.02", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "184708", "standardDeviation": "5801.13", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2527.14", "standardDeviation": "2151.44", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "347771", "standardDeviation": "19881.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "353155", "standardDeviation": "21100.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2331.22", "standardDeviation": "2315.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "639609", "standardDeviation": "66521.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "649513", "standardDeviation": "69275.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2559.9", "standardDeviation": "4765.07", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.12554e+06", "standardDeviation": "179151", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.1481e+06", "standardDeviation": "179001", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3019.89", "standardDeviation": "3626.27", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "192956", "standardDeviation": "6266.42", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "201978", "standardDeviation": "6503.36", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2847.26", "standardDeviation": "1786.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "368760", "standardDeviation": "24137.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "370037", "standardDeviation": "24647.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2364.18", "standardDeviation": "3134.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "682925", "standardDeviation": "71559.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "682615", "standardDeviation": "76417.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2309.83", "standardDeviation": "3214.83", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.2263e+06", "standardDeviation": "187666", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.21231e+06", "standardDeviation": "200534", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2340", "standardDeviation": "3077.99", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.4597e+06", "standardDeviation": "294078", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.51021e+06", "standardDeviation": "287847", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2485.42", "standardDeviation": "3287.42", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/system-info.log b/225267/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/225267/neon-cluster-meta-runner-amd/upwind.json b/225267/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..a24516b --- /dev/null +++ b/225267/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50373.2", "standardDeviation": "2154.11", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "48035.1", "standardDeviation": "2724.03", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2146.53", "standardDeviation": "1301.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "156198", "standardDeviation": "4002.99", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "156481", "standardDeviation": "4574.16", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2174.48", "standardDeviation": "1664.95", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "298023", "standardDeviation": "17887.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299008", "standardDeviation": "18272.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2271.66", "standardDeviation": "1957.26", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "557975", "standardDeviation": "55730.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "556972", "standardDeviation": "59119.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2385.03", "standardDeviation": "3219.42", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "863858", "standardDeviation": "88374.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "959220", "standardDeviation": "157566", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2042.78", "standardDeviation": "1971.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "175805", "standardDeviation": "4989.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "172022", "standardDeviation": "5252.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2191.93", "standardDeviation": "1923.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "330596", "standardDeviation": "16350.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "328062", "standardDeviation": "18539.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2080.16", "standardDeviation": "1379.66", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "611695", "standardDeviation": "54877", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "600022", "standardDeviation": "62109.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2606.39", "standardDeviation": "4262.41", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10857e+06", "standardDeviation": "143657", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07222e+06", "standardDeviation": "159296", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2362.65", "standardDeviation": "2843.07", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.56215e+06", "standardDeviation": "251770", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.6638e+06", "standardDeviation": "211055", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2719.88", "standardDeviation": "3011.64", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-amd/upwind_fvops.png b/225267/neon-cluster-meta-runner-amd/upwind_fvops.png new file mode 100644 index 0000000..2b93ec4 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/upwind_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-amd/upwind_relative.png b/225267/neon-cluster-meta-runner-amd/upwind_relative.png new file mode 100644 index 0000000..539d718 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/upwind_relative.png differ diff --git a/225267/neon-cluster-meta-runner-amd/upwind_time.png b/225267/neon-cluster-meta-runner-amd/upwind_time.png new file mode 100644 index 0000000..bee7025 Binary files /dev/null and b/225267/neon-cluster-meta-runner-amd/upwind_time.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/divOperator.json b/225267/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..95aa92a --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "512560", "standardDeviation": "9580.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "237201", "standardDeviation": "4041.4", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "509206", "standardDeviation": "6077.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "309789", "standardDeviation": "5049.71", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "996182", "standardDeviation": "9571.83", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "433764", "standardDeviation": "4962.59", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.98907e+06", "standardDeviation": "19627.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "511568", "standardDeviation": "8113.69", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.06826e+06", "standardDeviation": "27287.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "676391", "standardDeviation": "17151", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/divOperator_fvops.png b/225267/neon-cluster-meta-runner-nvidia/divOperator_fvops.png new file mode 100644 index 0000000..44f8355 Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/divOperator_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/divOperator_relative.png b/225267/neon-cluster-meta-runner-nvidia/divOperator_relative.png new file mode 100644 index 0000000..65e40ba Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/divOperator_relative.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/divOperator_time.png b/225267/neon-cluster-meta-runner-nvidia/divOperator_time.png new file mode 100644 index 0000000..58e903c Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/divOperator_time.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/field.json b/225267/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..5068205 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "426963", "standardDeviation": "1661.33", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27216.5", "standardDeviation": "701.948", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445289", "standardDeviation": "3411.04", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "107073", "standardDeviation": "2029.52", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "927050", "standardDeviation": "152429", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "154991", "standardDeviation": "4763.12", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.83869e+06", "standardDeviation": "188460", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "195105", "standardDeviation": "8097.94", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.62795e+06", "standardDeviation": "3212.09", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "274669", "standardDeviation": "15819.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "282809", "standardDeviation": "1217.39", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "22114.7", "standardDeviation": "606.656", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "564030", "standardDeviation": "1550.22", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "100474", "standardDeviation": "1488.69", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.12559e+06", "standardDeviation": "866.79", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147987", "standardDeviation": "4188.68", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.24728e+06", "standardDeviation": "1166.31", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "187439", "standardDeviation": "7771.22", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.52778e+06", "standardDeviation": "4709.94", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "274142", "standardDeviation": "15807.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/field_fvops.png b/225267/neon-cluster-meta-runner-nvidia/field_fvops.png new file mode 100644 index 0000000..9c150cc Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/field_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/field_relative.png b/225267/neon-cluster-meta-runner-nvidia/field_relative.png new file mode 100644 index 0000000..1ee71fd Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/field_relative.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/field_time.png b/225267/neon-cluster-meta-runner-nvidia/field_time.png new file mode 100644 index 0000000..5d1922c Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/field_time.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/linear.json b/225267/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..f0e4cf9 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "85423.7", "standardDeviation": "2144", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117071", "standardDeviation": "675.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2203.69", "standardDeviation": "95.8077", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171114", "standardDeviation": "3851.24", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233321", "standardDeviation": "1234.34", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2254.9", "standardDeviation": "181.175", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "343855", "standardDeviation": "3033.79", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "466320", "standardDeviation": "1398.45", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2286.24", "standardDeviation": "153.168", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "681971", "standardDeviation": "3100.66", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "933389", "standardDeviation": "8321.79", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2256.98", "standardDeviation": "71.1137", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.37249e+06", "standardDeviation": "8218.76", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86226e+06", "standardDeviation": "3274.25", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2287.97", "standardDeviation": "502.24", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "146150", "standardDeviation": "1293.76", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156610", "standardDeviation": "1702.68", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2245.82", "standardDeviation": "57.0736", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "294693", "standardDeviation": "8127.98", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "312026", "standardDeviation": "4271.95", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2266.2", "standardDeviation": "91.1501", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "590755", "standardDeviation": "8746.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "618735", "standardDeviation": "6070.85", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2307.22", "standardDeviation": "83.4654", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.16605e+06", "standardDeviation": "12580.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.24474e+06", "standardDeviation": "11491.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2350.07", "standardDeviation": "435.592", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.74839e+06", "standardDeviation": "18749", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.00692e+06", "standardDeviation": "26757.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2309.17", "standardDeviation": "169.189", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/linear_fvops.png b/225267/neon-cluster-meta-runner-nvidia/linear_fvops.png new file mode 100644 index 0000000..d90289b Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/linear_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/linear_relative.png b/225267/neon-cluster-meta-runner-nvidia/linear_relative.png new file mode 100644 index 0000000..9fffd1b Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/linear_relative.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/linear_time.png b/225267/neon-cluster-meta-runner-nvidia/linear_time.png new file mode 100644 index 0000000..7d37fb8 Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/linear_time.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/main/divOperator.json b/225267/neon-cluster-meta-runner-nvidia/main/divOperator.json new file mode 100644 index 0000000..8153a36 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/main/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "262890", "standardDeviation": "8581.25", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "261289", "standardDeviation": "6884.53", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "517003", "standardDeviation": "14982.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262535", "standardDeviation": "4183.94", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "998874", "standardDeviation": "31056.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "269234", "standardDeviation": "6324.98", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.97464e+06", "standardDeviation": "32914.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280208", "standardDeviation": "4091.91", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.28445e+06", "standardDeviation": "33412.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "303855", "standardDeviation": "4091.72", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/main/field.json b/225267/neon-cluster-meta-runner-nvidia/main/field.json new file mode 100644 index 0000000..9111233 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/main/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "429085", "standardDeviation": "2966.85", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31427", "standardDeviation": "689.985", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "445676", "standardDeviation": "10181.4", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31100.6", "standardDeviation": "765.718", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "934066", "standardDeviation": "195008", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40004.1", "standardDeviation": "1385.82", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.87051e+06", "standardDeviation": "294421", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41157.8", "standardDeviation": "911.195", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.71558e+06", "standardDeviation": "50883.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700861", "standardDeviation": "54872.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "288918", "standardDeviation": "50337.5", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26044.6", "standardDeviation": "743.675", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "564473", "standardDeviation": "4652.18", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28055.2", "standardDeviation": "2956.31", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.1279e+06", "standardDeviation": "10340.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34533.6", "standardDeviation": "1033.53", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.28258e+06", "standardDeviation": "238286", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34644", "standardDeviation": "1159.66", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.5686e+06", "standardDeviation": "47607", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "699878", "standardDeviation": "56610.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/main/linear.json b/225267/neon-cluster-meta-runner-nvidia/main/linear.json new file mode 100644 index 0000000..e1060a7 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/main/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "85208.4", "standardDeviation": "2369.6", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149385", "standardDeviation": "1110.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2545.43", "standardDeviation": "76.6713", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "171296", "standardDeviation": "3015.92", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "298823", "standardDeviation": "1516.93", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2534.04", "standardDeviation": "220.948", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "341467", "standardDeviation": "4321.03", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "597434", "standardDeviation": "5102.38", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2504.38", "standardDeviation": "209.796", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "683646", "standardDeviation": "10507.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19263e+06", "standardDeviation": "2758.19", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2585.02", "standardDeviation": "369.964", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.36546e+06", "standardDeviation": "16152.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38787e+06", "standardDeviation": "2897.76", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2526.55", "standardDeviation": "187.365", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "129152", "standardDeviation": "5636.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139041", "standardDeviation": "5788.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2512.14", "standardDeviation": "188.956", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "257468", "standardDeviation": "14117.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "283412", "standardDeviation": "11210.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2492.32", "standardDeviation": "103.563", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "517557", "standardDeviation": "28809.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "555318", "standardDeviation": "24959.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2513.21", "standardDeviation": "129.195", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.04935e+06", "standardDeviation": "50717", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.12004e+06", "standardDeviation": "55086.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2452.16", "standardDeviation": "197.56", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.26155e+06", "standardDeviation": "77784.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.25852e+06", "standardDeviation": "96863.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2515.67", "standardDeviation": "395.948", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/main/upwind.json b/225267/neon-cluster-meta-runner-nvidia/main/upwind.json new file mode 100644 index 0000000..35c7c1e --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/main/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83432.8", "standardDeviation": "1605.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116909", "standardDeviation": "1088.43", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2759.03", "standardDeviation": "173.035", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166665", "standardDeviation": "1880.51", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233887", "standardDeviation": "1591.22", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2760.7", "standardDeviation": "176.844", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "333580", "standardDeviation": "3321.33", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "466028", "standardDeviation": "1817.87", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2694.04", "standardDeviation": "242.216", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "667922", "standardDeviation": "7462.04", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "931698", "standardDeviation": "2112.49", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2706.94", "standardDeviation": "283.495", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33563e+06", "standardDeviation": "15639.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86407e+06", "standardDeviation": "4038.54", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2652.28", "standardDeviation": "143.531", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121847", "standardDeviation": "5848.04", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "136504", "standardDeviation": "5449.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2673.03", "standardDeviation": "183.638", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "252861", "standardDeviation": "11697.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "272516", "standardDeviation": "11672.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2681.77", "standardDeviation": "135.076", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "503626", "standardDeviation": "25169.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "553853", "standardDeviation": "47410.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2627.86", "standardDeviation": "169.664", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01086e+06", "standardDeviation": "106599", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.11099e+06", "standardDeviation": "87755.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2702.38", "standardDeviation": "392.686", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.10041e+06", "standardDeviation": "117536", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.20989e+06", "standardDeviation": "99171.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2637.41", "standardDeviation": "197.957", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/system-info.log b/225267/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..4ce7dc4 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Feb 18 16:10:01 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA L40S On | 00000000:61:00.0 Off | 0 | +| N/A 27C P8 33W / 350W | 0MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/225267/neon-cluster-meta-runner-nvidia/upwind.json b/225267/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..294b6e7 --- /dev/null +++ b/225267/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99205.9", "standardDeviation": "2244.46", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116481", "standardDeviation": "770.348", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2507.01", "standardDeviation": "1530.43", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "210616", "standardDeviation": "51111.6", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233316", "standardDeviation": "1189.42", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2317.35", "standardDeviation": "46.1938", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "397033", "standardDeviation": "1680.68", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "474983", "standardDeviation": "89128.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2332.75", "standardDeviation": "65.5209", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "789859", "standardDeviation": "30576.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "930714", "standardDeviation": "4377.97", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2279.62", "standardDeviation": "47.2186", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.57339e+06", "standardDeviation": "60399.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.8615e+06", "standardDeviation": "4581.43", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2338.75", "standardDeviation": "378.208", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "135240", "standardDeviation": "1323.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "134918", "standardDeviation": "851.584", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2261.46", "standardDeviation": "55.3493", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "232761", "standardDeviation": "2636.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "268925", "standardDeviation": "1330.65", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2346.52", "standardDeviation": "77.2048", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "462521", "standardDeviation": "3945.18", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "539689", "standardDeviation": "1839.78", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2332.49", "standardDeviation": "93.592", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "934326", "standardDeviation": "8617.87", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07547e+06", "standardDeviation": "2783.02", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2306.05", "standardDeviation": "149.705", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.23239e+06", "standardDeviation": "25787.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.52524e+06", "standardDeviation": "14890.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2307.64", "standardDeviation": "109.842", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/225267/neon-cluster-meta-runner-nvidia/upwind_fvops.png b/225267/neon-cluster-meta-runner-nvidia/upwind_fvops.png new file mode 100644 index 0000000..0ce7c6f Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/upwind_fvops.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/upwind_relative.png b/225267/neon-cluster-meta-runner-nvidia/upwind_relative.png new file mode 100644 index 0000000..47aa115 Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/upwind_relative.png differ diff --git a/225267/neon-cluster-meta-runner-nvidia/upwind_time.png b/225267/neon-cluster-meta-runner-nvidia/upwind_time.png new file mode 100644 index 0000000..cc3570e Binary files /dev/null and b/225267/neon-cluster-meta-runner-nvidia/upwind_time.png differ diff --git a/226/gdnxlarge/divOperator_fvops.png b/226/gdnxlarge/divOperator_fvops.png index fa5b079..08968f1 100644 Binary files a/226/gdnxlarge/divOperator_fvops.png and b/226/gdnxlarge/divOperator_fvops.png differ diff --git a/226/gdnxlarge/divOperator_relative.png b/226/gdnxlarge/divOperator_relative.png index ebb28d4..4a39d62 100644 Binary files a/226/gdnxlarge/divOperator_relative.png and b/226/gdnxlarge/divOperator_relative.png differ diff --git a/226/gdnxlarge/divOperator_time.png b/226/gdnxlarge/divOperator_time.png index de035ee..ade48d3 100644 Binary files a/226/gdnxlarge/divOperator_time.png and b/226/gdnxlarge/divOperator_time.png differ diff --git a/226/gdnxlarge/field_fvops.png b/226/gdnxlarge/field_fvops.png index 502a4a8..9f602ac 100644 Binary files a/226/gdnxlarge/field_fvops.png and b/226/gdnxlarge/field_fvops.png differ diff --git a/226/gdnxlarge/field_relative.png b/226/gdnxlarge/field_relative.png index 2cd2adc..ce2c42f 100644 Binary files a/226/gdnxlarge/field_relative.png and b/226/gdnxlarge/field_relative.png differ diff --git a/226/gdnxlarge/field_time.png b/226/gdnxlarge/field_time.png index f030647..ddb8b0c 100644 Binary files a/226/gdnxlarge/field_time.png and b/226/gdnxlarge/field_time.png differ diff --git a/229907/neon-cluster-meta-runner-amd/allocator.json b/229907/neon-cluster-meta-runner-amd/allocator.json new file mode 100644 index 0000000..0bbe7ba --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "201912", "standardDeviation": "10176", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "200965", "standardDeviation": "10654.4", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "205788", "standardDeviation": "28760.8", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "243371", "standardDeviation": "9860.36", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278033", "standardDeviation": "49374.4", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160567", "standardDeviation": "7202.95", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161230", "standardDeviation": "5888.76", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "169003", "standardDeviation": "6733.96", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "206005", "standardDeviation": "6114.23", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "271218", "standardDeviation": "101535", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31707.5", "standardDeviation": "12891.9", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32099", "standardDeviation": "13427.8", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31975.5", "standardDeviation": "12519.5", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32360.1", "standardDeviation": "13072.8", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123639", "standardDeviation": "196594", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/develop/allocator.json b/229907/neon-cluster-meta-runner-amd/develop/allocator.json new file mode 100644 index 0000000..cf7cab8 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "142012", "standardDeviation": "9759.56", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143374", "standardDeviation": "10485.3", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142352", "standardDeviation": "9615.96", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "174692", "standardDeviation": "7425.73", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "223997", "standardDeviation": "30811.2", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143414", "standardDeviation": "8139.38", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144952", "standardDeviation": "6794.21", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145258", "standardDeviation": "5560.73", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "175219", "standardDeviation": "14291.6", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "220841", "standardDeviation": "24862.1", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28586.9", "standardDeviation": "12196.3", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29053.4", "standardDeviation": "13370.4", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29117.4", "standardDeviation": "12385.5", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28059.1", "standardDeviation": "12431.7", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85404.2", "standardDeviation": "31970.1", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/develop/divOperator.json b/229907/neon-cluster-meta-runner-amd/develop/divOperator.json new file mode 100644 index 0000000..123a6d2 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "227393", "standardDeviation": "5784.66", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "607815", "standardDeviation": "15171.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "469645", "standardDeviation": "18471", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "616628", "standardDeviation": "13980", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "924614", "standardDeviation": "66159.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "700195", "standardDeviation": "16963.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.75613e+06", "standardDeviation": "80148.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "726150", "standardDeviation": "18953.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.71531e+06", "standardDeviation": "93493.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "784327", "standardDeviation": "16048.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/develop/field.json b/229907/neon-cluster-meta-runner-amd/develop/field.json new file mode 100644 index 0000000..a3cd16a --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "46095.9", "standardDeviation": "1646.14", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "73447", "standardDeviation": "3395.5", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "164790", "standardDeviation": "2300.51", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77626.4", "standardDeviation": "4349.95", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "429738", "standardDeviation": "27849.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109573", "standardDeviation": "13579.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "746367", "standardDeviation": "41430.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119948", "standardDeviation": "14052.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.46984e+06", "standardDeviation": "105938", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145062", "standardDeviation": "10068.5", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46282.1", "standardDeviation": "2229.99", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60167.3", "standardDeviation": "4401.42", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "179454", "standardDeviation": "4674.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "61126.1", "standardDeviation": "4266.9", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "431664", "standardDeviation": "29833.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93542.8", "standardDeviation": "21427.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "763885", "standardDeviation": "61770.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "102584", "standardDeviation": "18661.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.52949e+06", "standardDeviation": "185808", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "134818", "standardDeviation": "62296.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/develop/linear.json b/229907/neon-cluster-meta-runner-amd/develop/linear.json new file mode 100644 index 0000000..8f1610e --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50433", "standardDeviation": "1523.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50821", "standardDeviation": "695.063", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1465.93", "standardDeviation": "1201.48", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176985", "standardDeviation": "6197.03", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "156516", "standardDeviation": "5033.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1547.79", "standardDeviation": "1625.46", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "281559", "standardDeviation": "13416.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "279230", "standardDeviation": "14596.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1588.67", "standardDeviation": "1719.73", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "496645", "standardDeviation": "34131", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531803", "standardDeviation": "45865.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1754.42", "standardDeviation": "3114.01", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "961834", "standardDeviation": "73712.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "901726", "standardDeviation": "20053.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1543.42", "standardDeviation": "2703.96", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "131508", "standardDeviation": "1429.82", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "157951", "standardDeviation": "6093.34", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2556.47", "standardDeviation": "1998.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "264026", "standardDeviation": "7387.74", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "234042", "standardDeviation": "5720.41", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1519.12", "standardDeviation": "1317.21", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "540225", "standardDeviation": "51027.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "492573", "standardDeviation": "26475.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2600.92", "standardDeviation": "2862.97", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.05176e+06", "standardDeviation": "98733.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "922069", "standardDeviation": "35076.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1608.34", "standardDeviation": "2180.26", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.57334e+06", "standardDeviation": "114101", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.83553e+06", "standardDeviation": "144300", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1632.96", "standardDeviation": "2178.71", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/develop/upwind.json b/229907/neon-cluster-meta-runner-amd/develop/upwind.json new file mode 100644 index 0000000..bebb8ca --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "36562.8", "standardDeviation": "2353.86", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "49843.3", "standardDeviation": "606.509", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1567.42", "standardDeviation": "1303.08", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "135970", "standardDeviation": "4106.95", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "134725", "standardDeviation": "4157.98", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1527.98", "standardDeviation": "1248.84", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "250266", "standardDeviation": "11363.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "281827", "standardDeviation": "14486.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1568.35", "standardDeviation": "1484.52", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "447538", "standardDeviation": "36630.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "488813", "standardDeviation": "44721.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1896.31", "standardDeviation": "3775.67", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "841964", "standardDeviation": "62781.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "968823", "standardDeviation": "19116.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1686.48", "standardDeviation": "2118.44", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "140671", "standardDeviation": "3105.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "139342", "standardDeviation": "2331.92", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1540.22", "standardDeviation": "1344.84", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "286573", "standardDeviation": "10294.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "257869", "standardDeviation": "7668.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1532.81", "standardDeviation": "1423.72", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "555016", "standardDeviation": "31323.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "477108", "standardDeviation": "17332.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1751.52", "standardDeviation": "2488.66", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "985079", "standardDeviation": "66793.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "913063", "standardDeviation": "36537.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1740", "standardDeviation": "2088.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.32196e+06", "standardDeviation": "64507.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.38297e+06", "standardDeviation": "83785", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1797.96", "standardDeviation": "2364.41", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/divOperator.json b/229907/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..b460fc8 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "240225", "standardDeviation": "5144.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "622567", "standardDeviation": "12193.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "471776", "standardDeviation": "17649.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "611478", "standardDeviation": "10227", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "911781", "standardDeviation": "64093.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "707350", "standardDeviation": "17456.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.76755e+06", "standardDeviation": "122763", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "746612", "standardDeviation": "19080.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.84511e+06", "standardDeviation": "145722", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "810937", "standardDeviation": "39218.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/field.json b/229907/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..0b9a177 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "93647.7", "standardDeviation": "3886.17", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "91892.7", "standardDeviation": "5199.22", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "163949", "standardDeviation": "5249.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77252.7", "standardDeviation": "5666.16", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "407476", "standardDeviation": "23436.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111522", "standardDeviation": "15561", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "819952", "standardDeviation": "91260.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "122475", "standardDeviation": "14281.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.48695e+06", "standardDeviation": "131544", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149883", "standardDeviation": "24923.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46961.2", "standardDeviation": "1904.07", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "60484.4", "standardDeviation": "4422.33", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "142624", "standardDeviation": "2259.86", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58233.2", "standardDeviation": "6997.69", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "407504", "standardDeviation": "24866.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89898.1", "standardDeviation": "15991.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "796760", "standardDeviation": "80723.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99376.8", "standardDeviation": "15232.8", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50327e+06", "standardDeviation": "151447", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127623", "standardDeviation": "14627.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/linear.json b/229907/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..a106848 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50303", "standardDeviation": "715.449", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "50307", "standardDeviation": "662.033", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1405.09", "standardDeviation": "988.178", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "133328", "standardDeviation": "1935.02", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "127296", "standardDeviation": "1010.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1537.24", "standardDeviation": "1813.87", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "250133", "standardDeviation": "5952.53", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "249655", "standardDeviation": "6523.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1453.88", "standardDeviation": "1301.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "495115", "standardDeviation": "28085.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "494413", "standardDeviation": "29107.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1727.44", "standardDeviation": "2516.95", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "928039", "standardDeviation": "42082.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "923107", "standardDeviation": "51389.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1543.04", "standardDeviation": "1513.23", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147898", "standardDeviation": "4320.13", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "133931", "standardDeviation": "1894.98", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1445.33", "standardDeviation": "1092.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "256644", "standardDeviation": "6950.42", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "242899", "standardDeviation": "6708.03", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1534.72", "standardDeviation": "1379.44", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "498823", "standardDeviation": "18742.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "498448", "standardDeviation": "28667.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1751.03", "standardDeviation": "2732.51", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00411e+06", "standardDeviation": "90013", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "960494", "standardDeviation": "72344.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1720.1", "standardDeviation": "2636.63", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.28286e+06", "standardDeviation": "117339", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.39482e+06", "standardDeviation": "83104.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1733.27", "standardDeviation": "2632.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-amd/system-info.log b/229907/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/229907/neon-cluster-meta-runner-amd/upwind.json b/229907/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..adcbd89 --- /dev/null +++ b/229907/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34066.6", "standardDeviation": "2088.73", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45379", "standardDeviation": "395.48", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1526.84", "standardDeviation": "1140.14", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "124368", "standardDeviation": "1914.12", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116692", "standardDeviation": "1042.87", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1465.45", "standardDeviation": "1007.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "223136", "standardDeviation": "5174.57", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "239258", "standardDeviation": "9914.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1596.4", "standardDeviation": "1572.82", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "464926", "standardDeviation": "50271.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "438159", "standardDeviation": "29396.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1714.48", "standardDeviation": "2210.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "820453", "standardDeviation": "39947.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "807056", "standardDeviation": "35807.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1849.53", "standardDeviation": "3413.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "141967", "standardDeviation": "1818.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "138378", "standardDeviation": "3929.19", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1529.92", "standardDeviation": "1352.63", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "258943", "standardDeviation": "5995.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "265041", "standardDeviation": "11574.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1473.11", "standardDeviation": "1333.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "563332", "standardDeviation": "13529.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "549765", "standardDeviation": "45449.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1865.22", "standardDeviation": "2760.22", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.01879e+06", "standardDeviation": "125969", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "990987", "standardDeviation": "104459", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1759.01", "standardDeviation": "1886.61", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.26913e+06", "standardDeviation": "139470", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.19831e+06", "standardDeviation": "119856", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1866.11", "standardDeviation": "2314.78", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/allocator.json b/229907/neon-cluster-meta-runner-intel/allocator.json new file mode 100644 index 0000000..5217539 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "38340.2", "standardDeviation": "8697.54", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38538.3", "standardDeviation": "9301.93", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42588.5", "standardDeviation": "54184.6", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40747", "standardDeviation": "7451.01", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41260.9", "standardDeviation": "8237.54", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42822.7", "standardDeviation": "49001.2", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38584.6", "standardDeviation": "7863.11", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38836.2", "standardDeviation": "9201.66", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40909.8", "standardDeviation": "6954.05", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41136.9", "standardDeviation": "6739.09", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13733.9", "standardDeviation": "8224.38", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14047.1", "standardDeviation": "4993.95", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13392", "standardDeviation": "1286.55", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "15450.5", "standardDeviation": "12538.3", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "12734.8", "standardDeviation": "4333.64", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/develop/allocator.json b/229907/neon-cluster-meta-runner-intel/develop/allocator.json new file mode 100644 index 0000000..464b01d --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "39604.7", "standardDeviation": "17174.1", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38599", "standardDeviation": "7195.35", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42323.2", "standardDeviation": "41810.3", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39443.2", "standardDeviation": "10245.3", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41276.5", "standardDeviation": "7585.9", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42964.7", "standardDeviation": "49690.3", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38857.9", "standardDeviation": "6575.93", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38912.4", "standardDeviation": "7841.24", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39233.4", "standardDeviation": "7364.2", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40284.1", "standardDeviation": "7255.4", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14294.1", "standardDeviation": "8360.04", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13233.1", "standardDeviation": "4521.23", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13429.6", "standardDeviation": "716.033", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13581.4", "standardDeviation": "4435.76", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13325.7", "standardDeviation": "4373.97", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/develop/divOperator.json b/229907/neon-cluster-meta-runner-intel/develop/divOperator.json new file mode 100644 index 0000000..3a537bf --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "214866", "standardDeviation": "22310.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149520", "standardDeviation": "9967.16", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "469892", "standardDeviation": "29288.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "154994", "standardDeviation": "10273.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "940024", "standardDeviation": "119445", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160449", "standardDeviation": "11616.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.61863e+06", "standardDeviation": "159110", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "244063", "standardDeviation": "10529.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.03492e+06", "standardDeviation": "176637", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277300", "standardDeviation": "8873.26", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/develop/field.json b/229907/neon-cluster-meta-runner-intel/develop/field.json new file mode 100644 index 0000000..398b1c3 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "48176.2", "standardDeviation": "43421.5", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26640.5", "standardDeviation": "8490.73", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "163157", "standardDeviation": "4596.96", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33402.4", "standardDeviation": "49955.1", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "494377", "standardDeviation": "208936", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31066.3", "standardDeviation": "9042.28", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "846712", "standardDeviation": "284935", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "71733.3", "standardDeviation": "5960.7", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.7203e+06", "standardDeviation": "256016", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "84472.8", "standardDeviation": "7583.05", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "47292.6", "standardDeviation": "1031.25", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "20953.8", "standardDeviation": "6934.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "152653", "standardDeviation": "3167.13", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23443.8", "standardDeviation": "9259.95", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "435631", "standardDeviation": "22480.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30543.2", "standardDeviation": "51584.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "748084", "standardDeviation": "12727.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "67601.6", "standardDeviation": "6331.86", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.54816e+06", "standardDeviation": "111410", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "80007.4", "standardDeviation": "6199.84", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/develop/linear.json b/229907/neon-cluster-meta-runner-intel/develop/linear.json new file mode 100644 index 0000000..3eb372e --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "42807.9", "standardDeviation": "15296.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "59276.2", "standardDeviation": "1147.11", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3837.09", "standardDeviation": "5124.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "185334", "standardDeviation": "5360.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "169548", "standardDeviation": "6864.43", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3936.43", "standardDeviation": "6771.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "319092", "standardDeviation": "13885", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "326551", "standardDeviation": "14784.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3968.1", "standardDeviation": "6872.22", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "577581", "standardDeviation": "39215.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "492544", "standardDeviation": "16536.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10922.5", "standardDeviation": "74084.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.03842e+06", "standardDeviation": "87440.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.10268e+06", "standardDeviation": "134728", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "21078.4", "standardDeviation": "115930", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "151746", "standardDeviation": "2668.1", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "156419", "standardDeviation": "4052.99", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4316.15", "standardDeviation": "8317.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "347923", "standardDeviation": "12831.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "324353", "standardDeviation": "13414.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "13176.7", "standardDeviation": "96344.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "562052", "standardDeviation": "10875.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "581547", "standardDeviation": "39904.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "20191.1", "standardDeviation": "163201", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.15945e+06", "standardDeviation": "95564.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.03212e+06", "standardDeviation": "65430.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "29514.8", "standardDeviation": "207205", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.27705e+06", "standardDeviation": "174165", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.14211e+06", "standardDeviation": "271418", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "14821.8", "standardDeviation": "65123.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/develop/upwind.json b/229907/neon-cluster-meta-runner-intel/develop/upwind.json new file mode 100644 index 0000000..5af7118 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "42242.8", "standardDeviation": "13124.6", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "58498.7", "standardDeviation": "961.208", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3523.55", "standardDeviation": "2209.71", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137206", "standardDeviation": "1949.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "145049", "standardDeviation": "3774.64", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3919.33", "standardDeviation": "6616.56", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "267145", "standardDeviation": "9880.85", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "232373", "standardDeviation": "2598.87", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3947.18", "standardDeviation": "7462.99", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "507674", "standardDeviation": "32180.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "512488", "standardDeviation": "31253.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10353.8", "standardDeviation": "70732", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "904357", "standardDeviation": "67083.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.00148e+06", "standardDeviation": "83309.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "28050.5", "standardDeviation": "188490", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "154690", "standardDeviation": "6008.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "181995", "standardDeviation": "36634.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4017.03", "standardDeviation": "7292.89", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "313158", "standardDeviation": "8435.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "312552", "standardDeviation": "11697", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "12001.4", "standardDeviation": "82946.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "664733", "standardDeviation": "51204.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "592152", "standardDeviation": "37439", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "18206.7", "standardDeviation": "145088", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.08001e+06", "standardDeviation": "85711.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09244e+06", "standardDeviation": "107389", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "34059.6", "standardDeviation": "257851", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.27709e+06", "standardDeviation": "304447", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.03258e+06", "standardDeviation": "91900.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "17224.4", "standardDeviation": "88912.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/divOperator.json b/229907/neon-cluster-meta-runner-intel/divOperator.json new file mode 100644 index 0000000..80f93f7 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "219248", "standardDeviation": "23390.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140877", "standardDeviation": "10749.7", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "464630", "standardDeviation": "19721.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "151995", "standardDeviation": "10923.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "868378", "standardDeviation": "61142.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "155687", "standardDeviation": "11761.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55458e+06", "standardDeviation": "63509.8", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "239607", "standardDeviation": "9912.63", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.02464e+06", "standardDeviation": "179247", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278540", "standardDeviation": "13302.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/field.json b/229907/neon-cluster-meta-runner-intel/field.json new file mode 100644 index 0000000..a2c8311 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50896", "standardDeviation": "45518", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27088.2", "standardDeviation": "10104.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "148903", "standardDeviation": "1622.29", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33772.6", "standardDeviation": "50961.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "394527", "standardDeviation": "182477", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31641.4", "standardDeviation": "9819.78", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "869623", "standardDeviation": "278023", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "73621.5", "standardDeviation": "8029.2", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.60491e+06", "standardDeviation": "150419", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "84572.2", "standardDeviation": "6952.15", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "44715.6", "standardDeviation": "1364.22", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24330.6", "standardDeviation": "44279.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "159389", "standardDeviation": "1873.03", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23577.2", "standardDeviation": "6963.02", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "510823", "standardDeviation": "30662.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26374.1", "standardDeviation": "6896.82", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "916780", "standardDeviation": "81121.1", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "69347.6", "standardDeviation": "12919.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.61619e+06", "standardDeviation": "338589", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "90240.9", "standardDeviation": "7486.98", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/linear.json b/229907/neon-cluster-meta-runner-intel/linear.json new file mode 100644 index 0000000..25a6308 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44709.9", "standardDeviation": "16209.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "61237.2", "standardDeviation": "1257.19", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3665.97", "standardDeviation": "2344.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "143131", "standardDeviation": "2116.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "178141", "standardDeviation": "5372.78", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4013.26", "standardDeviation": "6973.94", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "308959", "standardDeviation": "37523.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "307886", "standardDeviation": "12866.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4049.58", "standardDeviation": "6927.73", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "623891", "standardDeviation": "54889.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "563235", "standardDeviation": "39900", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10747.5", "standardDeviation": "72859", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.12928e+06", "standardDeviation": "147615", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.17969e+06", "standardDeviation": "181456", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "21123.5", "standardDeviation": "120971", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "203398", "standardDeviation": "5898.86", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "176567", "standardDeviation": "4703.05", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4217.14", "standardDeviation": "7212.83", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "349156", "standardDeviation": "13666.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "286973", "standardDeviation": "8765.89", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "18630.6", "standardDeviation": "146490", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "631477", "standardDeviation": "37915.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "562763", "standardDeviation": "34232.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "27579.7", "standardDeviation": "235835", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.18766e+06", "standardDeviation": "118568", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07909e+06", "standardDeviation": "104443", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "42617.7", "standardDeviation": "338807", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.21184e+06", "standardDeviation": "98332", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.10716e+06", "standardDeviation": "253969", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "16374.7", "standardDeviation": "86652.2", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-intel/system-info.log b/229907/neon-cluster-meta-runner-intel/system-info.log new file mode 100644 index 0000000..3f898ec --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/system-info.log @@ -0,0 +1,66 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 52 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 224 +On-line CPU(s) list: 0-223 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Platinum 8480+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 56 +Socket(s): 2 +Stepping: 8 +CPU(s) scaling MHz: 26% +CPU max MHz: 3800.0000 +CPU min MHz: 800.0000 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 5.3 MiB (112 instances) +L1i cache: 3.5 MiB (112 instances) +L2 cache: 224 MiB (112 instances) +L3 cache: 210 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0-55,112-167 +NUMA node1 CPU(s): 56-111,168-223 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +[level_zero:gpu][level_zero:0] Intel(R) oneAPI Unified Runtime over Level-Zero, Intel(R) Data Center GPU Max 1100 12.60.7 [1.6.33578+15] + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +Intel(R) oneAPI DPC++/C++ Compiler 2025.3.0 (2025.3.0.20251010) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/intel/oneapi/compiler/2025.3/bin/compiler +Configuration file: /opt/intel/oneapi/compiler/2025.3/bin/compiler/../icpx.cfg diff --git a/229907/neon-cluster-meta-runner-intel/upwind.json b/229907/neon-cluster-meta-runner-intel/upwind.json new file mode 100644 index 0000000..0bec828 --- /dev/null +++ b/229907/neon-cluster-meta-runner-intel/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "37914.6", "standardDeviation": "1706.33", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "69594.4", "standardDeviation": "570.331", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3480.2", "standardDeviation": "2223.75", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "137959", "standardDeviation": "2255.87", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "154629", "standardDeviation": "13831", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3550.74", "standardDeviation": "3028.42", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "296960", "standardDeviation": "13319.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "283833", "standardDeviation": "6371", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3953.6", "standardDeviation": "6284.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "552685", "standardDeviation": "44901.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "554658", "standardDeviation": "1893.95", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10653.9", "standardDeviation": "74790.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "928433", "standardDeviation": "81735.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.10827e+06", "standardDeviation": "1970.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "19961.5", "standardDeviation": "113627", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "176219", "standardDeviation": "4368.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159649", "standardDeviation": "3452.89", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4073.61", "standardDeviation": "7573.45", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "335582", "standardDeviation": "11177.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "370855", "standardDeviation": "21480.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "14357.3", "standardDeviation": "106660", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "708963", "standardDeviation": "71916.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "506814", "standardDeviation": "22594.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "27509.6", "standardDeviation": "236447", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10927e+06", "standardDeviation": "83976.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.04679e+06", "standardDeviation": "79163.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "50453.7", "standardDeviation": "419605", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.21397e+06", "standardDeviation": "111263", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.28334e+06", "standardDeviation": "373116", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "15137.2", "standardDeviation": "68455", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/allocator.json b/229907/neon-cluster-meta-runner-nvidia/allocator.json new file mode 100644 index 0000000..a6e5048 --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "56176.4", "standardDeviation": "1616.95", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124135", "standardDeviation": "1774.45", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125906", "standardDeviation": "4978.63", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "304932", "standardDeviation": "3054.76", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "446440", "standardDeviation": "11179.6", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "57777.4", "standardDeviation": "1738.28", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127364", "standardDeviation": "3092.16", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119962", "standardDeviation": "2521.42", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "309558", "standardDeviation": "3835.82", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "432563", "standardDeviation": "3106.62", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "18824", "standardDeviation": "962.783", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "84293.7", "standardDeviation": "1773.64", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "91651", "standardDeviation": "1377.86", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "190782", "standardDeviation": "2017.43", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281414", "standardDeviation": "2728.3", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/develop/allocator.json b/229907/neon-cluster-meta-runner-nvidia/develop/allocator.json new file mode 100644 index 0000000..8b064eb --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "58671.9", "standardDeviation": "1106.53", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127844", "standardDeviation": "2303.09", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130196", "standardDeviation": "6078.69", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "302467", "standardDeviation": "4117.92", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "445937", "standardDeviation": "11820.9", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "58118.4", "standardDeviation": "1159.91", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "125137", "standardDeviation": "1811.81", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127662", "standardDeviation": "2328.7", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "309605", "standardDeviation": "3044.95", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "446726", "standardDeviation": "4067.31", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "20049.2", "standardDeviation": "1195.79", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "85105.7", "standardDeviation": "2181.47", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92448.1", "standardDeviation": "1280.29", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "188943", "standardDeviation": "1775.36", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "286100", "standardDeviation": "3157.58", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/develop/divOperator.json b/229907/neon-cluster-meta-runner-nvidia/develop/divOperator.json new file mode 100644 index 0000000..5aae1bc --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "308176", "standardDeviation": "5364.01", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "331632", "standardDeviation": "6695.57", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "594062", "standardDeviation": "15858.3", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "323218", "standardDeviation": "7805.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.14923e+06", "standardDeviation": "39769.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "459799", "standardDeviation": "7806.78", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.24088e+06", "standardDeviation": "65832.6", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "526661", "standardDeviation": "6210.27", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.394e+06", "standardDeviation": "22367", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "715168", "standardDeviation": "17663.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/develop/field.json b/229907/neon-cluster-meta-runner-nvidia/develop/field.json new file mode 100644 index 0000000..e06b40c --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "216328", "standardDeviation": "1594.27", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31741.7", "standardDeviation": "954.611", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "454208", "standardDeviation": "5524.03", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "112076", "standardDeviation": "1056.63", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "947824", "standardDeviation": "169709", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152955", "standardDeviation": "5678.74", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.85875e+06", "standardDeviation": "183142", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "201222", "standardDeviation": "7294.45", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66148e+06", "standardDeviation": "38675.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "280607", "standardDeviation": "15790.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "301355", "standardDeviation": "1335.56", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25947.6", "standardDeviation": "1148.29", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "599104", "standardDeviation": "1693.84", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "99392.2", "standardDeviation": "1195.22", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.19346e+06", "standardDeviation": "1899.51", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "146669", "standardDeviation": "5921.32", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.39824e+06", "standardDeviation": "172198", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "193038", "standardDeviation": "8229.19", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.75219e+06", "standardDeviation": "2410.46", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "282999", "standardDeviation": "16245.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/develop/linear.json b/229907/neon-cluster-meta-runner-nvidia/develop/linear.json new file mode 100644 index 0000000..80d20a3 --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "116330", "standardDeviation": "854.854", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133545", "standardDeviation": "981.368", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2728.91", "standardDeviation": "314.201", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "232617", "standardDeviation": "1252.07", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "273236", "standardDeviation": "68785", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2635.03", "standardDeviation": "147.888", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "464403", "standardDeviation": "8290.81", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "531120", "standardDeviation": "1420.79", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2794.1", "standardDeviation": "218.668", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "927118", "standardDeviation": "9487.41", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04962e+06", "standardDeviation": "29732.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2598.78", "standardDeviation": "62.8089", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.82889e+06", "standardDeviation": "65029.1", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.11457e+06", "standardDeviation": "26193.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2579.3", "standardDeviation": "120.102", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "162173", "standardDeviation": "3475.63", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "166816", "standardDeviation": "2768.73", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2796.81", "standardDeviation": "211.765", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "329943", "standardDeviation": "16019.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "312669", "standardDeviation": "13472.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2669.71", "standardDeviation": "73.8949", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "551350", "standardDeviation": "31231.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "603026", "standardDeviation": "46308.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2545.74", "standardDeviation": "115.078", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11758e+06", "standardDeviation": "71867.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18656e+06", "standardDeviation": "29987.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2566.98", "standardDeviation": "194.388", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.73207e+06", "standardDeviation": "83954.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.79492e+06", "standardDeviation": "122884", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2579.43", "standardDeviation": "292.232", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/develop/upwind.json b/229907/neon-cluster-meta-runner-nvidia/develop/upwind.json new file mode 100644 index 0000000..397b53d --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83561.4", "standardDeviation": "1246.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149575", "standardDeviation": "736.224", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2806", "standardDeviation": "47.76", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167266", "standardDeviation": "1113.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299090", "standardDeviation": "1372.44", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2854.74", "standardDeviation": "55.8579", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "335109", "standardDeviation": "1893.38", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596435", "standardDeviation": "1451.18", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2822.18", "standardDeviation": "176.632", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "671282", "standardDeviation": "3237.03", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19161e+06", "standardDeviation": "3197.39", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2695.79", "standardDeviation": "73.4733", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33851e+06", "standardDeviation": "5381.05", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.3807e+06", "standardDeviation": "1255.07", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2719.85", "standardDeviation": "124.198", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147219", "standardDeviation": "5119.77", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "154782", "standardDeviation": "1545", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2752.05", "standardDeviation": "131.638", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "280572", "standardDeviation": "8895.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "310531", "standardDeviation": "5616.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2721.88", "standardDeviation": "56.0113", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "535947", "standardDeviation": "24447.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "620700", "standardDeviation": "15611.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2731.94", "standardDeviation": "244.484", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "971392", "standardDeviation": "13465.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.2227e+06", "standardDeviation": "28899.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2771.15", "standardDeviation": "186.186", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.97103e+06", "standardDeviation": "136596", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.79949e+06", "standardDeviation": "55559.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2688.41", "standardDeviation": "156.271", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/divOperator.json b/229907/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..fe862e9 --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "268372", "standardDeviation": "21585.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "325852", "standardDeviation": "6827.82", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "532263", "standardDeviation": "12828.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "334254", "standardDeviation": "6642.43", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.02046e+06", "standardDeviation": "26715.8", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "451848", "standardDeviation": "7127.79", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.02226e+06", "standardDeviation": "79723.2", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "523091", "standardDeviation": "7010.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.1037e+06", "standardDeviation": "73142.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "698803", "standardDeviation": "14961.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/field.json b/229907/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..679d0c5 --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "184902", "standardDeviation": "2317.55", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31913.4", "standardDeviation": "1117.05", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "388184", "standardDeviation": "3492.45", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "114151", "standardDeviation": "16408.9", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "799874", "standardDeviation": "11550", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "153520", "standardDeviation": "4217.14", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.58532e+06", "standardDeviation": "26164.4", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "197738", "standardDeviation": "7510.38", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.14767e+06", "standardDeviation": "41647.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "283526", "standardDeviation": "15185", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "253380", "standardDeviation": "1225.81", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27184.9", "standardDeviation": "647.904", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "550541", "standardDeviation": "4426.66", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "103422", "standardDeviation": "1270.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.10382e+06", "standardDeviation": "11009.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "148109", "standardDeviation": "5481.52", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.00905e+06", "standardDeviation": "143548", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "197452", "standardDeviation": "7215.63", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.97219e+06", "standardDeviation": "6260.21", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "281927", "standardDeviation": "16687.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/linear.json b/229907/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..acecf9c --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "84891.3", "standardDeviation": "1474.77", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117445", "standardDeviation": "739.229", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2620.61", "standardDeviation": "297.095", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "172937", "standardDeviation": "2190.51", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233191", "standardDeviation": "1179.73", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2569.76", "standardDeviation": "53.688", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "341337", "standardDeviation": "3351.29", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "466364", "standardDeviation": "1592.59", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2726.01", "standardDeviation": "85.5382", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "679415", "standardDeviation": "3238.09", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "939024", "standardDeviation": "1826.56", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2642.26", "standardDeviation": "100.529", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.3656e+06", "standardDeviation": "9510.25", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86163e+06", "standardDeviation": "1980.63", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2618.1", "standardDeviation": "257.198", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "144576", "standardDeviation": "1976.39", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "158595", "standardDeviation": "4363.89", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2609.51", "standardDeviation": "157.162", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "274032", "standardDeviation": "5670.19", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "290577", "standardDeviation": "6158.17", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2485.76", "standardDeviation": "60.2829", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "582207", "standardDeviation": "39276.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "581180", "standardDeviation": "5192.14", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2483.19", "standardDeviation": "101.969", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.08139e+06", "standardDeviation": "36771.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18007e+06", "standardDeviation": "21637.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2620.36", "standardDeviation": "422.467", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.8309e+06", "standardDeviation": "97285.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.51258e+06", "standardDeviation": "124196", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2513.82", "standardDeviation": "235.323", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/229907/neon-cluster-meta-runner-nvidia/system-info.log b/229907/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..128f9bb --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Wed Mar 18 11:56:40 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 590.48.01 Driver Version: 590.48.01 CUDA Version: 13.1 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA L40S On | 00000000:E1:00.0 Off | 0 | +| N/A 26C P8 31W / 350W | 0MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/229907/neon-cluster-meta-runner-nvidia/upwind.json b/229907/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..4f2d20b --- /dev/null +++ b/229907/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83127.3", "standardDeviation": "808.345", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116749", "standardDeviation": "1047.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2745.03", "standardDeviation": "53.2684", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "168538", "standardDeviation": "1350.38", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233888", "standardDeviation": "1242.78", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2713.31", "standardDeviation": "51.5279", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332001", "standardDeviation": "1260.04", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "466098", "standardDeviation": "1845.86", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2754.95", "standardDeviation": "157.389", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "664532", "standardDeviation": "1657.53", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "930136", "standardDeviation": "1457.73", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2701.47", "standardDeviation": "71.2716", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.32899e+06", "standardDeviation": "3439.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.85822e+06", "standardDeviation": "1732.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2606.57", "standardDeviation": "85.0551", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "131469", "standardDeviation": "2942.81", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "131329", "standardDeviation": "1956.08", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2683.61", "standardDeviation": "64.4749", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "251032", "standardDeviation": "3377.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "263919", "standardDeviation": "8137.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2706.81", "standardDeviation": "161.441", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "499425", "standardDeviation": "12083", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "537106", "standardDeviation": "15472.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2597.49", "standardDeviation": "84.576", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "994626", "standardDeviation": "34838.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.00199e+06", "standardDeviation": "51040.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2570.82", "standardDeviation": "119.684", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.55764e+06", "standardDeviation": "72085.5", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "3.04214e+06", "standardDeviation": "81977", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2751.42", "standardDeviation": "192.968", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/allocator.json b/230567/neon-cluster-meta-runner-amd/allocator.json new file mode 100644 index 0000000..a2c8923 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "160362", "standardDeviation": "11568.9", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "163235", "standardDeviation": "7102.85", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "163730", "standardDeviation": "5285.39", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "201241", "standardDeviation": "6010.06", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "325451", "standardDeviation": "94112", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "162786", "standardDeviation": "5880.73", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160873", "standardDeviation": "8196.66", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "162009", "standardDeviation": "5927.19", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "202932", "standardDeviation": "5966.61", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "261796", "standardDeviation": "27355.3", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31541.1", "standardDeviation": "12099.9", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31679.8", "standardDeviation": "12805.2", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32214.6", "standardDeviation": "13131.5", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "32734.1", "standardDeviation": "12792.6", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "101671", "standardDeviation": "69653.7", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/develop/allocator.json b/230567/neon-cluster-meta-runner-amd/develop/allocator.json new file mode 100644 index 0000000..8ae64c8 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "160900", "standardDeviation": "6253.4", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160948", "standardDeviation": "6922.05", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "160944", "standardDeviation": "11399.4", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "205710", "standardDeviation": "5869.54", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "308998", "standardDeviation": "121141", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161746", "standardDeviation": "6689.99", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "166055", "standardDeviation": "13905.1", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "158819", "standardDeviation": "11159", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "199924", "standardDeviation": "7895.5", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "262252", "standardDeviation": "28382.9", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31800.7", "standardDeviation": "15082.8", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31912.9", "standardDeviation": "12372.6", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31628.8", "standardDeviation": "11924.4", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33199.8", "standardDeviation": "13080.5", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147720", "standardDeviation": "118330", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/develop/divOperator.json b/230567/neon-cluster-meta-runner-amd/develop/divOperator.json new file mode 100644 index 0000000..ab49e31 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "251692", "standardDeviation": "8078.26", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "679363", "standardDeviation": "23196.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "520248", "standardDeviation": "33736.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "661606", "standardDeviation": "10655.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "971648", "standardDeviation": "96232.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "779365", "standardDeviation": "31601.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82958e+06", "standardDeviation": "188146", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "782718", "standardDeviation": "14901.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.79483e+06", "standardDeviation": "277098", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "857986", "standardDeviation": "24667.7", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/develop/field.json b/230567/neon-cluster-meta-runner-amd/develop/field.json new file mode 100644 index 0000000..9c4f2f0 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "55572.6", "standardDeviation": "3059.74", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "81050.9", "standardDeviation": "3579.09", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "192652", "standardDeviation": "7591.16", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "97241.1", "standardDeviation": "8132.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "552703", "standardDeviation": "48655.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143372", "standardDeviation": "26366.9", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "965665", "standardDeviation": "145753", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "163587", "standardDeviation": "112347", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.72706e+06", "standardDeviation": "286090", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "199678", "standardDeviation": "178355", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "56675.8", "standardDeviation": "3263.86", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77414.6", "standardDeviation": "7512.52", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "200384", "standardDeviation": "37046.4", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "79657.3", "standardDeviation": "8190.8", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547706", "standardDeviation": "51412", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "133099", "standardDeviation": "35520.6", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "972583", "standardDeviation": "145417", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149751", "standardDeviation": "35893.4", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74143e+06", "standardDeviation": "281326", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "177601", "standardDeviation": "38484.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/develop/linear.json b/230567/neon-cluster-meta-runner-amd/develop/linear.json new file mode 100644 index 0000000..e478f49 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "59099.5", "standardDeviation": "2294.01", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "60478.6", "standardDeviation": "2256.88", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2012.72", "standardDeviation": "1740.81", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "204653", "standardDeviation": "7656.68", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "208963", "standardDeviation": "6754.09", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2070.29", "standardDeviation": "1636.72", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "384246", "standardDeviation": "26386.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "390863", "standardDeviation": "26738.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1990.62", "standardDeviation": "1777.88", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "709691", "standardDeviation": "82748.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "710529", "standardDeviation": "84169", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2683.11", "standardDeviation": "6691.43", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24988e+06", "standardDeviation": "213553", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.24406e+06", "standardDeviation": "218065", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2336.81", "standardDeviation": "4111.33", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "203197", "standardDeviation": "7307.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "209068", "standardDeviation": "6957.08", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1940.49", "standardDeviation": "1249.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "385654", "standardDeviation": "26915.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "397330", "standardDeviation": "27037.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2098.38", "standardDeviation": "2180.89", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "848416", "standardDeviation": "17956.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "620589", "standardDeviation": "71590.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2059.61", "standardDeviation": "2810.47", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0996e+06", "standardDeviation": "169571", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09735e+06", "standardDeviation": "183077", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2298.51", "standardDeviation": "3242.37", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.48108e+06", "standardDeviation": "242075", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.39306e+06", "standardDeviation": "247623", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2637.72", "standardDeviation": "3787.86", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/develop/upwind.json b/230567/neon-cluster-meta-runner-amd/develop/upwind.json new file mode 100644 index 0000000..e376b70 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "44654.5", "standardDeviation": "6899.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52425.4", "standardDeviation": "21430.5", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2162.01", "standardDeviation": "1442.53", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "121771", "standardDeviation": "1860.27", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "155159", "standardDeviation": "4168.06", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2149.47", "standardDeviation": "1508.62", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "296332", "standardDeviation": "17780", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "294358", "standardDeviation": "16790.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2142.18", "standardDeviation": "1666.53", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "504603", "standardDeviation": "45758.4", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "539161", "standardDeviation": "57687.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2282.49", "standardDeviation": "2556.54", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "978526", "standardDeviation": "155031", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "959874", "standardDeviation": "156898", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2335.1", "standardDeviation": "2652.47", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "155784", "standardDeviation": "3093.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "171535", "standardDeviation": "5560.89", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2214.94", "standardDeviation": "1673.06", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "323352", "standardDeviation": "17995.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "322693", "standardDeviation": "19544", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2204.85", "standardDeviation": "1978.27", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "589449", "standardDeviation": "54744.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "593908", "standardDeviation": "61680.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2471.95", "standardDeviation": "3086.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.10294e+06", "standardDeviation": "144214", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06715e+06", "standardDeviation": "155066", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2405.86", "standardDeviation": "2690.25", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.52008e+06", "standardDeviation": "247474", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.29992e+06", "standardDeviation": "244250", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2666.37", "standardDeviation": "2889.06", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/divOperator.json b/230567/neon-cluster-meta-runner-amd/divOperator.json new file mode 100644 index 0000000..0a1483c --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "252536", "standardDeviation": "7642.67", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "672499", "standardDeviation": "17111.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "540217", "standardDeviation": "38514.6", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "682135", "standardDeviation": "19635.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "981675", "standardDeviation": "103363", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "779983", "standardDeviation": "26421.7", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.82216e+06", "standardDeviation": "192670", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "812981", "standardDeviation": "27233.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.95947e+06", "standardDeviation": "421721", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "875197", "standardDeviation": "136378", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/field.json b/230567/neon-cluster-meta-runner-amd/field.json new file mode 100644 index 0000000..819a1b4 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "106353", "standardDeviation": "5083.83", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "97843.6", "standardDeviation": "3841.85", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "183047", "standardDeviation": "6159.72", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "87219.7", "standardDeviation": "11083.9", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "545030", "standardDeviation": "49434.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "123430", "standardDeviation": "13280.2", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "957769", "standardDeviation": "143337", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "138219", "standardDeviation": "15134.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71891e+06", "standardDeviation": "278739", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "161991", "standardDeviation": "8304.4", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "56537.9", "standardDeviation": "2702.35", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63548.8", "standardDeviation": "10220.2", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "187353", "standardDeviation": "6506.57", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "67208.4", "standardDeviation": "6935.83", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "536466", "standardDeviation": "50503.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "102640", "standardDeviation": "15350.3", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "933052", "standardDeviation": "125209", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "117029", "standardDeviation": "13475.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74818e+06", "standardDeviation": "283891", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142790", "standardDeviation": "8989.48", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/linear.json b/230567/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..c8b40d9 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50432.1", "standardDeviation": "2361.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "52555.4", "standardDeviation": "828.85", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2031.44", "standardDeviation": "1531.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177911", "standardDeviation": "5575.07", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "179041", "standardDeviation": "6015.12", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2028.47", "standardDeviation": "1658.67", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "406455", "standardDeviation": "25925.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "391893", "standardDeviation": "26903.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3302.51", "standardDeviation": "3274.77", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "717371", "standardDeviation": "82385.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "706039", "standardDeviation": "79943.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2302.85", "standardDeviation": "4508.01", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24511e+06", "standardDeviation": "214545", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.2427e+06", "standardDeviation": "216434", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2541.46", "standardDeviation": "3910.41", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "209210", "standardDeviation": "6693.94", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "214226", "standardDeviation": "6923.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1994.53", "standardDeviation": "1406.51", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "398212", "standardDeviation": "26485.2", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "405183", "standardDeviation": "27162.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2060.83", "standardDeviation": "2572.66", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "711177", "standardDeviation": "81014", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "675256", "standardDeviation": "63808.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2335.41", "standardDeviation": "3864.93", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.27046e+06", "standardDeviation": "209520", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.29478e+06", "standardDeviation": "193620", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2448", "standardDeviation": "3572.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.61919e+06", "standardDeviation": "256422", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.79732e+06", "standardDeviation": "288136", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2485.82", "standardDeviation": "4090.33", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-amd/system-info.log b/230567/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/230567/neon-cluster-meta-runner-amd/upwind.json b/230567/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..df6290d --- /dev/null +++ b/230567/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40661.9", "standardDeviation": "7077.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "45845.8", "standardDeviation": "673.649", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2156.57", "standardDeviation": "1245.32", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "156583", "standardDeviation": "4047.67", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "153756", "standardDeviation": "5355.52", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2090.4", "standardDeviation": "1656.86", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "299503", "standardDeviation": "15586.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "279855", "standardDeviation": "14279.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2369.41", "standardDeviation": "2562.71", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "546784", "standardDeviation": "55688.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "542985", "standardDeviation": "56396.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2285.11", "standardDeviation": "2701.26", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "994135", "standardDeviation": "156820", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "966851", "standardDeviation": "157027", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2068.81", "standardDeviation": "2539.36", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "165625", "standardDeviation": "4974.23", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "168394", "standardDeviation": "4820.95", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3903.7", "standardDeviation": "7751.41", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "333577", "standardDeviation": "17052", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "331015", "standardDeviation": "18996.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2186.78", "standardDeviation": "1960.46", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "615881", "standardDeviation": "55201.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "602042", "standardDeviation": "62997.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2753.37", "standardDeviation": "3399.42", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09696e+06", "standardDeviation": "144694", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.05784e+06", "standardDeviation": "151784", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2458.02", "standardDeviation": "2682.95", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.47058e+06", "standardDeviation": "245046", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.49475e+06", "standardDeviation": "225589", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2405.95", "standardDeviation": "2888.72", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/allocator.json b/230567/neon-cluster-meta-runner-intel/allocator.json new file mode 100644 index 0000000..209274c --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "38942.3", "standardDeviation": "8393.16", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39184.8", "standardDeviation": "8268.04", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41093.8", "standardDeviation": "17689.6", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40480.8", "standardDeviation": "8147.08", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42026.2", "standardDeviation": "7107.5", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38501.6", "standardDeviation": "7596.7", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43475.1", "standardDeviation": "48637.7", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39822.2", "standardDeviation": "7418.6", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40641.4", "standardDeviation": "6597.01", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41993.2", "standardDeviation": "6992.45", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13782.3", "standardDeviation": "8288.75", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13663.2", "standardDeviation": "8408.22", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13363.7", "standardDeviation": "4238.38", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "15036.8", "standardDeviation": "12492.9", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13128", "standardDeviation": "4249.33", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/develop/allocator.json b/230567/neon-cluster-meta-runner-intel/develop/allocator.json new file mode 100644 index 0000000..449c1dc --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "39422.9", "standardDeviation": "13383.2", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37745", "standardDeviation": "8415.8", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43182", "standardDeviation": "52878.9", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41068.1", "standardDeviation": "7714.23", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42480.9", "standardDeviation": "10002.6", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "43534.6", "standardDeviation": "49982.5", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "39710.2", "standardDeviation": "8048.96", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38720.8", "standardDeviation": "7449.38", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41190.6", "standardDeviation": "7457.11", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42478.6", "standardDeviation": "8005.77", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13807.5", "standardDeviation": "8262.04", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13612.5", "standardDeviation": "8325.71", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13896.1", "standardDeviation": "4343.56", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "15393.6", "standardDeviation": "12373.3", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13956.4", "standardDeviation": "4366.74", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/develop/divOperator.json b/230567/neon-cluster-meta-runner-intel/develop/divOperator.json new file mode 100644 index 0000000..32f1e89 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "205434", "standardDeviation": "21073", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147376", "standardDeviation": "11790.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "465079", "standardDeviation": "18884.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152888", "standardDeviation": "9457.52", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "866313", "standardDeviation": "59907.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "155776", "standardDeviation": "11084.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.56545e+06", "standardDeviation": "79413.5", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "236852", "standardDeviation": "10459.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.05488e+06", "standardDeviation": "43290.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "264873", "standardDeviation": "10328.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/develop/field.json b/230567/neon-cluster-meta-runner-intel/develop/field.json new file mode 100644 index 0000000..125b316 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "56682.1", "standardDeviation": "46333.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25651.1", "standardDeviation": "10325.1", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "211167", "standardDeviation": "3167.6", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27512.8", "standardDeviation": "7421.71", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "447828", "standardDeviation": "16354.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34921", "standardDeviation": "52090.4", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "863382", "standardDeviation": "251575", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "71448.2", "standardDeviation": "9753.13", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.56696e+06", "standardDeviation": "106811", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "83938.7", "standardDeviation": "5970.62", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "55578.3", "standardDeviation": "1922.07", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "20998.5", "standardDeviation": "7087.58", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "171430", "standardDeviation": "3617.34", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27223.2", "standardDeviation": "51154.5", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "391153", "standardDeviation": "7864.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "25768.8", "standardDeviation": "7408.37", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "842885", "standardDeviation": "55952.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "68068.6", "standardDeviation": "5428.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.53884e+06", "standardDeviation": "80394.6", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "80494.2", "standardDeviation": "6086.13", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/develop/linear.json b/230567/neon-cluster-meta-runner-intel/develop/linear.json new file mode 100644 index 0000000..8104309 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "42919.1", "standardDeviation": "14313.9", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "57392.9", "standardDeviation": "758.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3426.07", "standardDeviation": "2188.09", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "151092", "standardDeviation": "1739.61", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "145106", "standardDeviation": "2577.51", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3625.26", "standardDeviation": "2881.85", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "281731", "standardDeviation": "6501.83", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "263399", "standardDeviation": "5038.28", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3969.37", "standardDeviation": "7067.71", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "570179", "standardDeviation": "26839.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "600593", "standardDeviation": "34348.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "9620.72", "standardDeviation": "62815.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.08546e+06", "standardDeviation": "82444.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.08022e+06", "standardDeviation": "88478.3", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "25211.3", "standardDeviation": "141679", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "178316", "standardDeviation": "5241.26", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "152445", "standardDeviation": "1376.86", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4077.14", "standardDeviation": "6705.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "303159", "standardDeviation": "8123.58", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "313071", "standardDeviation": "7933.63", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "11773", "standardDeviation": "84418.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "647949", "standardDeviation": "33207.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "597067", "standardDeviation": "32522.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "28859.4", "standardDeviation": "243389", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.16067e+06", "standardDeviation": "76716.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.08136e+06", "standardDeviation": "81349.1", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "25163", "standardDeviation": "168092", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.29159e+06", "standardDeviation": "240821", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.97972e+06", "standardDeviation": "38667", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "18414.9", "standardDeviation": "104739", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/develop/upwind.json b/230567/neon-cluster-meta-runner-intel/develop/upwind.json new file mode 100644 index 0000000..0379494 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "38521.4", "standardDeviation": "1801.82", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "59328.9", "standardDeviation": "755.069", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3511.31", "standardDeviation": "2361.94", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "146366", "standardDeviation": "1410.25", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "118813", "standardDeviation": "1304.69", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3769.93", "standardDeviation": "2954.24", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "255833", "standardDeviation": "7540.53", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "261107", "standardDeviation": "6255.69", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4030.47", "standardDeviation": "7061.58", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "519217", "standardDeviation": "26532", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "470400", "standardDeviation": "9496.98", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10799", "standardDeviation": "73916.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "979318", "standardDeviation": "80204.2", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.04431e+06", "standardDeviation": "106057", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "19661.2", "standardDeviation": "113499", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "149494", "standardDeviation": "1495.42", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "162229", "standardDeviation": "35042.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3903.28", "standardDeviation": "7454.62", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "324229", "standardDeviation": "7123.03", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "312512", "standardDeviation": "9764.83", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "9313.39", "standardDeviation": "60269.1", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "525642", "standardDeviation": "2619.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "610977", "standardDeviation": "35434.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "19649.1", "standardDeviation": "160141", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.17594e+06", "standardDeviation": "82354.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.06846e+06", "standardDeviation": "44154.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "30456.9", "standardDeviation": "221187", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.15208e+06", "standardDeviation": "180106", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.06384e+06", "standardDeviation": "166181", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "14095.5", "standardDeviation": "60760.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/divOperator.json b/230567/neon-cluster-meta-runner-intel/divOperator.json new file mode 100644 index 0000000..b34add5 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "203549", "standardDeviation": "21495.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147786", "standardDeviation": "11303.3", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "495725", "standardDeviation": "35292.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "156159", "standardDeviation": "52369.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "822764", "standardDeviation": "56865.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "158025", "standardDeviation": "10803.2", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55518e+06", "standardDeviation": "74937.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "239475", "standardDeviation": "10700", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.11897e+06", "standardDeviation": "217385", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275324", "standardDeviation": "10225.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/field.json b/230567/neon-cluster-meta-runner-intel/field.json new file mode 100644 index 0000000..be7ee81 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "51678.2", "standardDeviation": "44202.7", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "27150.1", "standardDeviation": "11201.7", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "154869", "standardDeviation": "2978.73", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29326.4", "standardDeviation": "8754.65", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "442425", "standardDeviation": "197286", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31331.6", "standardDeviation": "8055.84", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "908104", "standardDeviation": "247131", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "72763.1", "standardDeviation": "6897.12", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.5929e+06", "standardDeviation": "158414", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "134395", "standardDeviation": "356926", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46098.3", "standardDeviation": "720.437", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "21648.5", "standardDeviation": "8646.49", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "165268", "standardDeviation": "3654.51", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23508.7", "standardDeviation": "7209.56", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "420906", "standardDeviation": "18352.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26875.8", "standardDeviation": "7583.65", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "822374", "standardDeviation": "63529.6", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "83081.9", "standardDeviation": "14579.3", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.58515e+06", "standardDeviation": "151692", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92412.1", "standardDeviation": "9751.52", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/linear.json b/230567/neon-cluster-meta-runner-intel/linear.json new file mode 100644 index 0000000..9a376fe --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "45435.7", "standardDeviation": "16400.1", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "58506.7", "standardDeviation": "972.312", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3512.3", "standardDeviation": "4662.01", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "166058", "standardDeviation": "3520.53", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "167440", "standardDeviation": "4957.65", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3628.75", "standardDeviation": "2919.14", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "259491", "standardDeviation": "6154.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "323985", "standardDeviation": "15607.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "4297.84", "standardDeviation": "10054.3", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "532809", "standardDeviation": "27243.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "665801", "standardDeviation": "68613.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "9948.84", "standardDeviation": "65731.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.06986e+06", "standardDeviation": "105524", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.0123e+06", "standardDeviation": "75379.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "20763.8", "standardDeviation": "118810", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "174923", "standardDeviation": "4309.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "150843", "standardDeviation": "2911.66", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3943.52", "standardDeviation": "6972.33", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "381894", "standardDeviation": "18567.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "263684", "standardDeviation": "6548.05", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "12850.4", "standardDeviation": "92310.5", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "571730", "standardDeviation": "25213.2", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "561588", "standardDeviation": "31965.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "26837.9", "standardDeviation": "227635", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07764e+06", "standardDeviation": "19226.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.0312e+06", "standardDeviation": "64259.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "32368.6", "standardDeviation": "240921", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.20022e+06", "standardDeviation": "68733.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.18271e+06", "standardDeviation": "259176", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "15152.6", "standardDeviation": "67560", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-intel/system-info.log b/230567/neon-cluster-meta-runner-intel/system-info.log new file mode 100644 index 0000000..72c155d --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/system-info.log @@ -0,0 +1,66 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 52 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 224 +On-line CPU(s) list: 0-223 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Platinum 8480+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 56 +Socket(s): 2 +Stepping: 8 +CPU(s) scaling MHz: 25% +CPU max MHz: 3800.0000 +CPU min MHz: 800.0000 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 5.3 MiB (112 instances) +L1i cache: 3.5 MiB (112 instances) +L2 cache: 224 MiB (112 instances) +L3 cache: 210 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0-55,112-167 +NUMA node1 CPU(s): 56-111,168-223 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +[level_zero:gpu][level_zero:0] Intel(R) oneAPI Unified Runtime over Level-Zero, Intel(R) Data Center GPU Max 1100 12.60.7 [1.6.33578+15] + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +Intel(R) oneAPI DPC++/C++ Compiler 2025.3.0 (2025.3.0.20251010) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/intel/oneapi/compiler/2025.3/bin/compiler +Configuration file: /opt/intel/oneapi/compiler/2025.3/bin/compiler/../icpx.cfg diff --git a/230567/neon-cluster-meta-runner-intel/upwind.json b/230567/neon-cluster-meta-runner-intel/upwind.json new file mode 100644 index 0000000..87aa551 --- /dev/null +++ b/230567/neon-cluster-meta-runner-intel/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40562.2", "standardDeviation": "14147.4", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "69771.3", "standardDeviation": "907.964", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3382.87", "standardDeviation": "2278.52", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "143224", "standardDeviation": "3853.04", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "140549", "standardDeviation": "1531.38", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3489.04", "standardDeviation": "2989.07", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "257294", "standardDeviation": "10038.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "278490", "standardDeviation": "1911.84", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "5749.92", "standardDeviation": "23899.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "472552", "standardDeviation": "22945.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "563824", "standardDeviation": "17866.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "10498.7", "standardDeviation": "74178.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "897527", "standardDeviation": "60571.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.1081e+06", "standardDeviation": "1998.22", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "20910.6", "standardDeviation": "120344", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "185712", "standardDeviation": "5798.37", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "152119", "standardDeviation": "3584.21", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3887.26", "standardDeviation": "3072.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "296413", "standardDeviation": "9834.42", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "310270", "standardDeviation": "12602.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "11961.3", "standardDeviation": "84791.8", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "567123", "standardDeviation": "32905.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "608036", "standardDeviation": "48760.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "27645.3", "standardDeviation": "237136", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.28465e+06", "standardDeviation": "141338", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.07428e+06", "standardDeviation": "107491", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "49421.5", "standardDeviation": "410166", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.34877e+06", "standardDeviation": "169109", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.12092e+06", "standardDeviation": "151991", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "14191.6", "standardDeviation": "62162.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/allocator.json b/230567/neon-cluster-meta-runner-nvidia/allocator.json new file mode 100644 index 0000000..cfe9533 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "52708.4", "standardDeviation": "1171.77", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113494", "standardDeviation": "1609.46", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "114831", "standardDeviation": "2961.75", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "298400", "standardDeviation": "3035.72", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "424558", "standardDeviation": "4249.53", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "50013.5", "standardDeviation": "1529.97", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113403", "standardDeviation": "6701.82", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "113780", "standardDeviation": "1388.14", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "292254", "standardDeviation": "1853.19", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "418377", "standardDeviation": "7152.04", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "17792", "standardDeviation": "272.616", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "82050.6", "standardDeviation": "7593.78", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "86709", "standardDeviation": "1140.86", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "183224", "standardDeviation": "1616.99", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "275066", "standardDeviation": "2130.29", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/develop/allocator.json b/230567/neon-cluster-meta-runner-nvidia/develop/allocator.json new file mode 100644 index 0000000..df2eb4d --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "52980.7", "standardDeviation": "1420.77", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121514", "standardDeviation": "2376.27", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111260", "standardDeviation": "3530.62", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "305629", "standardDeviation": "3831.78", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "428341", "standardDeviation": "3662.64", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "52109.1", "standardDeviation": "1681.73", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "120760", "standardDeviation": "13799.6", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "119384", "standardDeviation": "2464.78", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "297119", "standardDeviation": "4113.12", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "422178", "standardDeviation": "4931.79", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "18779.4", "standardDeviation": "1179.02", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "88113.1", "standardDeviation": "7036.49", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "90062", "standardDeviation": "1095.79", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "190770", "standardDeviation": "2625.96", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "283337", "standardDeviation": "3088.66", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/develop/divOperator.json b/230567/neon-cluster-meta-runner-nvidia/develop/divOperator.json new file mode 100644 index 0000000..dd1b154 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "301377", "standardDeviation": "23871.6", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "313312", "standardDeviation": "6379.23", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "572677", "standardDeviation": "4320.43", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "319995", "standardDeviation": "6867.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.13959e+06", "standardDeviation": "35595.3", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "431810", "standardDeviation": "6501.24", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.21817e+06", "standardDeviation": "40078.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "501074", "standardDeviation": "7314.27", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.41094e+06", "standardDeviation": "90862.4", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "671387", "standardDeviation": "10075.2", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/develop/field.json b/230567/neon-cluster-meta-runner-nvidia/develop/field.json new file mode 100644 index 0000000..81851ca --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "216073", "standardDeviation": "1338.3", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28848.9", "standardDeviation": "838.252", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "453250", "standardDeviation": "6309.18", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "107724", "standardDeviation": "2008.77", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "956284", "standardDeviation": "154006", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "152002", "standardDeviation": "5200.72", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.84274e+06", "standardDeviation": "24378.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "197034", "standardDeviation": "7466.86", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.66352e+06", "standardDeviation": "61161.7", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "277163", "standardDeviation": "15755.2", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "300548", "standardDeviation": "1343.19", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "24337.7", "standardDeviation": "650.83", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "598431", "standardDeviation": "2444.87", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "101764", "standardDeviation": "1164.48", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.19255e+06", "standardDeviation": "1757.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "147317", "standardDeviation": "5171.94", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.39703e+06", "standardDeviation": "139555", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "186203", "standardDeviation": "8408.5", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.79036e+06", "standardDeviation": "14386.2", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276395", "standardDeviation": "15871.3", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/develop/linear.json b/230567/neon-cluster-meta-runner-nvidia/develop/linear.json new file mode 100644 index 0000000..34b6d41 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "115876", "standardDeviation": "2399.66", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "133288", "standardDeviation": "774.154", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2478.05", "standardDeviation": "327.765", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "232366", "standardDeviation": "1262.13", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "271046", "standardDeviation": "52980.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2530.54", "standardDeviation": "50.2788", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "463973", "standardDeviation": "13167.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "528798", "standardDeviation": "9863.17", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2458.04", "standardDeviation": "179.879", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "923716", "standardDeviation": "16694.2", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.05873e+06", "standardDeviation": "7254.28", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2453.22", "standardDeviation": "87.8675", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.81266e+06", "standardDeviation": "71324.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.11103e+06", "standardDeviation": "34370.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2468.34", "standardDeviation": "107.584", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "150784", "standardDeviation": "2551.18", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "153487", "standardDeviation": "2354.35", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2425.7", "standardDeviation": "208.982", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "310134", "standardDeviation": "12325.9", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "310922", "standardDeviation": "12441", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2501.88", "standardDeviation": "226.796", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "565693", "standardDeviation": "24999.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "629881", "standardDeviation": "24691.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2431.74", "standardDeviation": "119.237", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12079e+06", "standardDeviation": "69210.9", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.18218e+06", "standardDeviation": "77282.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2570.02", "standardDeviation": "151.904", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.72186e+06", "standardDeviation": "105493", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.92474e+06", "standardDeviation": "140607", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2520.44", "standardDeviation": "209.634", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/develop/upwind.json b/230567/neon-cluster-meta-runner-nvidia/develop/upwind.json new file mode 100644 index 0000000..88e1b99 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83324.2", "standardDeviation": "982.093", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "149388", "standardDeviation": "598.056", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2370.56", "standardDeviation": "49.8278", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "167416", "standardDeviation": "1180.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "299034", "standardDeviation": "1492.45", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2477.29", "standardDeviation": "162.101", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "333186", "standardDeviation": "1738.48", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "596297", "standardDeviation": "1479.81", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2587.94", "standardDeviation": "58.9877", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "665187", "standardDeviation": "2422.48", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.19185e+06", "standardDeviation": "9100.14", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2533.17", "standardDeviation": "83.7009", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33033e+06", "standardDeviation": "2602.86", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "2.38093e+06", "standardDeviation": "1618.63", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2580.17", "standardDeviation": "79.9278", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "151371", "standardDeviation": "3393.66", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "158224", "standardDeviation": "2010.29", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2594.49", "standardDeviation": "54.6953", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "291666", "standardDeviation": "13636", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "316712", "standardDeviation": "8229.74", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2529.52", "standardDeviation": "61.1038", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "518279", "standardDeviation": "30502.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "610649", "standardDeviation": "9725.14", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2423.04", "standardDeviation": "94.9058", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.09696e+06", "standardDeviation": "149797", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.21162e+06", "standardDeviation": "15626.6", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2600.64", "standardDeviation": "107.173", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.32184e+06", "standardDeviation": "147476", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.77576e+06", "standardDeviation": "52674.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2515.86", "standardDeviation": "435.037", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/divOperator.json b/230567/neon-cluster-meta-runner-nvidia/divOperator.json new file mode 100644 index 0000000..2ad550c --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "267581", "standardDeviation": "4906.58", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "300451", "standardDeviation": "5625.44", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "547910", "standardDeviation": "19796.8", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "310152", "standardDeviation": "7620.87", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.01853e+06", "standardDeviation": "25337.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "433898", "standardDeviation": "8704.49", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.00489e+06", "standardDeviation": "73836.3", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "506358", "standardDeviation": "7140.03", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.08092e+06", "standardDeviation": "75134.9", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "680296", "standardDeviation": "13271.8", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/field.json b/230567/neon-cluster-meta-runner-nvidia/field.json new file mode 100644 index 0000000..44e9680 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "368590", "standardDeviation": "4252.02", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "28740.2", "standardDeviation": "698.928", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "388471", "standardDeviation": "3308.2", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "104534", "standardDeviation": "1265.7", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "790176", "standardDeviation": "2667.96", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "154405", "standardDeviation": "5107.23", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.60713e+06", "standardDeviation": "239358", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "196442", "standardDeviation": "8032", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.1427e+06", "standardDeviation": "17501.8", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276920", "standardDeviation": "15689.3", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "256778", "standardDeviation": "34917", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23159.7", "standardDeviation": "469.752", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "501192", "standardDeviation": "1721.2", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "98669.3", "standardDeviation": "2950.72", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "998008", "standardDeviation": "1286.9", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144648", "standardDeviation": "4894.96", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.00368e+06", "standardDeviation": "146239", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "189519", "standardDeviation": "8026.37", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.97471e+06", "standardDeviation": "10401.8", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276388", "standardDeviation": "15615.9", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/linear.json b/230567/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..d1d9bc0 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "88420", "standardDeviation": "2842.95", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "239443", "standardDeviation": "2766.07", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2368.46", "standardDeviation": "42.9101", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "177635", "standardDeviation": "64519.6", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "233974", "standardDeviation": "1390.76", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2442.5", "standardDeviation": "372.481", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "342022", "standardDeviation": "5859.42", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "467473", "standardDeviation": "1906.92", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2376.43", "standardDeviation": "48.9512", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "683984", "standardDeviation": "5412.95", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "931347", "standardDeviation": "1102.16", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2343.59", "standardDeviation": "122.979", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.37369e+06", "standardDeviation": "4041.51", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86514e+06", "standardDeviation": "2842.19", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2492.89", "standardDeviation": "418.759", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "142521", "standardDeviation": "2539.7", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "153460", "standardDeviation": "2750.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2352.33", "standardDeviation": "60.0956", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "272811", "standardDeviation": "5191.72", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "306532", "standardDeviation": "13387", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2309.43", "standardDeviation": "78.0813", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "534449", "standardDeviation": "14265.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "568526", "standardDeviation": "10180", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2394.04", "standardDeviation": "97.0416", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07744e+06", "standardDeviation": "32294", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.15106e+06", "standardDeviation": "46566.4", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2453.61", "standardDeviation": "132.968", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.81982e+06", "standardDeviation": "38143.9", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.97906e+06", "standardDeviation": "27587.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2368.64", "standardDeviation": "241.589", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/230567/neon-cluster-meta-runner-nvidia/system-info.log b/230567/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..c7bca19 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Thu Mar 19 21:00:47 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 590.48.01 Driver Version: 590.48.01 CUDA Version: 13.1 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA L40S On | 00000000:61:00.0 Off | 0 | +| N/A 26C P8 33W / 350W | 0MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/230567/neon-cluster-meta-runner-nvidia/upwind.json b/230567/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..a189a42 --- /dev/null +++ b/230567/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "83363.5", "standardDeviation": "1111.05", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "116751", "standardDeviation": "665.971", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2596.78", "standardDeviation": "327.488", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "170710", "standardDeviation": "1480.96", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "234408", "standardDeviation": "1692.79", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2520.6", "standardDeviation": "152.147", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "332402", "standardDeviation": "1437.2", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "465699", "standardDeviation": "1513.99", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2573.44", "standardDeviation": "169.982", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "676233", "standardDeviation": "4784.46", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "931556", "standardDeviation": "2300.02", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2407.55", "standardDeviation": "156.416", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.33432e+06", "standardDeviation": "3846.27", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.8581e+06", "standardDeviation": "1651.57", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2562.1", "standardDeviation": "85.5013", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "150012", "standardDeviation": "4284.44", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "123502", "standardDeviation": "1864.96", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2561.44", "standardDeviation": "57.429", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "313116", "standardDeviation": "15596", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "281741", "standardDeviation": "10186", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2622.37", "standardDeviation": "186.608", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "554451", "standardDeviation": "39641.8", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "550712", "standardDeviation": "22271.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2541.37", "standardDeviation": "117.714", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0591e+06", "standardDeviation": "81128.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.01428e+06", "standardDeviation": "23328.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2612.7", "standardDeviation": "145.161", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.33166e+06", "standardDeviation": "74392.6", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.52973e+06", "standardDeviation": "132126", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2546.76", "standardDeviation": "131.322", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/244/gdnxlarge/divOperator_fvops.png b/244/gdnxlarge/divOperator_fvops.png index 3ad8bbc..44112f9 100644 Binary files a/244/gdnxlarge/divOperator_fvops.png and b/244/gdnxlarge/divOperator_fvops.png differ diff --git a/244/gdnxlarge/divOperator_relative.png b/244/gdnxlarge/divOperator_relative.png index d765c2f..8b21971 100644 Binary files a/244/gdnxlarge/divOperator_relative.png and b/244/gdnxlarge/divOperator_relative.png differ diff --git a/244/gdnxlarge/divOperator_time.png b/244/gdnxlarge/divOperator_time.png index 2d1f4d0..85eb0cb 100644 Binary files a/244/gdnxlarge/divOperator_time.png and b/244/gdnxlarge/divOperator_time.png differ diff --git a/244/gdnxlarge/field_fvops.png b/244/gdnxlarge/field_fvops.png index 3f23254..eb41405 100644 Binary files a/244/gdnxlarge/field_fvops.png and b/244/gdnxlarge/field_fvops.png differ diff --git a/244/gdnxlarge/field_relative.png b/244/gdnxlarge/field_relative.png index 66f3e2b..92939d0 100644 Binary files a/244/gdnxlarge/field_relative.png and b/244/gdnxlarge/field_relative.png differ diff --git a/244/gdnxlarge/field_time.png b/244/gdnxlarge/field_time.png index 7955613..a3ca9d3 100644 Binary files a/244/gdnxlarge/field_time.png and b/244/gdnxlarge/field_time.png differ diff --git a/245240/neon-cluster-meta-runner-amd/allocator.json b/245240/neon-cluster-meta-runner-amd/allocator.json new file mode 100644 index 0000000..80027a1 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "141514", "standardDeviation": "8565.27", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "137002", "standardDeviation": "6060.72", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "145368", "standardDeviation": "8655.02", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "173362", "standardDeviation": "4059.83", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "227792", "standardDeviation": "21487.9", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143756", "standardDeviation": "11273.8", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "142200", "standardDeviation": "10498.8", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "144269", "standardDeviation": "6615.63", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "177149", "standardDeviation": "4766.56", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "228037", "standardDeviation": "49749.1", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30862.5", "standardDeviation": "18701.6", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30042.3", "standardDeviation": "12151.7", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29970.8", "standardDeviation": "12485.2", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "30371.8", "standardDeviation": "11507.1", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "89274.4", "standardDeviation": "62911.6", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/develop/allocator.json b/245240/neon-cluster-meta-runner-amd/develop/allocator.json new file mode 100644 index 0000000..f56178f --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "146580", "standardDeviation": "6821.81", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149676", "standardDeviation": "6926.47", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150521", "standardDeviation": "9279.32", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "185019", "standardDeviation": "5763.29", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "241137", "standardDeviation": "33005.3", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150168", "standardDeviation": "14080.7", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150149", "standardDeviation": "11786.8", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150782", "standardDeviation": "6600.13", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "185856", "standardDeviation": "8316.53", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "244175", "standardDeviation": "99750.6", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29205.7", "standardDeviation": "13601.9", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31121.4", "standardDeviation": "12789.1", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31403", "standardDeviation": "13209.6", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "31857.7", "standardDeviation": "12025.6", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "131416", "standardDeviation": "90671.9", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/develop/divOperator.json b/245240/neon-cluster-meta-runner-amd/develop/divOperator.json new file mode 100644 index 0000000..b44b3c7 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "266119", "standardDeviation": "8448.73", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "630225", "standardDeviation": "18224.8", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "473933", "standardDeviation": "3778.91", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "634060", "standardDeviation": "14760.5", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.05015e+06", "standardDeviation": "117305", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "730316", "standardDeviation": "19439.1", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.99887e+06", "standardDeviation": "239827", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "866818", "standardDeviation": "181404", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "5.3509e+06", "standardDeviation": "1.5191e+06", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "816847", "standardDeviation": "21154.1", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/develop/field.json b/245240/neon-cluster-meta-runner-amd/develop/field.json new file mode 100644 index 0000000..1e8fdf1 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "54237.9", "standardDeviation": "2810.12", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77639.1", "standardDeviation": "9102.35", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "146491", "standardDeviation": "4199.13", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "80310.4", "standardDeviation": "6219.53", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "516829", "standardDeviation": "43262.5", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "112667", "standardDeviation": "18662.8", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "969467", "standardDeviation": "148783", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128609", "standardDeviation": "68307.9", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71235e+06", "standardDeviation": "274806", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "156596", "standardDeviation": "78233.6", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "50812.9", "standardDeviation": "2572.57", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "62750.1", "standardDeviation": "9903.45", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "213268", "standardDeviation": "5932.12", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "63062.5", "standardDeviation": "5778.25", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "557101", "standardDeviation": "51850.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "94439", "standardDeviation": "24832.7", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "865008", "standardDeviation": "91760.2", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "109761", "standardDeviation": "60592.9", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.74647e+06", "standardDeviation": "290007", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "140141", "standardDeviation": "64131", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/develop/linear.json b/245240/neon-cluster-meta-runner-amd/develop/linear.json new file mode 100644 index 0000000..ffe6e0d --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50575.2", "standardDeviation": "5454.32", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "60092.8", "standardDeviation": "2572.11", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1688.88", "standardDeviation": "1479.38", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206306", "standardDeviation": "6799.34", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "209659", "standardDeviation": "7474.92", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1705.53", "standardDeviation": "1672.54", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "424062", "standardDeviation": "3340.61", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "389087", "standardDeviation": "27198.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1730.64", "standardDeviation": "2756.56", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "707664", "standardDeviation": "82675.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "678748", "standardDeviation": "72322.8", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1841.86", "standardDeviation": "2918.74", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.10905e+06", "standardDeviation": "105524", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.25035e+06", "standardDeviation": "219519", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2546.57", "standardDeviation": "6452.81", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "207271", "standardDeviation": "7065.15", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "213011", "standardDeviation": "7230.65", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1717.15", "standardDeviation": "2039.93", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "397908", "standardDeviation": "26747.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "405800", "standardDeviation": "27312.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1564.03", "standardDeviation": "2366.84", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "505800", "standardDeviation": "26285.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "618434", "standardDeviation": "72189.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1891.76", "standardDeviation": "3147.14", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.05845e+06", "standardDeviation": "137977", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "919540", "standardDeviation": "24236.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1942.04", "standardDeviation": "2680.02", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.41583e+06", "standardDeviation": "201934", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.45201e+06", "standardDeviation": "254549", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2029.08", "standardDeviation": "3059.94", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/develop/upwind.json b/245240/neon-cluster-meta-runner-amd/develop/upwind.json new file mode 100644 index 0000000..c9eba05 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "38016", "standardDeviation": "6163.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "44963.9", "standardDeviation": "516.147", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1728.17", "standardDeviation": "1918.17", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "153964", "standardDeviation": "5239.61", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "134864", "standardDeviation": "4088.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1624.93", "standardDeviation": "1219.98", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "282530", "standardDeviation": "14934.9", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "245932", "standardDeviation": "11472.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1725.51", "standardDeviation": "1762.38", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "555649", "standardDeviation": "56457.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "754288", "standardDeviation": "33791.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1813.2", "standardDeviation": "2501.43", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "927393", "standardDeviation": "31648.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.11347e+06", "standardDeviation": "187086", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2013.91", "standardDeviation": "3501.79", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "196658", "standardDeviation": "6786.55", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "152374", "standardDeviation": "4543.47", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1691.96", "standardDeviation": "1771.14", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "378274", "standardDeviation": "22186.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "369137", "standardDeviation": "24691.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1640.02", "standardDeviation": "1754.57", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "665566", "standardDeviation": "62009.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "644031", "standardDeviation": "65474.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1810.23", "standardDeviation": "4714.16", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.22425e+06", "standardDeviation": "189737", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.15924e+06", "standardDeviation": "164490", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1573.95", "standardDeviation": "2149.67", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.47794e+06", "standardDeviation": "315378", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.38971e+06", "standardDeviation": "251195", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1955.68", "standardDeviation": "2657.18", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/gradOperator.json b/245240/neon-cluster-meta-runner-amd/gradOperator.json new file mode 100644 index 0000000..be5506a --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_explicit", "mean": "1.71067e+06", "standardDeviation": "27170.4", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "689390", "standardDeviation": "11765", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.41236e+06", "standardDeviation": "47511.6", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "759982", "standardDeviation": "17006.7", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "6.79183e+06", "standardDeviation": "50059.2", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "881911", "standardDeviation": "20718.9", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "1.36825e+07", "standardDeviation": "122271", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "952932", "standardDeviation": "18822.7", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "2.88408e+07", "standardDeviation": "559143", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "1.26593e+06", "standardDeviation": "30004.4", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/linear.json b/245240/neon-cluster-meta-runner-amd/linear.json new file mode 100644 index 0000000..9927b7a --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "53987.6", "standardDeviation": "2975.8", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2196.97", "standardDeviation": "1424.97", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "206644", "standardDeviation": "6821.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2089.68", "standardDeviation": "2082.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "349427", "standardDeviation": "19404.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2032.97", "standardDeviation": "2208.19", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "708864", "standardDeviation": "82890.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2447.13", "standardDeviation": "3885.99", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.24417e+06", "standardDeviation": "215374", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2127.69", "standardDeviation": "3008.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "215712", "standardDeviation": "6857.21", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2083.81", "standardDeviation": "1943.67", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "406308", "standardDeviation": "27761.8", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2044.37", "standardDeviation": "3835.08", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "721157", "standardDeviation": "82717.4", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2368.35", "standardDeviation": "3517.12", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.26606e+06", "standardDeviation": "209419", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2193.42", "standardDeviation": "2581.26", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.5656e+06", "standardDeviation": "246060", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2183.73", "standardDeviation": "2764.97", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/solver.json b/245240/neon-cluster-meta-runner-amd/solver.json new file mode 100644 index 0000000..56ebd90 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/solver.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_diagonal", "mean": "302977", "standardDeviation": "17835.3", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "150443", "standardDeviation": "4782.1", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "592848", "standardDeviation": "58964.3", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "230207", "standardDeviation": "169827", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "1.05851e+06", "standardDeviation": "144816", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "240107", "standardDeviation": "17488.3", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "3.05631e+06", "standardDeviation": "94033.5", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "278944", "standardDeviation": "20196.4", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "4.90941e+06", "standardDeviation": "25430.2", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "332479", "standardDeviation": "65982.5", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "734978", "standardDeviation": "91560.2", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "212332", "standardDeviation": "12851.6", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.38094e+06", "standardDeviation": "166228", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "263268", "standardDeviation": "50291.9", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "2.68457e+06", "standardDeviation": "257789", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "283194", "standardDeviation": "93246.3", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "6.45307e+06", "standardDeviation": "527904", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "375065", "standardDeviation": "58176", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.51715e+07", "standardDeviation": "2.21157e+06", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "514362", "standardDeviation": "22856", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "8.28584e+07", "standardDeviation": "2.14888e+07", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.10437e+07", "standardDeviation": "485576", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "2.59286e+06", "standardDeviation": "32921", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "750539", "standardDeviation": "234067", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "5.16268e+06", "standardDeviation": "58962.6", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.49055e+07", "standardDeviation": "303936", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "1.00388e+07", "standardDeviation": "87379.9", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.99173e+07", "standardDeviation": "168823", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "2.25072e+07", "standardDeviation": "160081", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "2.94867e+07", "standardDeviation": "338962", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-amd/system-info.log b/245240/neon-cluster-meta-runner-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/245240/neon-cluster-meta-runner-amd/upwind.json b/245240/neon-cluster-meta-runner-amd/upwind.json new file mode 100644 index 0000000..1310f4a --- /dev/null +++ b/245240/neon-cluster-meta-runner-amd/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "34374.3", "standardDeviation": "2015.15", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1623.2", "standardDeviation": "1335.1", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "132643", "standardDeviation": "1362.26", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1648.47", "standardDeviation": "1438.55", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "251555", "standardDeviation": "10133.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1992.38", "standardDeviation": "3110.5", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "576577", "standardDeviation": "49814.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2176.04", "standardDeviation": "4779.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "972869", "standardDeviation": "148698", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "1925.18", "standardDeviation": "3168.98", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "154388", "standardDeviation": "3079.45", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1701.93", "standardDeviation": "1911.18", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "262646", "standardDeviation": "10204.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1663.09", "standardDeviation": "2250.12", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "550052", "standardDeviation": "32081.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1796.37", "standardDeviation": "2766.25", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "987819", "standardDeviation": "56882.7", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "1927.72", "standardDeviation": "2969.01", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.52259e+06", "standardDeviation": "203515", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3760.59", "standardDeviation": "5966.44", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/allocator.json b/245240/neon-cluster-meta-runner-intel/allocator.json new file mode 100644 index 0000000..56aec3c --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "37189.2", "standardDeviation": "9634.93", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35773.8", "standardDeviation": "8223.09", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37515.8", "standardDeviation": "18671.9", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37326.2", "standardDeviation": "8177.23", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41062", "standardDeviation": "7678.85", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "35430.9", "standardDeviation": "10509.2", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37025.6", "standardDeviation": "7822.94", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "34752.4", "standardDeviation": "7243.17", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37172.6", "standardDeviation": "8072.48", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "40985.5", "standardDeviation": "9143.88", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14374.2", "standardDeviation": "8512.6", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14348", "standardDeviation": "8826.06", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13511.6", "standardDeviation": "1318.44", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14152.7", "standardDeviation": "6297.14", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13987.3", "standardDeviation": "4391.34", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/develop/allocator.json b/245240/neon-cluster-meta-runner-intel/develop/allocator.json new file mode 100644 index 0000000..e12f68a --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "37925.5", "standardDeviation": "8476.65", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41293.6", "standardDeviation": "48506.9", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38411.4", "standardDeviation": "19705.9", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38274.1", "standardDeviation": "7787.56", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "44522.7", "standardDeviation": "48106.8", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37800", "standardDeviation": "7457.86", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "37985.1", "standardDeviation": "7783.6", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "42524.7", "standardDeviation": "56394.7", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "38176.5", "standardDeviation": "7866.85", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "41317.1", "standardDeviation": "6722.64", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "14421.5", "standardDeviation": "8652.93", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13757.5", "standardDeviation": "8424.19", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13529.4", "standardDeviation": "782.884", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "12496.7", "standardDeviation": "1630.93", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "13959.1", "standardDeviation": "4497.48", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/develop/divOperator.json b/245240/neon-cluster-meta-runner-intel/develop/divOperator.json new file mode 100644 index 0000000..97fdb55 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "191960", "standardDeviation": "30724.1", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "143727", "standardDeviation": "11381.5", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "454275", "standardDeviation": "23787.2", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "149701", "standardDeviation": "12196.7", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "877378", "standardDeviation": "81746.4", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "154340", "standardDeviation": "12028.9", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.55049e+06", "standardDeviation": "66655.9", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "239772", "standardDeviation": "9088.85", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.22658e+06", "standardDeviation": "300489", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "276763", "standardDeviation": "24444.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/develop/field.json b/245240/neon-cluster-meta-runner-intel/develop/field.json new file mode 100644 index 0000000..3d250d4 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "52170.3", "standardDeviation": "54658.8", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26437.6", "standardDeviation": "9205.17", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "161244", "standardDeviation": "3040.79", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "26759.2", "standardDeviation": "7920.48", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "455336", "standardDeviation": "198728", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "33716.3", "standardDeviation": "49054.1", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "822837", "standardDeviation": "64676.5", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "70836.5", "standardDeviation": "7109.38", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.50674e+06", "standardDeviation": "51781", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "83285.6", "standardDeviation": "7290.31", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "46410.8", "standardDeviation": "1423.05", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "21491.3", "standardDeviation": "10141.3", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "169875", "standardDeviation": "4143.85", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "21007.3", "standardDeviation": "7978.66", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "378595", "standardDeviation": "6542.8", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23906.3", "standardDeviation": "7864.75", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "863983", "standardDeviation": "254266", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "78858.6", "standardDeviation": "12357", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.71006e+06", "standardDeviation": "194625", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "77554.2", "standardDeviation": "6570.04", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/develop/linear.json b/245240/neon-cluster-meta-runner-intel/develop/linear.json new file mode 100644 index 0000000..133e043 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "42145.2", "standardDeviation": "1741.2", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "58307", "standardDeviation": "1193.77", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3316.35", "standardDeviation": "1778.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "165633", "standardDeviation": "4063.74", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "153696", "standardDeviation": "10590", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3770.84", "standardDeviation": "4873.03", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "305819", "standardDeviation": "12033.1", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "305488", "standardDeviation": "13720", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3985.34", "standardDeviation": "6942.68", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "571179", "standardDeviation": "39389.6", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "623369", "standardDeviation": "57864", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "14345.7", "standardDeviation": "108142", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.04039e+06", "standardDeviation": "87693.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.16036e+06", "standardDeviation": "147543", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "22855.3", "standardDeviation": "153018", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "153625", "standardDeviation": "3347.46", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "159500", "standardDeviation": "3396.08", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4051.14", "standardDeviation": "6879.84", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "287009", "standardDeviation": "7400.11", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "264258", "standardDeviation": "12868.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "14343.7", "standardDeviation": "106775", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "613717", "standardDeviation": "38721.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "554368", "standardDeviation": "34672.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "23924.3", "standardDeviation": "200154", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.0738e+06", "standardDeviation": "48836.7", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.09194e+06", "standardDeviation": "120787", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "22078.8", "standardDeviation": "139805", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.29977e+06", "standardDeviation": "202866", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.97431e+06", "standardDeviation": "40314.6", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "16448.5", "standardDeviation": "80573.8", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/develop/upwind.json b/245240/neon-cluster-meta-runner-intel/develop/upwind.json new file mode 100644 index 0000000..895fd5c --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "40414.4", "standardDeviation": "2216.57", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "69636.4", "standardDeviation": "588.844", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3399.59", "standardDeviation": "1816.8", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "153770", "standardDeviation": "3207.7", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "139203", "standardDeviation": "1149.17", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3504.16", "standardDeviation": "2205.67", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "277694", "standardDeviation": "11898.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "283731", "standardDeviation": "6634.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3637.28", "standardDeviation": "3030.02", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "474367", "standardDeviation": "23664.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "556071", "standardDeviation": "2279.55", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "11945.7", "standardDeviation": "88298", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.05036e+06", "standardDeviation": "143650", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.11236e+06", "standardDeviation": "3818.22", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "25851.9", "standardDeviation": "147094", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "163489", "standardDeviation": "2758.12", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "168658", "standardDeviation": "5269.99", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "4115.2", "standardDeviation": "6832.02", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "334168", "standardDeviation": "15516.5", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "330938", "standardDeviation": "16324.3", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "12086.3", "standardDeviation": "83612.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "650148", "standardDeviation": "42639.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "559643", "standardDeviation": "36408.1", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "24697", "standardDeviation": "208832", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.12322e+06", "standardDeviation": "27401.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.13783e+06", "standardDeviation": "113213", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "22691.3", "standardDeviation": "146200", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.41922e+06", "standardDeviation": "244582", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.09886e+06", "standardDeviation": "31551.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "17509", "standardDeviation": "92453.9", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/gradOperator.json b/245240/neon-cluster-meta-runner-intel/gradOperator.json new file mode 100644 index 0000000..fe37ce8 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_explicit", "mean": "1.75863e+06", "standardDeviation": "62129.1", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "228636", "standardDeviation": "14014.7", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.55856e+06", "standardDeviation": "110894", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "334344", "standardDeviation": "124313", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "7.02348e+06", "standardDeviation": "14308.8", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "514199", "standardDeviation": "11031.2", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "1.40768e+07", "standardDeviation": "239064", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "848693", "standardDeviation": "13250.4", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "2.91526e+07", "standardDeviation": "690209", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "1.55671e+06", "standardDeviation": "16927.4", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/linear.json b/245240/neon-cluster-meta-runner-intel/linear.json new file mode 100644 index 0000000..411aba7 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "45366.5", "standardDeviation": "18472.8", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3327.16", "standardDeviation": "1830.49", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "119654", "standardDeviation": "1343", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3542.32", "standardDeviation": "2277.75", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "305520", "standardDeviation": "11835.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3935.51", "standardDeviation": "6635.7", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "629953", "standardDeviation": "55313.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "12118.9", "standardDeviation": "86333.5", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.04117e+06", "standardDeviation": "86896.7", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "22947.7", "standardDeviation": "157589", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "186614", "standardDeviation": "4050.37", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3926.65", "standardDeviation": "7892.24", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "307368", "standardDeviation": "10450.7", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "15174.4", "standardDeviation": "114232", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "636592", "standardDeviation": "45644.8", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "25152.9", "standardDeviation": "214960", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.07905e+06", "standardDeviation": "39912.3", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "24280.9", "standardDeviation": "157053", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.31518e+06", "standardDeviation": "172415", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "16827.8", "standardDeviation": "85893.5", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/solver.json b/245240/neon-cluster-meta-runner-intel/solver.json new file mode 100644 index 0000000..f84477a --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/solver.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_diagonal", "mean": "285109", "standardDeviation": "10327.3", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "571009", "standardDeviation": "19697.8", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "596269", "standardDeviation": "50382.3", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "467760", "standardDeviation": "9958.06", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "1.0808e+06", "standardDeviation": "137980", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "504251", "standardDeviation": "17645.6", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "1.96355e+06", "standardDeviation": "329136", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "668219", "standardDeviation": "20764.8", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "3.90649e+06", "standardDeviation": "398793", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "590125", "standardDeviation": "17017.9", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "697033", "standardDeviation": "49954.9", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "611935", "standardDeviation": "17928.7", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.25006e+06", "standardDeviation": "2011.46", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "635074", "standardDeviation": "19018.9", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "2.58594e+06", "standardDeviation": "302862", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "503651", "standardDeviation": "13615.9", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "6.33295e+06", "standardDeviation": "376820", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "703024", "standardDeviation": "65005.6", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.73394e+07", "standardDeviation": "510196", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "1.04939e+06", "standardDeviation": "9421.59", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "1.80158e+06", "standardDeviation": "354135", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.08714e+07", "standardDeviation": "158410", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "1.69923e+08", "standardDeviation": "682773", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.76748e+07", "standardDeviation": "27834.8", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "3.53019e+08", "standardDeviation": "1.79538e+06", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "2.68546e+07", "standardDeviation": "30110", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "1.14138e+07", "standardDeviation": "217898", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "2.90791e+07", "standardDeviation": "66338.8", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "2.34643e+07", "standardDeviation": "352240", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "3.44721e+07", "standardDeviation": "112285", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-intel/system-info.log b/245240/neon-cluster-meta-runner-intel/system-info.log new file mode 100644 index 0000000..d426493 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/system-info.log @@ -0,0 +1,66 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 52 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 224 +On-line CPU(s) list: 0-223 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Platinum 8480+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 56 +Socket(s): 2 +Stepping: 8 +CPU(s) scaling MHz: 24% +CPU max MHz: 3800.0000 +CPU min MHz: 800.0000 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 5.3 MiB (112 instances) +L1i cache: 3.5 MiB (112 instances) +L2 cache: 224 MiB (112 instances) +L3 cache: 210 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0-55,112-167 +NUMA node1 CPU(s): 56-111,168-223 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +[level_zero:gpu][level_zero:0] Intel(R) oneAPI Unified Runtime over Level-Zero, Intel(R) Data Center GPU Max 1100 12.60.7 [1.6.33578+15] + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +Intel(R) oneAPI DPC++/C++ Compiler 2025.3.0 (2025.3.0.20251010) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/intel/oneapi/compiler/2025.3/bin/compiler +Configuration file: /opt/intel/oneapi/compiler/2025.3/bin/compiler/../icpx.cfg diff --git a/245240/neon-cluster-meta-runner-intel/upwind.json b/245240/neon-cluster-meta-runner-intel/upwind.json new file mode 100644 index 0000000..7882245 --- /dev/null +++ b/245240/neon-cluster-meta-runner-intel/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "50164.1", "standardDeviation": "99905.9", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3819.32", "standardDeviation": "3838.74", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "111859", "standardDeviation": "1532.19", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3692.68", "standardDeviation": "4520.9", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "260378", "standardDeviation": "38929.4", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "3992.73", "standardDeviation": "7209.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "492340", "standardDeviation": "27396.3", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "9621.68", "standardDeviation": "64725", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.01527e+06", "standardDeviation": "127835", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "20460.9", "standardDeviation": "114419", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "181322", "standardDeviation": "5614.23", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "3722.05", "standardDeviation": "6259.87", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "384087", "standardDeviation": "20428.2", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "11850.4", "standardDeviation": "84611", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "614558", "standardDeviation": "98164.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "25961.7", "standardDeviation": "220629", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.11496e+06", "standardDeviation": "137260", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "20514", "standardDeviation": "120483", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.27692e+06", "standardDeviation": "49616.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "18234.7", "standardDeviation": "99066.3", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/allocator.json b/245240/neon-cluster-meta-runner-nvidia/allocator.json new file mode 100644 index 0000000..73f12fd --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "56151.6", "standardDeviation": "2080.69", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "128462", "standardDeviation": "2443.83", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "127185", "standardDeviation": "4652.24", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "320836", "standardDeviation": "3459.94", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "439107", "standardDeviation": "3334.69", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "55975", "standardDeviation": "2170.01", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126116", "standardDeviation": "3062.68", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "130686", "standardDeviation": "2557", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "327543", "standardDeviation": "4093.98", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "457274", "standardDeviation": "7303.78", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "18407.4", "standardDeviation": "1093.99", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "92336.2", "standardDeviation": "12717.7", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "93108", "standardDeviation": "2003.31", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "197906", "standardDeviation": "2160.59", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "305831", "standardDeviation": "4001.14", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/develop/allocator.json b/245240/neon-cluster-meta-runner-nvidia/develop/allocator.json new file mode 100644 index 0000000..48db78e --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/develop/allocator.json @@ -0,0 +1 @@ +[{"executor": "GPUExecutor", "mean": "55780.7", "standardDeviation": "2228.28", "size": "16384", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "121346", "standardDeviation": "3437.83", "size": "32768", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126374", "standardDeviation": "5217.24", "size": "65536", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "315087", "standardDeviation": "6169.05", "size": "131072", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "449846", "standardDeviation": "3600.55", "size": "262144", "test_case": "Vector::defaultAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "53010.2", "standardDeviation": "1723.95", "size": "16384", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "124696", "standardDeviation": "2861.45", "size": "32768", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "126515", "standardDeviation": "2316.77", "size": "65536", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "323970", "standardDeviation": "8459.09", "size": "131072", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "464934", "standardDeviation": "4715.46", "size": "262144", "test_case": "Vector::umpireAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "18135.8", "standardDeviation": "1003.72", "size": "16384", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "91836.8", "standardDeviation": "1743.32", "size": "32768", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "94492.3", "standardDeviation": "1127.61", "size": "65536", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "193530", "standardDeviation": "2214.09", "size": "131072", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}, {"executor": "GPUExecutor", "mean": "297840", "standardDeviation": "2945.75", "size": "262144", "test_case": "Vector::umpirePoolAllocator", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/develop/divOperator.json b/245240/neon-cluster-meta-runner-nvidia/develop/divOperator.json new file mode 100644 index 0000000..a7dc968 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/develop/divOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "268099", "standardDeviation": "4248.59", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "240982", "standardDeviation": "5352.23", "size": "65536", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "552667", "standardDeviation": "17603.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "318944", "standardDeviation": "5315.4", "size": "131072", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.09943e+06", "standardDeviation": "72036.5", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "446769", "standardDeviation": "7835.03", "size": "262144", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "2.03367e+06", "standardDeviation": "12735.4", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "526761", "standardDeviation": "8455.48", "size": "524288", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "SerialExecutor", "mean": "4.19656e+06", "standardDeviation": "109821", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}, {"executor": "GPUExecutor", "mean": "683098", "standardDeviation": "17234.3", "size": "1048576", "test_case": "DivOperator::div", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/develop/field.json b/245240/neon-cluster-meta-runner-nvidia/develop/field.json new file mode 100644 index 0000000..2b5bbc7 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/develop/field.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "184175", "standardDeviation": "1059.68", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "29722.9", "standardDeviation": "1246.44", "size": "65536", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "388459", "standardDeviation": "5817.28", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "111033", "standardDeviation": "1668.44", "size": "131072", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "806963", "standardDeviation": "162287", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "156617", "standardDeviation": "5670.46", "size": "262144", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.59874e+06", "standardDeviation": "115048", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "205612", "standardDeviation": "7849.12", "size": "524288", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.13365e+06", "standardDeviation": "18843", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "GPUExecutor", "mean": "285317", "standardDeviation": "15384.9", "size": "1048576", "test_case": "Vector::addition", "test_type": ""}, {"executor": "SerialExecutor", "mean": "237428", "standardDeviation": "1172.13", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "23816.8", "standardDeviation": "683.546", "size": "65536", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "477279", "standardDeviation": "68244.8", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "101539", "standardDeviation": "1959.33", "size": "131072", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "931238", "standardDeviation": "1673.2", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "150558", "standardDeviation": "5912.4", "size": "262144", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "1.85848e+06", "standardDeviation": "2237.11", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "198701", "standardDeviation": "8605.87", "size": "524288", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "SerialExecutor", "mean": "3.70934e+06", "standardDeviation": "2355.18", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}, {"executor": "GPUExecutor", "mean": "278788", "standardDeviation": "15251.5", "size": "1048576", "test_case": "Vector::multiplication", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/develop/linear.json b/245240/neon-cluster-meta-runner-nvidia/develop/linear.json new file mode 100644 index 0000000..7c6f57e --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/develop/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "99786.5", "standardDeviation": "3095.25", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "117298", "standardDeviation": "910.368", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2284.55", "standardDeviation": "418.737", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "199775", "standardDeviation": "7011.15", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "234476", "standardDeviation": "1384.49", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2442.5", "standardDeviation": "69.5956", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "398847", "standardDeviation": "16443", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "467698", "standardDeviation": "5832.46", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2380.98", "standardDeviation": "268.437", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "788870", "standardDeviation": "30667", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "937927", "standardDeviation": "2223.05", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2485.61", "standardDeviation": "107.257", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.51837e+06", "standardDeviation": "95349.4", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.86316e+06", "standardDeviation": "1374.35", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2471.89", "standardDeviation": "309.575", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "174389", "standardDeviation": "4425.16", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "168288", "standardDeviation": "3661.74", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2464.83", "standardDeviation": "73.1774", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "353811", "standardDeviation": "20703.1", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "343165", "standardDeviation": "10273.3", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2519.95", "standardDeviation": "95.6829", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "661323", "standardDeviation": "55184.9", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "699644", "standardDeviation": "64091", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2300.28", "standardDeviation": "111.044", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.2885e+06", "standardDeviation": "185489", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.35206e+06", "standardDeviation": "115698", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2476.59", "standardDeviation": "122.657", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "3.60073e+06", "standardDeviation": "255360", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.94476e+06", "standardDeviation": "141222", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2440.21", "standardDeviation": "280.556", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/develop/upwind.json b/245240/neon-cluster-meta-runner-nvidia/develop/upwind.json new file mode 100644 index 0000000..d1ff1e4 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/develop/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "73374.6", "standardDeviation": "4380.36", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "101332", "standardDeviation": "892.212", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2450.78", "standardDeviation": "101.83", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "147506", "standardDeviation": "7337.95", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "201718", "standardDeviation": "1253.11", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2506.44", "standardDeviation": "207.823", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "298316", "standardDeviation": "11984.7", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "403786", "standardDeviation": "4491.59", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2558.09", "standardDeviation": "87.3545", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "574044", "standardDeviation": "12315.1", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "803034", "standardDeviation": "4098.5", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2579.5", "standardDeviation": "228.912", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.18477e+06", "standardDeviation": "37195.7", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "CPUExecutor", "mean": "1.60578e+06", "standardDeviation": "2483.15", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2592.78", "standardDeviation": "83.947", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "132650", "standardDeviation": "1244.22", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "128266", "standardDeviation": "1968.73", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2549.62", "standardDeviation": "246.687", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "262504", "standardDeviation": "5475.81", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "270400", "standardDeviation": "9250.49", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2387.39", "standardDeviation": "186.938", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "524318", "standardDeviation": "15010.3", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "515058", "standardDeviation": "24926.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2502.98", "standardDeviation": "269.011", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.00355e+06", "standardDeviation": "41926.9", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "1.00043e+06", "standardDeviation": "26967.2", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2473.8", "standardDeviation": "85.4373", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.6117e+06", "standardDeviation": "58287.8", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "CPUExecutor", "mean": "2.3225e+06", "standardDeviation": "68824.1", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2472.23", "standardDeviation": "71.3853", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/gradOperator.json b/245240/neon-cluster-meta-runner-nvidia/gradOperator.json new file mode 100644 index 0000000..8951d63 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/gradOperator.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_explicit", "mean": "2.06703e+06", "standardDeviation": "10651.4", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "442571", "standardDeviation": "6748.87", "size": "65536", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "4.11469e+06", "standardDeviation": "8440.58", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "513233", "standardDeviation": "7833.3", "size": "131072", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "8.20804e+06", "standardDeviation": "453852", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "818832", "standardDeviation": "762741", "size": "262144", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "1.64702e+07", "standardDeviation": "660713", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "955292", "standardDeviation": "24788.2", "size": "524288", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "SerialExecutor_explicit", "mean": "3.36304e+07", "standardDeviation": "362926", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}, {"executor": "GPUExecutor_explicit", "mean": "1.45114e+06", "standardDeviation": "45859", "size": "1048576", "test_case": "GradOperator::grad", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/linear.json b/245240/neon-cluster-meta-runner-nvidia/linear.json new file mode 100644 index 0000000..5430858 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/linear.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "100204", "standardDeviation": "1809.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2565.4", "standardDeviation": "201.785", "size": "65536", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "209248", "standardDeviation": "3194.65", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2439.76", "standardDeviation": "62.7859", "size": "131072", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "410997", "standardDeviation": "63202.6", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2566.24", "standardDeviation": "701.297", "size": "262144", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "820989", "standardDeviation": "154769", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2510.69", "standardDeviation": "94.2768", "size": "524288", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.53271e+06", "standardDeviation": "105143", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2550.01", "standardDeviation": "211.377", "size": "1048576", "test_case": "linear", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "190766", "standardDeviation": "5548.47", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2474.5", "standardDeviation": "65.077", "size": "65536", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "410058", "standardDeviation": "26718.4", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2605.02", "standardDeviation": "431.77", "size": "131072", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "741064", "standardDeviation": "82661.5", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2449.03", "standardDeviation": "262.935", "size": "262144", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.33711e+06", "standardDeviation": "191325", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2597.22", "standardDeviation": "112.508", "size": "524288", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.89603e+06", "standardDeviation": "232518", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2658.01", "standardDeviation": "480.224", "size": "1048576", "test_case": "linear", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/solver.json b/245240/neon-cluster-meta-runner-nvidia/solver.json new file mode 100644 index 0000000..e747f53 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/solver.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor_diagonal", "mean": "274820", "standardDeviation": "9801.41", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "59662", "standardDeviation": "1812.47", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "528249", "standardDeviation": "28780", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "277198", "standardDeviation": "4900.38", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "1.05767e+06", "standardDeviation": "105309", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "403334", "standardDeviation": "3571.29", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "1.94587e+06", "standardDeviation": "75679.2", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "584504", "standardDeviation": "7985.76", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "4.84628e+06", "standardDeviation": "193189", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor_diagonal", "mean": "919611", "standardDeviation": "12781.5", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor_diagonal", "mean": "683636", "standardDeviation": "58438.3", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "331852", "standardDeviation": "14720.9", "size": "65536", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.26735e+06", "standardDeviation": "83652.2", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "454858", "standardDeviation": "5223.25", "size": "131072", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "2.56652e+06", "standardDeviation": "155233", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "761275", "standardDeviation": "11991.1", "size": "262144", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "6.7944e+06", "standardDeviation": "177456", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "1.35279e+06", "standardDeviation": "15416.2", "size": "524288", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_diagonal", "mean": "1.36721e+07", "standardDeviation": "614415", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor_diagonal", "mean": "2.55976e+06", "standardDeviation": "83026", "size": "1048576", "test_case": "Solver::DiagonalSolver", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "7.61027e+07", "standardDeviation": "599056", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "8.4075e+06", "standardDeviation": "119021", "size": "65536", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "2.56267e+06", "standardDeviation": "18601", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.05454e+07", "standardDeviation": "50234.8", "size": "131072", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "4.49328e+08", "standardDeviation": "911533", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.31417e+07", "standardDeviation": "231990", "size": "262144", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "1.06623e+07", "standardDeviation": "58138.6", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "1.86098e+07", "standardDeviation": "655341", "size": "524288", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "SerialExecutor_ginkgo_cg", "mean": "2.62939e+07", "standardDeviation": "274852", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}, {"executor": "GPUExecutor_ginkgo_cg", "mean": "2.71504e+07", "standardDeviation": "1.01029e+06", "size": "1048576", "test_case": "Solver::GinkgoCG", "test_type": ""}] \ No newline at end of file diff --git a/245240/neon-cluster-meta-runner-nvidia/system-info.log b/245240/neon-cluster-meta-runner-nvidia/system-info.log new file mode 100644 index 0000000..d6e7b73 --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Sat May 16 01:47:33 2026 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 595.71.05 Driver Version: 595.71.05 CUDA Version: 13.2 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA L40S On | 00000000:61:00.0 Off | 0 | +| N/A 26C P8 33W / 350W | 0MiB / 46068MiB | 0% Default | +| | | N/A | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/245240/neon-cluster-meta-runner-nvidia/upwind.json b/245240/neon-cluster-meta-runner-nvidia/upwind.json new file mode 100644 index 0000000..6fa3c6d --- /dev/null +++ b/245240/neon-cluster-meta-runner-nvidia/upwind.json @@ -0,0 +1 @@ +[{"executor": "SerialExecutor", "mean": "71985.9", "standardDeviation": "2395.88", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2752.48", "standardDeviation": "62.7336", "size": "65536", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "156237", "standardDeviation": "7492.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2827.11", "standardDeviation": "1366.4", "size": "131072", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "294349", "standardDeviation": "13081.6", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2684.27", "standardDeviation": "213.004", "size": "262144", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "582746", "standardDeviation": "22877.8", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2456.6", "standardDeviation": "282.341", "size": "524288", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "1.16985e+06", "standardDeviation": "46230.4", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "GPUExecutor", "mean": "2621.05", "standardDeviation": "129.268", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::scalar"}, {"executor": "SerialExecutor", "mean": "143322", "standardDeviation": "3771.78", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2564.21", "standardDeviation": "65.7788", "size": "65536", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "269538", "standardDeviation": "6016.14", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2542.8", "standardDeviation": "57.4962", "size": "131072", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "489561", "standardDeviation": "3170.14", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2758.88", "standardDeviation": "396.316", "size": "262144", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "1.03737e+06", "standardDeviation": "156816", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2620.22", "standardDeviation": "69.1887", "size": "524288", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "SerialExecutor", "mean": "2.71297e+06", "standardDeviation": "111127", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}, {"executor": "GPUExecutor", "mean": "2560.39", "standardDeviation": "172.187", "size": "1048576", "test_case": "upwind", "test_type": "NeoN::Vec3"}] \ No newline at end of file diff --git a/251/gdnxlarge/divOperator_fvops.png b/251/gdnxlarge/divOperator_fvops.png index 76b0254..1ec2fa2 100644 Binary files a/251/gdnxlarge/divOperator_fvops.png and b/251/gdnxlarge/divOperator_fvops.png differ diff --git a/251/gdnxlarge/divOperator_relative.png b/251/gdnxlarge/divOperator_relative.png index 5a9c0e6..deb49e1 100644 Binary files a/251/gdnxlarge/divOperator_relative.png and b/251/gdnxlarge/divOperator_relative.png differ diff --git a/251/gdnxlarge/divOperator_time.png b/251/gdnxlarge/divOperator_time.png index 5202bac..4f31f3d 100644 Binary files a/251/gdnxlarge/divOperator_time.png and b/251/gdnxlarge/divOperator_time.png differ diff --git a/251/gdnxlarge/field_fvops.png b/251/gdnxlarge/field_fvops.png index 6e471f1..6566dff 100644 Binary files a/251/gdnxlarge/field_fvops.png and b/251/gdnxlarge/field_fvops.png differ diff --git a/251/gdnxlarge/field_relative.png b/251/gdnxlarge/field_relative.png index f6aee12..fb356dc 100644 Binary files a/251/gdnxlarge/field_relative.png and b/251/gdnxlarge/field_relative.png differ diff --git a/251/gdnxlarge/field_time.png b/251/gdnxlarge/field_time.png index 4531197..7fab631 100644 Binary files a/251/gdnxlarge/field_time.png and b/251/gdnxlarge/field_time.png differ diff --git a/258/gdnxlarge/divOperator_fvops.png b/258/gdnxlarge/divOperator_fvops.png index 1a62c58..57d61fa 100644 Binary files a/258/gdnxlarge/divOperator_fvops.png and b/258/gdnxlarge/divOperator_fvops.png differ diff --git a/258/gdnxlarge/divOperator_relative.png b/258/gdnxlarge/divOperator_relative.png index f50c6c6..e065eb5 100644 Binary files a/258/gdnxlarge/divOperator_relative.png and b/258/gdnxlarge/divOperator_relative.png differ diff --git a/258/gdnxlarge/divOperator_time.png b/258/gdnxlarge/divOperator_time.png index a2f1bd0..31ed907 100644 Binary files a/258/gdnxlarge/divOperator_time.png and b/258/gdnxlarge/divOperator_time.png differ diff --git a/258/gdnxlarge/field_fvops.png b/258/gdnxlarge/field_fvops.png index db84a8e..8199b54 100644 Binary files a/258/gdnxlarge/field_fvops.png and b/258/gdnxlarge/field_fvops.png differ diff --git a/258/gdnxlarge/field_relative.png b/258/gdnxlarge/field_relative.png index 06e431b..bd58555 100644 Binary files a/258/gdnxlarge/field_relative.png and b/258/gdnxlarge/field_relative.png differ diff --git a/258/gdnxlarge/field_time.png b/258/gdnxlarge/field_time.png index 3d91360..6785b68 100644 Binary files a/258/gdnxlarge/field_time.png and b/258/gdnxlarge/field_time.png differ diff --git a/277/gdnxlarge/divOperator_fvops.png b/277/gdnxlarge/divOperator_fvops.png index 51c89b4..41bdadc 100644 Binary files a/277/gdnxlarge/divOperator_fvops.png and b/277/gdnxlarge/divOperator_fvops.png differ diff --git a/277/gdnxlarge/divOperator_relative.png b/277/gdnxlarge/divOperator_relative.png index 1bf835f..d5b1901 100644 Binary files a/277/gdnxlarge/divOperator_relative.png and b/277/gdnxlarge/divOperator_relative.png differ diff --git a/277/gdnxlarge/divOperator_time.png b/277/gdnxlarge/divOperator_time.png index e981aa4..137a486 100644 Binary files a/277/gdnxlarge/divOperator_time.png and b/277/gdnxlarge/divOperator_time.png differ diff --git a/277/gdnxlarge/field_fvops.png b/277/gdnxlarge/field_fvops.png index d7ed17d..e98df7e 100644 Binary files a/277/gdnxlarge/field_fvops.png and b/277/gdnxlarge/field_fvops.png differ diff --git a/277/gdnxlarge/field_relative.png b/277/gdnxlarge/field_relative.png index 13d9aa0..ea6c732 100644 Binary files a/277/gdnxlarge/field_relative.png and b/277/gdnxlarge/field_relative.png differ diff --git a/277/gdnxlarge/field_time.png b/277/gdnxlarge/field_time.png index a2ca57a..ddba414 100644 Binary files a/277/gdnxlarge/field_time.png and b/277/gdnxlarge/field_time.png differ diff --git a/278/gdnxlarge/divOperator_fvops.png b/278/gdnxlarge/divOperator_fvops.png index 293f7d0..4aaede4 100644 Binary files a/278/gdnxlarge/divOperator_fvops.png and b/278/gdnxlarge/divOperator_fvops.png differ diff --git a/278/gdnxlarge/divOperator_relative.png b/278/gdnxlarge/divOperator_relative.png index 1093631..1cfade8 100644 Binary files a/278/gdnxlarge/divOperator_relative.png and b/278/gdnxlarge/divOperator_relative.png differ diff --git a/278/gdnxlarge/divOperator_time.png b/278/gdnxlarge/divOperator_time.png index f5366e4..c7c8ff4 100644 Binary files a/278/gdnxlarge/divOperator_time.png and b/278/gdnxlarge/divOperator_time.png differ diff --git a/278/gdnxlarge/field_fvops.png b/278/gdnxlarge/field_fvops.png index e3ca964..f66f5f4 100644 Binary files a/278/gdnxlarge/field_fvops.png and b/278/gdnxlarge/field_fvops.png differ diff --git a/278/gdnxlarge/field_relative.png b/278/gdnxlarge/field_relative.png index 92d45c2..a569156 100644 Binary files a/278/gdnxlarge/field_relative.png and b/278/gdnxlarge/field_relative.png differ diff --git a/278/gdnxlarge/field_time.png b/278/gdnxlarge/field_time.png index 7befba5..37c5991 100644 Binary files a/278/gdnxlarge/field_time.png and b/278/gdnxlarge/field_time.png differ diff --git a/285/g4dn.xlarge/divOperator_fvops.png b/285/g4dn.xlarge/divOperator_fvops.png index 80dadee..227c86a 100644 Binary files a/285/g4dn.xlarge/divOperator_fvops.png and b/285/g4dn.xlarge/divOperator_fvops.png differ diff --git a/285/g4dn.xlarge/divOperator_relative.png b/285/g4dn.xlarge/divOperator_relative.png index 007ca47..13912bd 100644 Binary files a/285/g4dn.xlarge/divOperator_relative.png and b/285/g4dn.xlarge/divOperator_relative.png differ diff --git a/285/g4dn.xlarge/divOperator_time.png b/285/g4dn.xlarge/divOperator_time.png index 5ac1cb6..80ba734 100644 Binary files a/285/g4dn.xlarge/divOperator_time.png and b/285/g4dn.xlarge/divOperator_time.png differ diff --git a/285/g4dn.xlarge/field_fvops.png b/285/g4dn.xlarge/field_fvops.png index 6e4a455..facaf96 100644 Binary files a/285/g4dn.xlarge/field_fvops.png and b/285/g4dn.xlarge/field_fvops.png differ diff --git a/285/g4dn.xlarge/field_relative.png b/285/g4dn.xlarge/field_relative.png index c265baa..19a0e4e 100644 Binary files a/285/g4dn.xlarge/field_relative.png and b/285/g4dn.xlarge/field_relative.png differ diff --git a/285/g4dn.xlarge/field_time.png b/285/g4dn.xlarge/field_time.png index 1e4f569..ff06be7 100644 Binary files a/285/g4dn.xlarge/field_time.png and b/285/g4dn.xlarge/field_time.png differ diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/DivOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/DivOperator.csv new file mode 100644 index 0000000..ed535af --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/DivOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,90,DivOperator,OpenFOAM,73296.5,OpenFOAM,with Allocation,1.0 +2DSquare,N128,91,DivOperator,SerialExecutor,613078.0,NeoN,with Allocation,0.1195549342824241 +2DSquare,N128,92,DivOperator,SerialExecutor,465581.0,NeoN,No allocation,0.15743017863701483 +2DSquare,N128,93,DivOperator,GPUExecutor,1854710.0,NeoN,with Allocation,0.039519116196063 +2DSquare,N128,94,DivOperator,GPUExecutor,603127.0,NeoN,No allocation,0.12152747265501296 +2DSquare,N16,0,DivOperator,OpenFOAM,1936.15,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,44967.5,NeoN,with Allocation,0.04305665202646356 +2DSquare,N16,2,DivOperator,SerialExecutor,20678.1,NeoN,No allocation,0.09363287729530277 +2DSquare,N16,3,DivOperator,GPUExecutor,1784040.0,NeoN,with Allocation,0.001085261541221049 +2DSquare,N16,4,DivOperator,GPUExecutor,577392.0,NeoN,No allocation,0.003353267797267714 +2DSquare,N256,70,DivOperator,OpenFOAM,500073.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,71,DivOperator,SerialExecutor,2455260.0,NeoN,with Allocation,0.2036741526355661 +2DSquare,N256,72,DivOperator,SerialExecutor,1902380.0,NeoN,No allocation,0.2628670402338124 +2DSquare,N256,73,DivOperator,GPUExecutor,2093380.0,NeoN,with Allocation,0.23888305037785781 +2DSquare,N256,74,DivOperator,GPUExecutor,639905.0,NeoN,No allocation,0.7814800634469179 +2DSquare,N32,40,DivOperator,OpenFOAM,4682.43,OpenFOAM,with Allocation,1.0 +2DSquare,N32,41,DivOperator,SerialExecutor,68126.1,NeoN,with Allocation,0.06873180763319785 +2DSquare,N32,42,DivOperator,SerialExecutor,41502.8,NeoN,No allocation,0.11282202646568425 +2DSquare,N32,43,DivOperator,GPUExecutor,1854350.0,NeoN,with Allocation,0.002525105832232319 +2DSquare,N32,44,DivOperator,GPUExecutor,600581.0,NeoN,No allocation,0.007796500388790189 +2DSquare,N512,100,DivOperator,OpenFOAM,2268890.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,101,DivOperator,SerialExecutor,9952420.0,NeoN,with Allocation,0.22797369885917193 +2DSquare,N512,102,DivOperator,SerialExecutor,7514440.0,NeoN,No allocation,0.30193733664784067 +2DSquare,N512,103,DivOperator,GPUExecutor,2431730.0,NeoN,with Allocation,0.9330353287577157 +2DSquare,N512,104,DivOperator,GPUExecutor,801587.0,NeoN,No allocation,2.8304975005832183 +2DSquare,N64,80,DivOperator,OpenFOAM,19472.8,OpenFOAM,with Allocation,1.0 +2DSquare,N64,81,DivOperator,SerialExecutor,160505.0,NeoN,with Allocation,0.12132207719385689 +2DSquare,N64,82,DivOperator,SerialExecutor,124203.0,NeoN,No allocation,0.15678204230171575 +2DSquare,N64,83,DivOperator,GPUExecutor,1818490.0,NeoN,with Allocation,0.01070822495586998 +2DSquare,N64,84,DivOperator,GPUExecutor,597467.0,NeoN,No allocation,0.03259226032567489 +2DSquare,N8,10,DivOperator,OpenFOAM,1077.21,OpenFOAM,with Allocation,1.0 +2DSquare,N8,11,DivOperator,SerialExecutor,38057.4,NeoN,with Allocation,0.028304876318403255 +2DSquare,N8,12,DivOperator,SerialExecutor,14967.0,NeoN,No allocation,0.07197233914612147 +2DSquare,N8,13,DivOperator,GPUExecutor,1769630.0,NeoN,with Allocation,0.0006087204669902748 +2DSquare,N8,14,DivOperator,GPUExecutor,579813.0,NeoN,No allocation,0.0018578576196118404 +3DCube,N128,50,DivOperator,OpenFOAM,54616000.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,51,DivOperator,SerialExecutor,182045000.0,NeoN,with Allocation,0.30001373286824684 +3DCube,N128,52,DivOperator,SerialExecutor,110586000.0,NeoN,No allocation,0.4938780677481779 +3DCube,N128,53,DivOperator,GPUExecutor,4462790.0,NeoN,with Allocation,12.238084247746364 +3DCube,N128,54,DivOperator,GPUExecutor,2218150.0,NeoN,No allocation,24.622320402136914 +3DCube,N16,20,DivOperator,OpenFOAM,27335.6,OpenFOAM,with Allocation,1.0 +3DCube,N16,21,DivOperator,SerialExecutor,229748.0,NeoN,with Allocation,0.11898079635078433 +3DCube,N16,22,DivOperator,SerialExecutor,184720.0,NeoN,No allocation,0.14798397574707664 +3DCube,N16,23,DivOperator,GPUExecutor,1904770.0,NeoN,with Allocation,0.014351129007701717 +3DCube,N16,24,DivOperator,GPUExecutor,614383.0,NeoN,No allocation,0.044492767540768544 +3DCube,N32,60,DivOperator,OpenFOAM,314441.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,DivOperator,SerialExecutor,1868710.0,NeoN,with Allocation,0.16826634416255062 +3DCube,N32,62,DivOperator,SerialExecutor,1469820.0,NeoN,No allocation,0.2139316378876325 +3DCube,N32,63,DivOperator,GPUExecutor,1941440.0,NeoN,with Allocation,0.1619627699027526 +3DCube,N32,64,DivOperator,GPUExecutor,643285.0,NeoN,No allocation,0.4888051174829197 +3DCube,N64,110,DivOperator,OpenFOAM,3467820.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,111,DivOperator,SerialExecutor,15970300.0,NeoN,with Allocation,0.21714181950245143 +3DCube,N64,112,DivOperator,SerialExecutor,11551700.0,NeoN,No allocation,0.3001999705671027 +3DCube,N64,113,DivOperator,GPUExecutor,2867750.0,NeoN,with Allocation,1.2092476680324296 +3DCube,N64,114,DivOperator,GPUExecutor,892221.0,NeoN,No allocation,3.886727615691628 +3DCube,N8,30,DivOperator,OpenFOAM,4086.77,OpenFOAM,with Allocation,1.0 +3DCube,N8,31,DivOperator,SerialExecutor,62177.7,NeoN,with Allocation,0.06572726234646827 +3DCube,N8,32,DivOperator,SerialExecutor,36566.8,NeoN,No allocation,0.11176176203550761 +3DCube,N8,33,DivOperator,GPUExecutor,1818740.0,NeoN,with Allocation,0.0022470336606661757 +3DCube,N8,34,DivOperator,GPUExecutor,600545.0,NeoN,No allocation,0.006805102032320642 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv new file mode 100644 index 0000000..c06fdc3 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,95,LaplacianOperator,OpenFOAM,68568.7,OpenFOAM,with Allocation,1.0 +2DSquare,N128,96,LaplacianOperator,SerialExecutor,576937.0,NeoN,with Allocation,0.11884954509764498 +2DSquare,N128,97,LaplacianOperator,SerialExecutor,420494.0,NeoN,No allocation,0.16306701165771686 +2DSquare,N128,98,LaplacianOperator,GPUExecutor,1305150.0,NeoN,with Allocation,0.05253702639543347 +2DSquare,N128,99,LaplacianOperator,GPUExecutor,44134.2,NeoN,No allocation,1.553640940585759 +2DSquare,N16,5,LaplacianOperator,OpenFOAM,2685.72,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,30471.6,NeoN,with Allocation,0.088138463356043 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,7549.64,NeoN,No allocation,0.3557414658182376 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1240690.0,NeoN,with Allocation,0.0021646986757368884 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,34723.2,NeoN,No allocation,0.07734655792092894 +2DSquare,N256,75,LaplacianOperator,OpenFOAM,403647.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,LaplacianOperator,SerialExecutor,2286430.0,NeoN,with Allocation,0.17654028332378424 +2DSquare,N256,77,LaplacianOperator,SerialExecutor,1732680.0,NeoN,No allocation,0.23296107763695548 +2DSquare,N256,78,LaplacianOperator,GPUExecutor,1480860.0,NeoN,with Allocation,0.2725760706616426 +2DSquare,N256,79,LaplacianOperator,GPUExecutor,73327.2,NeoN,No allocation,5.504737668968677 +2DSquare,N32,45,LaplacianOperator,OpenFOAM,5160.58,OpenFOAM,with Allocation,1.0 +2DSquare,N32,46,LaplacianOperator,SerialExecutor,54775.8,NeoN,with Allocation,0.094212772793825 +2DSquare,N32,47,LaplacianOperator,SerialExecutor,32154.2,NeoN,No allocation,0.16049474096696542 +2DSquare,N32,48,LaplacianOperator,GPUExecutor,1250650.0,NeoN,with Allocation,0.004126318314476472 +2DSquare,N32,49,LaplacianOperator,GPUExecutor,40840.0,NeoN,No allocation,0.1263609206660137 +2DSquare,N512,105,LaplacianOperator,OpenFOAM,1650470.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,106,LaplacianOperator,SerialExecutor,9271460.0,NeoN,with Allocation,0.17801619162462007 +2DSquare,N512,107,LaplacianOperator,SerialExecutor,6906240.0,NeoN,No allocation,0.23898242748586784 +2DSquare,N512,108,LaplacianOperator,GPUExecutor,1737320.0,NeoN,with Allocation,0.9500092095871803 +2DSquare,N512,109,LaplacianOperator,GPUExecutor,151593.0,NeoN,No allocation,10.887507998390427 +2DSquare,N64,85,LaplacianOperator,OpenFOAM,17914.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,86,LaplacianOperator,SerialExecutor,142760.0,NeoN,with Allocation,0.125484729616139 +2DSquare,N64,87,LaplacianOperator,SerialExecutor,105881.0,NeoN,No allocation,0.16919182856225387 +2DSquare,N64,88,LaplacianOperator,GPUExecutor,1281920.0,NeoN,with Allocation,0.013974506989515727 +2DSquare,N64,89,LaplacianOperator,GPUExecutor,41475.3,NeoN,No allocation,0.43192454304128 +2DSquare,N8,15,LaplacianOperator,OpenFOAM,1865.38,OpenFOAM,with Allocation,1.0 +2DSquare,N8,16,LaplacianOperator,SerialExecutor,25125.0,NeoN,with Allocation,0.07424398009950249 +2DSquare,N8,17,LaplacianOperator,SerialExecutor,2464.19,NeoN,No allocation,0.7569951992338253 +2DSquare,N8,18,LaplacianOperator,GPUExecutor,1240290.0,NeoN,with Allocation,0.0015039869707890896 +2DSquare,N8,19,LaplacianOperator,GPUExecutor,35287.9,NeoN,No allocation,0.05286174581088702 +3DCube,N128,55,LaplacianOperator,OpenFOAM,38396300.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,56,LaplacianOperator,SerialExecutor,163599000.0,NeoN,with Allocation,0.2346976448511299 +3DCube,N128,57,LaplacianOperator,SerialExecutor,92669500.0,NeoN,No allocation,0.4143358926076001 +3DCube,N128,58,LaplacianOperator,GPUExecutor,3660070.0,NeoN,with Allocation,10.490591709994618 +3DCube,N128,59,LaplacianOperator,GPUExecutor,1450600.0,NeoN,No allocation,26.469254101750998 +3DCube,N16,25,LaplacianOperator,OpenFOAM,25108.3,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,LaplacianOperator,SerialExecutor,206438.0,NeoN,with Allocation,0.12162634786231216 +3DCube,N16,27,LaplacianOperator,SerialExecutor,162255.0,NeoN,No allocation,0.15474592462481895 +3DCube,N16,28,LaplacianOperator,GPUExecutor,1327020.0,NeoN,with Allocation,0.01892081505930581 +3DCube,N16,29,LaplacianOperator,GPUExecutor,85275.4,NeoN,No allocation,0.29443778627834055 +3DCube,N32,65,LaplacianOperator,OpenFOAM,301770.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,LaplacianOperator,SerialExecutor,1722380.0,NeoN,with Allocation,0.17520523926195147 +3DCube,N32,67,LaplacianOperator,SerialExecutor,1312860.0,NeoN,No allocation,0.22985695352131988 +3DCube,N32,68,LaplacianOperator,GPUExecutor,1361610.0,NeoN,with Allocation,0.22162733822460176 +3DCube,N32,69,LaplacianOperator,GPUExecutor,72179.4,NeoN,No allocation,4.180832758377044 +3DCube,N64,115,LaplacianOperator,OpenFOAM,2490700.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,116,LaplacianOperator,SerialExecutor,14627900.0,NeoN,with Allocation,0.17027051046288258 +3DCube,N64,117,LaplacianOperator,SerialExecutor,10325400.0,NeoN,No allocation,0.24122067910202027 +3DCube,N64,118,LaplacianOperator,GPUExecutor,1823490.0,NeoN,with Allocation,1.3658972629408441 +3DCube,N64,119,LaplacianOperator,GPUExecutor,233198.0,NeoN,No allocation,10.680623332961689 +3DCube,N8,35,LaplacianOperator,OpenFOAM,5418.38,OpenFOAM,with Allocation,1.0 +3DCube,N8,36,LaplacianOperator,SerialExecutor,47863.9,NeoN,with Allocation,0.11320389688261925 +3DCube,N8,37,LaplacianOperator,SerialExecutor,21896.2,NeoN,No allocation,0.24745754971182213 +3DCube,N8,38,LaplacianOperator,GPUExecutor,1265470.0,NeoN,with Allocation,0.004281713513556228 +3DCube,N8,39,LaplacianOperator,GPUExecutor,41883.9,NeoN,No allocation,0.1293666540126397 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/advection-diffusion-equation_scalar.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/advection-diffusion-equation_scalar.csv new file mode 100644 index 0000000..3b6a462 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/advection-diffusion-equation_scalar.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,36,advection-diffusion-equation_scalar,OpenFOAM,205351.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N128,37,advection-diffusion-equation_scalar,OpenFOAM,266897.0,OpenFOAM,implicit-time-integration,0.7694016792995051 +2DSquare,N128,38,advection-diffusion-equation_scalar,SerialExecutor,256572.0,NeoN,explicit-time-integration,0.8003640303696429 +2DSquare,N128,39,advection-diffusion-equation_scalar,SerialExecutor,1120690.0,NeoN,implicit-time-integration,0.18323622054270136 +2DSquare,N16,0,advection-diffusion-equation_scalar,OpenFOAM,8264.33,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,advection-diffusion-equation_scalar,OpenFOAM,7782.48,OpenFOAM,implicit-time-integration,1.061914710991869 +2DSquare,N16,2,advection-diffusion-equation_scalar,SerialExecutor,42249.8,NeoN,explicit-time-integration,0.19560636973429457 +2DSquare,N16,3,advection-diffusion-equation_scalar,SerialExecutor,68340.4,NeoN,implicit-time-integration,0.1209289088152835 +2DSquare,N256,28,advection-diffusion-equation_scalar,OpenFOAM,950812.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,29,advection-diffusion-equation_scalar,OpenFOAM,1381750.0,OpenFOAM,implicit-time-integration,0.6881215849466257 +2DSquare,N256,30,advection-diffusion-equation_scalar,SerialExecutor,1062430.0,NeoN,explicit-time-integration,0.8949408431614319 +2DSquare,N256,31,advection-diffusion-equation_scalar,SerialExecutor,4509350.0,NeoN,implicit-time-integration,0.2108534489449699 +2DSquare,N32,16,advection-diffusion-equation_scalar,OpenFOAM,16394.5,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N32,17,advection-diffusion-equation_scalar,OpenFOAM,15735.1,OpenFOAM,implicit-time-integration,1.0419063113675795 +2DSquare,N32,18,advection-diffusion-equation_scalar,SerialExecutor,49139.0,NeoN,explicit-time-integration,0.3336351981114797 +2DSquare,N32,19,advection-diffusion-equation_scalar,SerialExecutor,115298.0,NeoN,implicit-time-integration,0.1421924057659283 +2DSquare,N512,40,advection-diffusion-equation_scalar,OpenFOAM,5016440.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N512,41,advection-diffusion-equation_scalar,OpenFOAM,7188500.0,OpenFOAM,implicit-time-integration,0.6978423871461362 +2DSquare,N512,42,advection-diffusion-equation_scalar,SerialExecutor,4384920.0,NeoN,explicit-time-integration,1.1440208715324338 +2DSquare,N512,43,advection-diffusion-equation_scalar,SerialExecutor,19193400.0,NeoN,implicit-time-integration,0.26136276011545634 +2DSquare,N64,32,advection-diffusion-equation_scalar,OpenFOAM,49315.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,33,advection-diffusion-equation_scalar,OpenFOAM,54675.5,OpenFOAM,implicit-time-integration,0.9019579153368511 +2DSquare,N64,34,advection-diffusion-equation_scalar,SerialExecutor,68193.3,NeoN,explicit-time-integration,0.7231648856999148 +2DSquare,N64,35,advection-diffusion-equation_scalar,SerialExecutor,293822.0,NeoN,implicit-time-integration,0.16783971247898388 +2DSquare,N8,4,advection-diffusion-equation_scalar,OpenFOAM,6314.95,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N8,5,advection-diffusion-equation_scalar,OpenFOAM,4656.43,OpenFOAM,implicit-time-integration,1.3561784457191453 +2DSquare,N8,6,advection-diffusion-equation_scalar,SerialExecutor,41705.7,NeoN,explicit-time-integration,0.15141695259880544 +2DSquare,N8,7,advection-diffusion-equation_scalar,SerialExecutor,58208.4,NeoN,implicit-time-integration,0.10848863737879756 +3DCube,N128,20,advection-diffusion-equation_scalar,OpenFOAM,82917600.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N128,21,advection-diffusion-equation_scalar,OpenFOAM,155434000.0,OpenFOAM,implicit-time-integration,0.5334585740571561 +3DCube,N128,22,advection-diffusion-equation_scalar,SerialExecutor,125777000.0,NeoN,explicit-time-integration,0.6592429458486051 +3DCube,N128,23,advection-diffusion-equation_scalar,SerialExecutor,298901000.0,NeoN,implicit-time-integration,0.27740823884831434 +3DCube,N16,8,advection-diffusion-equation_scalar,OpenFOAM,67838.2,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,9,advection-diffusion-equation_scalar,OpenFOAM,76580.6,OpenFOAM,implicit-time-integration,0.8858405392488437 +3DCube,N16,10,advection-diffusion-equation_scalar,SerialExecutor,78788.9,NeoN,explicit-time-integration,0.8610121476502401 +3DCube,N16,11,advection-diffusion-equation_scalar,SerialExecutor,425219.0,NeoN,implicit-time-integration,0.15953708559589294 +3DCube,N32,24,advection-diffusion-equation_scalar,OpenFOAM,689367.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,25,advection-diffusion-equation_scalar,OpenFOAM,940675.0,OpenFOAM,implicit-time-integration,0.7328429053605124 +3DCube,N32,26,advection-diffusion-equation_scalar,SerialExecutor,751157.0,NeoN,explicit-time-integration,0.9177402327343018 +3DCube,N32,27,advection-diffusion-equation_scalar,SerialExecutor,3415280.0,NeoN,implicit-time-integration,0.20184787191679746 +3DCube,N64,44,advection-diffusion-equation_scalar,OpenFOAM,7126440.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,45,advection-diffusion-equation_scalar,OpenFOAM,10398800.0,OpenFOAM,implicit-time-integration,0.6853136900411586 +3DCube,N64,46,advection-diffusion-equation_scalar,SerialExecutor,6632400.0,NeoN,explicit-time-integration,1.074488872806224 +3DCube,N64,47,advection-diffusion-equation_scalar,SerialExecutor,29290200.0,NeoN,implicit-time-integration,0.24330458651699202 +3DCube,N8,12,advection-diffusion-equation_scalar,OpenFOAM,16019.9,OpenFOAM,explicit-time-integration,1.0 +3DCube,N8,13,advection-diffusion-equation_scalar,OpenFOAM,14799.9,OpenFOAM,implicit-time-integration,1.0824329894120905 +3DCube,N8,14,advection-diffusion-equation_scalar,SerialExecutor,48406.3,NeoN,explicit-time-integration,0.33094659166265544 +3DCube,N8,15,advection-diffusion-equation_scalar,SerialExecutor,103934.0,NeoN,implicit-time-integration,0.15413531664325436 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv new file mode 100644 index 0000000..4eedd6c --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,90,DivOperator,OpenFOAM,74303.8,OpenFOAM,with Allocation,1.0 +2DSquare,N128,91,DivOperator,SerialExecutor,622123.0,NeoN,with Allocation,0.11943586718382057 +2DSquare,N128,92,DivOperator,SerialExecutor,465893.0,NeoN,No allocation,0.15948683495995863 +2DSquare,N128,93,DivOperator,GPUExecutor,1856660.0,NeoN,with Allocation,0.040020143698900175 +2DSquare,N128,94,DivOperator,GPUExecutor,608151.0,NeoN,No allocation,0.12217985335878755 +2DSquare,N16,0,DivOperator,OpenFOAM,1929.57,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,43341.2,NeoN,with Allocation,0.04452045628639724 +2DSquare,N16,2,DivOperator,SerialExecutor,20054.2,NeoN,No allocation,0.09621774989777701 +2DSquare,N16,3,DivOperator,GPUExecutor,1800780.0,NeoN,with Allocation,0.0010715190084296805 +2DSquare,N16,4,DivOperator,GPUExecutor,564883.0,NeoN,No allocation,0.0034158754998822763 +2DSquare,N256,70,DivOperator,OpenFOAM,481140.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,71,DivOperator,SerialExecutor,2447010.0,NeoN,with Allocation,0.19662363455809334 +2DSquare,N256,72,DivOperator,SerialExecutor,1892850.0,NeoN,No allocation,0.2541881290118076 +2DSquare,N256,73,DivOperator,GPUExecutor,2026410.0,NeoN,with Allocation,0.23743467511510505 +2DSquare,N256,74,DivOperator,GPUExecutor,638294.0,NeoN,No allocation,0.7537905729961428 +2DSquare,N32,40,DivOperator,OpenFOAM,4611.68,OpenFOAM,with Allocation,1.0 +2DSquare,N32,41,DivOperator,SerialExecutor,68100.8,NeoN,with Allocation,0.06771844089937269 +2DSquare,N32,42,DivOperator,SerialExecutor,41451.3,NeoN,No allocation,0.11125537679156021 +2DSquare,N32,43,DivOperator,GPUExecutor,1808150.0,NeoN,with Allocation,0.0025504963636866413 +2DSquare,N32,44,DivOperator,GPUExecutor,593992.0,NeoN,No allocation,0.007763875607752294 +2DSquare,N512,100,DivOperator,OpenFOAM,2350500.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,101,DivOperator,SerialExecutor,9961160.0,NeoN,with Allocation,0.23596649386216062 +2DSquare,N512,102,DivOperator,SerialExecutor,7570040.0,NeoN,No allocation,0.31050034081722155 +2DSquare,N512,103,DivOperator,GPUExecutor,2390860.0,NeoN,with Allocation,0.983119045029822 +2DSquare,N512,104,DivOperator,GPUExecutor,795425.0,NeoN,No allocation,2.9550240437501962 +2DSquare,N64,80,DivOperator,OpenFOAM,18557.6,OpenFOAM,with Allocation,1.0 +2DSquare,N64,81,DivOperator,SerialExecutor,160353.0,NeoN,with Allocation,0.11572967141244628 +2DSquare,N64,82,DivOperator,SerialExecutor,124424.0,NeoN,No allocation,0.1491480743264965 +2DSquare,N64,83,DivOperator,GPUExecutor,1820030.0,NeoN,with Allocation,0.010196315445349801 +2DSquare,N64,84,DivOperator,GPUExecutor,594556.0,NeoN,No allocation,0.031212535068185332 +2DSquare,N8,10,DivOperator,OpenFOAM,1056.52,OpenFOAM,with Allocation,1.0 +2DSquare,N8,11,DivOperator,SerialExecutor,38125.3,NeoN,with Allocation,0.027711781940076535 +2DSquare,N8,12,DivOperator,SerialExecutor,14962.6,NeoN,No allocation,0.07061072273535347 +2DSquare,N8,13,DivOperator,GPUExecutor,1785810.0,NeoN,with Allocation,0.0005916194891953791 +2DSquare,N8,14,DivOperator,GPUExecutor,587329.0,NeoN,No allocation,0.0017988554966637098 +3DCube,N128,50,DivOperator,OpenFOAM,54000400.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,51,DivOperator,SerialExecutor,181282000.0,NeoN,with Allocation,0.297880650036959 +3DCube,N128,52,DivOperator,SerialExecutor,109971000.0,NeoN,No allocation,0.49104218384846915 +3DCube,N128,53,DivOperator,GPUExecutor,4476980.0,NeoN,with Allocation,12.061791654195462 +3DCube,N128,54,DivOperator,GPUExecutor,2266640.0,NeoN,No allocation,23.82398616454311 +3DCube,N16,20,DivOperator,OpenFOAM,28550.0,OpenFOAM,with Allocation,1.0 +3DCube,N16,21,DivOperator,SerialExecutor,230876.0,NeoN,with Allocation,0.12365945355948647 +3DCube,N16,22,DivOperator,SerialExecutor,186848.0,NeoN,No allocation,0.15279799623223156 +3DCube,N16,23,DivOperator,GPUExecutor,1892120.0,NeoN,with Allocation,0.015088894996089043 +3DCube,N16,24,DivOperator,GPUExecutor,618574.0,NeoN,No allocation,0.046154542544626836 +3DCube,N32,60,DivOperator,OpenFOAM,314248.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,DivOperator,SerialExecutor,1858300.0,NeoN,with Allocation,0.16910509605553461 +3DCube,N32,62,DivOperator,SerialExecutor,1466960.0,NeoN,No allocation,0.21421715656868626 +3DCube,N32,63,DivOperator,GPUExecutor,1899800.0,NeoN,with Allocation,0.16541109590483208 +3DCube,N32,64,DivOperator,GPUExecutor,631538.0,NeoN,No allocation,0.4975915938550016 +3DCube,N64,110,DivOperator,OpenFOAM,3340500.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,111,DivOperator,SerialExecutor,15824500.0,NeoN,with Allocation,0.21109671711586464 +3DCube,N64,112,DivOperator,SerialExecutor,11439700.0,NeoN,No allocation,0.2920094058410623 +3DCube,N64,113,DivOperator,GPUExecutor,2494090.0,NeoN,with Allocation,1.339366261842997 +3DCube,N64,114,DivOperator,GPUExecutor,887751.0,NeoN,No allocation,3.7628794560636933 +3DCube,N8,30,DivOperator,OpenFOAM,4126.14,OpenFOAM,with Allocation,1.0 +3DCube,N8,31,DivOperator,SerialExecutor,62452.8,NeoN,with Allocation,0.06606813465529168 +3DCube,N8,32,DivOperator,SerialExecutor,36468.1,NeoN,No allocation,0.11314381610229216 +3DCube,N8,33,DivOperator,GPUExecutor,1802480.0,NeoN,with Allocation,0.0022891460654209756 +3DCube,N8,34,DivOperator,GPUExecutor,593518.0,NeoN,No allocation,0.006952004825464435 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv new file mode 100644 index 0000000..c99ee09 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,95,LaplacianOperator,OpenFOAM,70410.3,OpenFOAM,with Allocation,1.0 +2DSquare,N128,96,LaplacianOperator,SerialExecutor,573265.0,NeoN,with Allocation,0.12282330161443661 +2DSquare,N128,97,LaplacianOperator,SerialExecutor,421920.0,NeoN,No allocation,0.1668806882821388 +2DSquare,N128,98,LaplacianOperator,GPUExecutor,1296480.0,NeoN,with Allocation,0.05430882080710848 +2DSquare,N128,99,LaplacianOperator,GPUExecutor,44227.4,NeoN,No allocation,1.592006312828699 +2DSquare,N16,5,LaplacianOperator,OpenFOAM,2772.6,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,29447.9,NeoN,with Allocation,0.09415272396333864 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,7467.3,NeoN,No allocation,0.37129886304286686 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1232810.0,NeoN,with Allocation,0.002249008363008087 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,32491.6,NeoN,No allocation,0.0853328244838666 +2DSquare,N256,75,LaplacianOperator,OpenFOAM,393586.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,LaplacianOperator,SerialExecutor,2281570.0,NeoN,with Allocation,0.17250665112181524 +2DSquare,N256,77,LaplacianOperator,SerialExecutor,1728800.0,NeoN,No allocation,0.22766427579824156 +2DSquare,N256,78,LaplacianOperator,GPUExecutor,1457420.0,NeoN,with Allocation,0.2700566754950529 +2DSquare,N256,79,LaplacianOperator,GPUExecutor,115485.0,NeoN,No allocation,3.408113607827856 +2DSquare,N32,45,LaplacianOperator,OpenFOAM,5062.54,OpenFOAM,with Allocation,1.0 +2DSquare,N32,46,LaplacianOperator,SerialExecutor,53655.8,NeoN,with Allocation,0.09435214832320084 +2DSquare,N32,47,LaplacianOperator,SerialExecutor,27471.9,NeoN,No allocation,0.18428066497038792 +2DSquare,N32,48,LaplacianOperator,GPUExecutor,1294520.0,NeoN,with Allocation,0.003910746840527763 +2DSquare,N32,49,LaplacianOperator,GPUExecutor,40718.3,NeoN,No allocation,0.12433082913579396 +2DSquare,N512,105,LaplacianOperator,OpenFOAM,1708970.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,106,LaplacianOperator,SerialExecutor,9308070.0,NeoN,with Allocation,0.1836008968561689 +2DSquare,N512,107,LaplacianOperator,SerialExecutor,6922610.0,NeoN,No allocation,0.24686787208870642 +2DSquare,N512,108,LaplacianOperator,GPUExecutor,1700920.0,NeoN,with Allocation,1.0047327328739741 +2DSquare,N512,109,LaplacianOperator,GPUExecutor,154293.0,NeoN,No allocation,11.076134367728931 +2DSquare,N64,85,LaplacianOperator,OpenFOAM,15835.8,OpenFOAM,with Allocation,1.0 +2DSquare,N64,86,LaplacianOperator,SerialExecutor,141167.0,NeoN,with Allocation,0.1121777752590903 +2DSquare,N64,87,LaplacianOperator,SerialExecutor,105787.0,NeoN,No allocation,0.14969514212521387 +2DSquare,N64,88,LaplacianOperator,GPUExecutor,1278330.0,NeoN,with Allocation,0.012387881063575133 +2DSquare,N64,89,LaplacianOperator,GPUExecutor,41478.9,NeoN,No allocation,0.381779651822975 +2DSquare,N8,15,LaplacianOperator,OpenFOAM,1829.06,OpenFOAM,with Allocation,1.0 +2DSquare,N8,16,LaplacianOperator,SerialExecutor,23888.7,NeoN,with Allocation,0.07656590773043322 +2DSquare,N8,17,LaplacianOperator,SerialExecutor,2451.44,NeoN,No allocation,0.7461165682211272 +2DSquare,N8,18,LaplacianOperator,GPUExecutor,1200300.0,NeoN,with Allocation,0.0015238357077397317 +2DSquare,N8,19,LaplacianOperator,GPUExecutor,30735.0,NeoN,No allocation,0.05951065560435985 +3DCube,N128,55,LaplacianOperator,OpenFOAM,35105100.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,56,LaplacianOperator,SerialExecutor,164234000.0,NeoN,with Allocation,0.21375050233203843 +3DCube,N128,57,LaplacianOperator,SerialExecutor,92129400.0,NeoN,No allocation,0.3810412311379429 +3DCube,N128,58,LaplacianOperator,GPUExecutor,3678180.0,NeoN,with Allocation,9.544149552224198 +3DCube,N128,59,LaplacianOperator,GPUExecutor,1438160.0,NeoN,No allocation,24.409731879623966 +3DCube,N16,25,LaplacianOperator,OpenFOAM,25181.4,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,LaplacianOperator,SerialExecutor,205118.0,NeoN,with Allocation,0.12276543258027088 +3DCube,N16,27,LaplacianOperator,SerialExecutor,161947.0,NeoN,No allocation,0.15549161145312973 +3DCube,N16,28,LaplacianOperator,GPUExecutor,1342270.0,NeoN,with Allocation,0.018760309028734906 +3DCube,N16,29,LaplacianOperator,GPUExecutor,47410.5,NeoN,No allocation,0.5311355079570982 +3DCube,N32,65,LaplacianOperator,OpenFOAM,300867.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,LaplacianOperator,SerialExecutor,1711460.0,NeoN,with Allocation,0.17579551961483178 +3DCube,N32,67,LaplacianOperator,SerialExecutor,1310420.0,NeoN,No allocation,0.22959585476412142 +3DCube,N32,68,LaplacianOperator,GPUExecutor,1336890.0,NeoN,with Allocation,0.22504992931355608 +3DCube,N32,69,LaplacianOperator,GPUExecutor,71187.6,NeoN,No allocation,4.226396170119515 +3DCube,N64,115,LaplacianOperator,OpenFOAM,2486090.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,116,LaplacianOperator,SerialExecutor,14610500.0,NeoN,with Allocation,0.17015776325245544 +3DCube,N64,117,LaplacianOperator,SerialExecutor,10357400.0,NeoN,No allocation,0.24003031648869408 +3DCube,N64,118,LaplacianOperator,GPUExecutor,1827960.0,NeoN,with Allocation,1.3600352305302086 +3DCube,N64,119,LaplacianOperator,GPUExecutor,230026.0,NeoN,No allocation,10.8078651978472 +3DCube,N8,35,LaplacianOperator,OpenFOAM,5363.15,OpenFOAM,with Allocation,1.0 +3DCube,N8,36,LaplacianOperator,SerialExecutor,48363.6,NeoN,with Allocation,0.11089228262577641 +3DCube,N8,37,LaplacianOperator,SerialExecutor,21833.0,NeoN,No allocation,0.24564420830852376 +3DCube,N8,38,LaplacianOperator,GPUExecutor,1256270.0,NeoN,with Allocation,0.004269106163483964 +3DCube,N8,39,LaplacianOperator,GPUExecutor,43583.8,NeoN,No allocation,0.12305374932887907 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/advection-diffusion-equation_scalar.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/advection-diffusion-equation_scalar.csv new file mode 100644 index 0000000..d23cf92 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/develop/advection-diffusion-equation_scalar.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,36,advection-diffusion-equation_scalar,OpenFOAM,204516.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N128,37,advection-diffusion-equation_scalar,OpenFOAM,261059.0,OpenFOAM,implicit-time-integration,0.7834091144147491 +2DSquare,N128,38,advection-diffusion-equation_scalar,SerialExecutor,253934.0,NeoN,explicit-time-integration,0.8053903770271015 +2DSquare,N128,39,advection-diffusion-equation_scalar,SerialExecutor,1114900.0,NeoN,implicit-time-integration,0.18343887344156426 +2DSquare,N16,0,advection-diffusion-equation_scalar,OpenFOAM,8623.92,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,advection-diffusion-equation_scalar,OpenFOAM,7951.97,OpenFOAM,implicit-time-integration,1.0845010733189386 +2DSquare,N16,2,advection-diffusion-equation_scalar,SerialExecutor,42519.4,NeoN,explicit-time-integration,0.20282318188873785 +2DSquare,N16,3,advection-diffusion-equation_scalar,SerialExecutor,68602.6,NeoN,implicit-time-integration,0.12570835507692127 +2DSquare,N256,28,advection-diffusion-equation_scalar,OpenFOAM,1777700.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,29,advection-diffusion-equation_scalar,OpenFOAM,2611550.0,OpenFOAM,implicit-time-integration,0.680706859910781 +2DSquare,N256,30,advection-diffusion-equation_scalar,SerialExecutor,1099160.0,NeoN,explicit-time-integration,1.6173259580042942 +2DSquare,N256,31,advection-diffusion-equation_scalar,SerialExecutor,4589230.0,NeoN,implicit-time-integration,0.3873634574863321 +2DSquare,N32,16,advection-diffusion-equation_scalar,OpenFOAM,18032.6,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N32,17,advection-diffusion-equation_scalar,OpenFOAM,16084.5,OpenFOAM,implicit-time-integration,1.1211166029407191 +2DSquare,N32,18,advection-diffusion-equation_scalar,SerialExecutor,48668.2,NeoN,explicit-time-integration,0.3705212027566255 +2DSquare,N32,19,advection-diffusion-equation_scalar,SerialExecutor,115609.0,NeoN,implicit-time-integration,0.15597920577117697 +2DSquare,N512,40,advection-diffusion-equation_scalar,OpenFOAM,10071900.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N512,41,advection-diffusion-equation_scalar,OpenFOAM,8015610.0,OpenFOAM,implicit-time-integration,1.256535684745141 +2DSquare,N512,42,advection-diffusion-equation_scalar,SerialExecutor,5486080.0,NeoN,explicit-time-integration,1.8359010440970602 +2DSquare,N512,43,advection-diffusion-equation_scalar,SerialExecutor,20687800.0,NeoN,implicit-time-integration,0.4868521544098454 +2DSquare,N64,32,advection-diffusion-equation_scalar,OpenFOAM,52448.9,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,33,advection-diffusion-equation_scalar,OpenFOAM,56405.4,OpenFOAM,implicit-time-integration,0.9298560066943945 +2DSquare,N64,34,advection-diffusion-equation_scalar,SerialExecutor,69311.1,NeoN,explicit-time-integration,0.7567171780566172 +2DSquare,N64,35,advection-diffusion-equation_scalar,SerialExecutor,295930.0,NeoN,implicit-time-integration,0.1772341432095428 +2DSquare,N8,4,advection-diffusion-equation_scalar,OpenFOAM,6448.5,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N8,5,advection-diffusion-equation_scalar,OpenFOAM,4649.68,OpenFOAM,implicit-time-integration,1.3868696340393316 +2DSquare,N8,6,advection-diffusion-equation_scalar,SerialExecutor,41351.7,NeoN,explicit-time-integration,0.1559428028351918 +2DSquare,N8,7,advection-diffusion-equation_scalar,SerialExecutor,57301.0,NeoN,implicit-time-integration,0.112537303013909 +3DCube,N128,20,advection-diffusion-equation_scalar,OpenFOAM,82804500.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N128,21,advection-diffusion-equation_scalar,OpenFOAM,155965000.0,OpenFOAM,implicit-time-integration,0.530917192959959 +3DCube,N128,22,advection-diffusion-equation_scalar,SerialExecutor,126471000.0,NeoN,explicit-time-integration,0.6547311241312238 +3DCube,N128,23,advection-diffusion-equation_scalar,SerialExecutor,310412000.0,NeoN,implicit-time-integration,0.26675676198085124 +3DCube,N16,8,advection-diffusion-equation_scalar,OpenFOAM,67483.5,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,9,advection-diffusion-equation_scalar,OpenFOAM,77894.9,OpenFOAM,implicit-time-integration,0.8663404150977793 +3DCube,N16,10,advection-diffusion-equation_scalar,SerialExecutor,78907.0,NeoN,explicit-time-integration,0.8552283067408468 +3DCube,N16,11,advection-diffusion-equation_scalar,SerialExecutor,427625.0,NeoN,implicit-time-integration,0.1578099970768781 +3DCube,N32,24,advection-diffusion-equation_scalar,OpenFOAM,681146.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,25,advection-diffusion-equation_scalar,OpenFOAM,936147.0,OpenFOAM,implicit-time-integration,0.7276058140441619 +3DCube,N32,26,advection-diffusion-equation_scalar,SerialExecutor,753754.0,NeoN,explicit-time-integration,0.9036714896372026 +3DCube,N32,27,advection-diffusion-equation_scalar,SerialExecutor,3433330.0,NeoN,implicit-time-integration,0.19839223144876839 +3DCube,N64,44,advection-diffusion-equation_scalar,OpenFOAM,9711490.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,45,advection-diffusion-equation_scalar,OpenFOAM,12223900.0,OpenFOAM,implicit-time-integration,0.7944673958392984 +3DCube,N64,46,advection-diffusion-equation_scalar,SerialExecutor,8629520.0,NeoN,explicit-time-integration,1.1253800906655296 +3DCube,N64,47,advection-diffusion-equation_scalar,SerialExecutor,30669300.0,NeoN,implicit-time-integration,0.31665183098407856 +3DCube,N8,12,advection-diffusion-equation_scalar,OpenFOAM,16369.9,OpenFOAM,explicit-time-integration,1.0 +3DCube,N8,13,advection-diffusion-equation_scalar,OpenFOAM,15023.6,OpenFOAM,implicit-time-integration,1.0896123432466251 +3DCube,N8,14,advection-diffusion-equation_scalar,SerialExecutor,48731.2,NeoN,explicit-time-integration,0.33592236595856456 +3DCube,N8,15,advection-diffusion-equation_scalar,SerialExecutor,104603.0,NeoN,implicit-time-integration,0.1564955116010057 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/system-info.log b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/DivOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/DivOperator.csv new file mode 100644 index 0000000..8e8a13e --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/DivOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,40,DivOperator,OpenFOAM,115227.0,OpenFOAM,with Allocation,1.0 +2DSquare,N128,41,DivOperator,SerialExecutor,1167160.0,NeoN,with Allocation,0.09872425374413105 +2DSquare,N128,42,DivOperator,SerialExecutor,654757.0,NeoN,No allocation,0.17598437282839283 +2DSquare,N128,43,DivOperator,GPUExecutor,906853.0,NeoN,with Allocation,0.12706248973097073 +2DSquare,N128,44,DivOperator,GPUExecutor,294318.0,NeoN,No allocation,0.39150510672130145 +2DSquare,N16,10,DivOperator,OpenFOAM,2088.64,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,DivOperator,SerialExecutor,77374.1,NeoN,with Allocation,0.026994045811195216 +2DSquare,N16,12,DivOperator,SerialExecutor,33894.8,NeoN,No allocation,0.0616212516374193 +2DSquare,N16,13,DivOperator,GPUExecutor,909401.0,NeoN,with Allocation,0.002296720588607226 +2DSquare,N16,14,DivOperator,GPUExecutor,288724.0,NeoN,No allocation,0.007234036657846247 +2DSquare,N256,90,DivOperator,OpenFOAM,454645.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,DivOperator,SerialExecutor,3097920.0,NeoN,with Allocation,0.1467581474021279 +2DSquare,N256,92,DivOperator,SerialExecutor,2555700.0,NeoN,No allocation,0.1778945103102868 +2DSquare,N256,93,DivOperator,GPUExecutor,915080.0,NeoN,with Allocation,0.4968363421777331 +2DSquare,N256,94,DivOperator,GPUExecutor,302536.0,NeoN,No allocation,1.5027798344659808 +2DSquare,N32,60,DivOperator,OpenFOAM,5084.58,OpenFOAM,with Allocation,1.0 +2DSquare,N32,61,DivOperator,SerialExecutor,111466.0,NeoN,with Allocation,0.045615524016291965 +2DSquare,N32,62,DivOperator,SerialExecutor,64737.0,NeoN,No allocation,0.07854210111682654 +2DSquare,N32,63,DivOperator,GPUExecutor,924299.0,NeoN,with Allocation,0.005501012118372951 +2DSquare,N32,64,DivOperator,GPUExecutor,291821.0,NeoN,No allocation,0.017423626126975098 +2DSquare,N512,100,DivOperator,OpenFOAM,2099040.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,101,DivOperator,SerialExecutor,12257100.0,NeoN,with Allocation,0.1712509484298896 +2DSquare,N512,102,DivOperator,SerialExecutor,10177500.0,NeoN,No allocation,0.20624318349299928 +2DSquare,N512,103,DivOperator,GPUExecutor,1068650.0,NeoN,with Allocation,1.9641978196790344 +2DSquare,N512,104,DivOperator,GPUExecutor,331506.0,NeoN,No allocation,6.331831098079673 +2DSquare,N64,110,DivOperator,OpenFOAM,20394.3,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,DivOperator,SerialExecutor,240404.0,NeoN,with Allocation,0.08483344703083143 +2DSquare,N64,112,DivOperator,SerialExecutor,181845.0,NeoN,No allocation,0.11215210756413428 +2DSquare,N64,113,DivOperator,GPUExecutor,926836.0,NeoN,with Allocation,0.022004216495690714 +2DSquare,N64,114,DivOperator,GPUExecutor,298592.0,NeoN,No allocation,0.06830156199764227 +2DSquare,N8,20,DivOperator,OpenFOAM,1097.51,OpenFOAM,with Allocation,1.0 +2DSquare,N8,21,DivOperator,SerialExecutor,69550.0,NeoN,with Allocation,0.01578015815959741 +2DSquare,N8,22,DivOperator,SerialExecutor,26797.1,NeoN,No allocation,0.040956297509805166 +2DSquare,N8,23,DivOperator,GPUExecutor,898170.0,NeoN,with Allocation,0.001221940167228921 +2DSquare,N8,24,DivOperator,GPUExecutor,289593.0,NeoN,No allocation,0.003789836080291996 +3DCube,N128,70,DivOperator,OpenFOAM,62447800.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,71,DivOperator,SerialExecutor,222009000.0,NeoN,with Allocation,0.2812849929507362 +3DCube,N128,72,DivOperator,SerialExecutor,136098000.0,NeoN,No allocation,0.4588443621508031 +3DCube,N128,73,DivOperator,GPUExecutor,2699280.0,NeoN,with Allocation,23.13498414391986 +3DCube,N128,74,DivOperator,GPUExecutor,979770.0,NeoN,No allocation,63.737203629423234 +3DCube,N16,80,DivOperator,OpenFOAM,29557.4,OpenFOAM,with Allocation,1.0 +3DCube,N16,81,DivOperator,SerialExecutor,334604.0,NeoN,with Allocation,0.08833546520663232 +3DCube,N16,82,DivOperator,SerialExecutor,264271.0,NeoN,No allocation,0.11184503785886458 +3DCube,N16,83,DivOperator,GPUExecutor,922486.0,NeoN,with Allocation,0.0320410282649276 +3DCube,N16,84,DivOperator,GPUExecutor,298584.0,NeoN,No allocation,0.0989919084746671 +3DCube,N32,50,DivOperator,OpenFOAM,296327.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,2317640.0,NeoN,with Allocation,0.12785721682401063 +3DCube,N32,52,DivOperator,SerialExecutor,1946570.0,NeoN,No allocation,0.15223033335559472 +3DCube,N32,53,DivOperator,GPUExecutor,927841.0,NeoN,with Allocation,0.3193726080222797 +3DCube,N32,54,DivOperator,GPUExecutor,310701.0,NeoN,No allocation,0.9537368724271889 +3DCube,N64,0,DivOperator,OpenFOAM,3980090.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,1,DivOperator,SerialExecutor,20074000.0,NeoN,with Allocation,0.19827089767858921 +3DCube,N64,2,DivOperator,SerialExecutor,15373000.0,NeoN,No allocation,0.25890132049697523 +3DCube,N64,3,DivOperator,GPUExecutor,1036860.0,NeoN,with Allocation,3.8385992322975135 +3DCube,N64,4,DivOperator,GPUExecutor,371120.0,NeoN,No allocation,10.724536538046992 +3DCube,N8,30,DivOperator,OpenFOAM,6361.21,OpenFOAM,with Allocation,1.0 +3DCube,N8,31,DivOperator,SerialExecutor,148020.0,NeoN,with Allocation,0.04297534117011215 +3DCube,N8,32,DivOperator,SerialExecutor,56574.6,NeoN,No allocation,0.1124393278962644 +3DCube,N8,33,DivOperator,GPUExecutor,1016960.0,NeoN,with Allocation,0.006255123112020138 +3DCube,N8,34,DivOperator,GPUExecutor,291730.0,NeoN,No allocation,0.0218051280293422 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/LaplacianOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/LaplacianOperator.csv new file mode 100644 index 0000000..67aa0be --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/LaplacianOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,45,LaplacianOperator,OpenFOAM,62312.7,OpenFOAM,with Allocation,1.0 +2DSquare,N128,46,LaplacianOperator,SerialExecutor,744241.0,NeoN,with Allocation,0.08372650794567889 +2DSquare,N128,47,LaplacianOperator,SerialExecutor,583461.0,NeoN,No allocation,0.10679839783635924 +2DSquare,N128,48,LaplacianOperator,GPUExecutor,620837.0,NeoN,with Allocation,0.10036885688191909 +2DSquare,N128,49,LaplacianOperator,GPUExecutor,20021.2,NeoN,No allocation,3.112335923920644 +2DSquare,N16,15,LaplacianOperator,OpenFOAM,2590.49,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,LaplacianOperator,SerialExecutor,60156.7,NeoN,with Allocation,0.04306236878020237 +2DSquare,N16,17,LaplacianOperator,SerialExecutor,10635.6,NeoN,No allocation,0.243567828801384 +2DSquare,N16,18,LaplacianOperator,GPUExecutor,612768.0,NeoN,with Allocation,0.004227521672149981 +2DSquare,N16,19,LaplacianOperator,GPUExecutor,18365.5,NeoN,No allocation,0.14105197244834064 +2DSquare,N256,95,LaplacianOperator,OpenFOAM,364481.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,LaplacianOperator,SerialExecutor,2849770.0,NeoN,with Allocation,0.12789839180004 +2DSquare,N256,97,LaplacianOperator,SerialExecutor,2328080.0,NeoN,No allocation,0.15655862341500293 +2DSquare,N256,98,LaplacianOperator,GPUExecutor,628810.0,NeoN,with Allocation,0.5796361381021294 +2DSquare,N256,99,LaplacianOperator,GPUExecutor,25299.2,NeoN,No allocation,14.406819187958511 +2DSquare,N32,65,LaplacianOperator,OpenFOAM,4923.41,OpenFOAM,with Allocation,1.0 +2DSquare,N32,66,LaplacianOperator,SerialExecutor,91730.6,NeoN,with Allocation,0.053672493148415025 +2DSquare,N32,67,LaplacianOperator,SerialExecutor,38110.3,NeoN,No allocation,0.12918843462266105 +2DSquare,N32,68,LaplacianOperator,GPUExecutor,631362.0,NeoN,with Allocation,0.007798077806393163 +2DSquare,N32,69,LaplacianOperator,GPUExecutor,18832.8,NeoN,No allocation,0.26142740325389746 +2DSquare,N512,105,LaplacianOperator,OpenFOAM,1538310.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,106,LaplacianOperator,SerialExecutor,11455000.0,NeoN,with Allocation,0.13429157573112177 +2DSquare,N512,107,LaplacianOperator,SerialExecutor,9331860.0,NeoN,No allocation,0.16484495052433276 +2DSquare,N512,108,LaplacianOperator,GPUExecutor,768279.0,NeoN,with Allocation,2.002280421565603 +2DSquare,N512,109,LaplacianOperator,GPUExecutor,48415.5,NeoN,No allocation,31.77308919664157 +2DSquare,N64,115,LaplacianOperator,OpenFOAM,15414.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,LaplacianOperator,SerialExecutor,210497.0,NeoN,with Allocation,0.07322764694983777 +2DSquare,N64,117,LaplacianOperator,SerialExecutor,146490.0,NeoN,No allocation,0.105223564748447 +2DSquare,N64,118,LaplacianOperator,GPUExecutor,635244.0,NeoN,with Allocation,0.024265006832020455 +2DSquare,N64,119,LaplacianOperator,GPUExecutor,19006.0,NeoN,No allocation,0.8110175733978744 +2DSquare,N8,25,LaplacianOperator,OpenFOAM,1744.76,OpenFOAM,with Allocation,1.0 +2DSquare,N8,26,LaplacianOperator,SerialExecutor,52778.9,NeoN,with Allocation,0.03305790761080659 +2DSquare,N8,27,LaplacianOperator,SerialExecutor,3776.86,NeoN,No allocation,0.4619604645128493 +2DSquare,N8,28,LaplacianOperator,GPUExecutor,607391.0,NeoN,with Allocation,0.002872548325543184 +2DSquare,N8,29,LaplacianOperator,GPUExecutor,18196.7,NeoN,No allocation,0.0958833195029868 +3DCube,N128,75,LaplacianOperator,OpenFOAM,45147100.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,76,LaplacianOperator,SerialExecutor,197311000.0,NeoN,with Allocation,0.22881187566836111 +3DCube,N128,77,LaplacianOperator,SerialExecutor,116042000.0,NeoN,No allocation,0.38905827200496373 +3DCube,N128,78,LaplacianOperator,GPUExecutor,2257780.0,NeoN,with Allocation,19.996235239925944 +3DCube,N128,79,LaplacianOperator,GPUExecutor,428002.0,NeoN,No allocation,105.48338559165612 +3DCube,N16,85,LaplacianOperator,OpenFOAM,24492.1,OpenFOAM,with Allocation,1.0 +3DCube,N16,86,LaplacianOperator,SerialExecutor,287013.0,NeoN,with Allocation,0.08533446220206053 +3DCube,N16,87,LaplacianOperator,SerialExecutor,216272.0,NeoN,No allocation,0.11324674483983131 +3DCube,N16,88,LaplacianOperator,GPUExecutor,627317.0,NeoN,with Allocation,0.03904262119470698 +3DCube,N16,89,LaplacianOperator,GPUExecutor,19392.9,NeoN,No allocation,1.2629415920259475 +3DCube,N32,55,LaplacianOperator,OpenFOAM,283120.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,2095820.0,NeoN,with Allocation,0.13508793694114954 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1715430.0,NeoN,No allocation,0.16504316701934793 +3DCube,N32,58,LaplacianOperator,GPUExecutor,638333.0,NeoN,with Allocation,0.44353025771815024 +3DCube,N32,59,LaplacianOperator,GPUExecutor,23123.2,NeoN,No allocation,12.243980071962358 +3DCube,N64,5,LaplacianOperator,OpenFOAM,2481160.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,6,LaplacianOperator,SerialExecutor,17667800.0,NeoN,with Allocation,0.14043400989370494 +3DCube,N64,7,LaplacianOperator,SerialExecutor,13674700.0,NeoN,No allocation,0.1814416404016176 +3DCube,N64,8,LaplacianOperator,GPUExecutor,741564.0,NeoN,with Allocation,3.345847425171664 +3DCube,N64,9,LaplacianOperator,GPUExecutor,68750.6,NeoN,No allocation,36.08928503896693 +3DCube,N8,35,LaplacianOperator,OpenFOAM,5203.52,OpenFOAM,with Allocation,1.0 +3DCube,N8,36,LaplacianOperator,SerialExecutor,83574.4,NeoN,with Allocation,0.062262128115786665 +3DCube,N8,37,LaplacianOperator,SerialExecutor,28987.2,NeoN,No allocation,0.1795109565601369 +3DCube,N8,38,LaplacianOperator,GPUExecutor,2632680.0,NeoN,with Allocation,0.0019765106279532644 +3DCube,N8,39,LaplacianOperator,GPUExecutor,19516.7,NeoN,No allocation,0.2666188443743051 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/advection-diffusion-equation_scalar.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/advection-diffusion-equation_scalar.csv new file mode 100644 index 0000000..fb13b15 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/advection-diffusion-equation_scalar.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,16,advection-diffusion-equation_scalar,OpenFOAM,194261.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N128,17,advection-diffusion-equation_scalar,OpenFOAM,259831.0,OpenFOAM,implicit-time-integration,0.747643660687139 +2DSquare,N128,18,advection-diffusion-equation_scalar,SerialExecutor,348010.0,NeoN,explicit-time-integration,0.5582052239878165 +2DSquare,N128,19,advection-diffusion-equation_scalar,SerialExecutor,1300140.0,NeoN,implicit-time-integration,0.14941544756718508 +2DSquare,N16,4,advection-diffusion-equation_scalar,OpenFOAM,8623.94,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,5,advection-diffusion-equation_scalar,OpenFOAM,8304.0,OpenFOAM,implicit-time-integration,1.0385284200385356 +2DSquare,N16,6,advection-diffusion-equation_scalar,SerialExecutor,70841.4,NeoN,explicit-time-integration,0.12173587760829122 +2DSquare,N16,7,advection-diffusion-equation_scalar,SerialExecutor,108733.0,NeoN,implicit-time-integration,0.07931299605455566 +2DSquare,N256,36,advection-diffusion-equation_scalar,OpenFOAM,914045.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,37,advection-diffusion-equation_scalar,OpenFOAM,1344470.0,OpenFOAM,implicit-time-integration,0.6798552589496233 +2DSquare,N256,38,advection-diffusion-equation_scalar,SerialExecutor,1323830.0,NeoN,explicit-time-integration,0.6904549677828724 +2DSquare,N256,39,advection-diffusion-equation_scalar,SerialExecutor,5034100.0,NeoN,implicit-time-integration,0.18157068790846428 +2DSquare,N32,24,advection-diffusion-equation_scalar,OpenFOAM,16601.1,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N32,25,advection-diffusion-equation_scalar,OpenFOAM,16698.8,OpenFOAM,implicit-time-integration,0.9941492801877979 +2DSquare,N32,26,advection-diffusion-equation_scalar,SerialExecutor,122530.0,NeoN,explicit-time-integration,0.13548600342773198 +2DSquare,N32,27,advection-diffusion-equation_scalar,SerialExecutor,238239.0,NeoN,implicit-time-integration,0.06968254567891906 +2DSquare,N512,40,advection-diffusion-equation_scalar,OpenFOAM,4102720.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N512,41,advection-diffusion-equation_scalar,OpenFOAM,7414700.0,OpenFOAM,implicit-time-integration,0.5533224540439937 +2DSquare,N512,42,advection-diffusion-equation_scalar,SerialExecutor,9084920.0,NeoN,explicit-time-integration,0.4515967119138088 +2DSquare,N512,43,advection-diffusion-equation_scalar,SerialExecutor,20493400.0,NeoN,implicit-time-integration,0.2001971366391131 +2DSquare,N64,44,advection-diffusion-equation_scalar,OpenFOAM,50042.8,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,45,advection-diffusion-equation_scalar,OpenFOAM,55037.4,OpenFOAM,implicit-time-integration,0.9092508003648428 +2DSquare,N64,46,advection-diffusion-equation_scalar,SerialExecutor,120802.0,NeoN,explicit-time-integration,0.41425473088193904 +2DSquare,N64,47,advection-diffusion-equation_scalar,SerialExecutor,373949.0,NeoN,implicit-time-integration,0.13382252660122104 +2DSquare,N8,8,advection-diffusion-equation_scalar,OpenFOAM,8727.04,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N8,9,advection-diffusion-equation_scalar,OpenFOAM,7264.02,OpenFOAM,implicit-time-integration,1.2014063837929962 +2DSquare,N8,10,advection-diffusion-equation_scalar,SerialExecutor,101966.0,NeoN,explicit-time-integration,0.08558774493458604 +2DSquare,N8,11,advection-diffusion-equation_scalar,SerialExecutor,140671.0,NeoN,implicit-time-integration,0.062038657576899296 +3DCube,N128,28,advection-diffusion-equation_scalar,OpenFOAM,90236800.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N128,29,advection-diffusion-equation_scalar,OpenFOAM,166314000.0,OpenFOAM,implicit-time-integration,0.542568875741068 +3DCube,N128,30,advection-diffusion-equation_scalar,SerialExecutor,154211000.0,NeoN,explicit-time-integration,0.5851515131864783 +3DCube,N128,31,advection-diffusion-equation_scalar,SerialExecutor,351552000.0,NeoN,implicit-time-integration,0.25668123065720005 +3DCube,N16,32,advection-diffusion-equation_scalar,OpenFOAM,69672.8,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,33,advection-diffusion-equation_scalar,OpenFOAM,78629.8,OpenFOAM,implicit-time-integration,0.8860864455969619 +3DCube,N16,34,advection-diffusion-equation_scalar,SerialExecutor,138045.0,NeoN,explicit-time-integration,0.5047107827157811 +3DCube,N16,35,advection-diffusion-equation_scalar,SerialExecutor,524718.0,NeoN,implicit-time-integration,0.132781417828243 +3DCube,N32,20,advection-diffusion-equation_scalar,OpenFOAM,614339.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,21,advection-diffusion-equation_scalar,OpenFOAM,887384.0,OpenFOAM,implicit-time-integration,0.6923034447319312 +3DCube,N32,22,advection-diffusion-equation_scalar,SerialExecutor,905708.0,NeoN,explicit-time-integration,0.6782969787172024 +3DCube,N32,23,advection-diffusion-equation_scalar,SerialExecutor,3804930.0,NeoN,implicit-time-integration,0.16145868649357545 +3DCube,N64,0,advection-diffusion-equation_scalar,OpenFOAM,6886080.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,1,advection-diffusion-equation_scalar,OpenFOAM,20153100.0,OpenFOAM,implicit-time-integration,0.3416883754856573 +3DCube,N64,2,advection-diffusion-equation_scalar,SerialExecutor,9028790.0,NeoN,explicit-time-integration,0.7626802705567413 +3DCube,N64,3,advection-diffusion-equation_scalar,SerialExecutor,33705100.0,NeoN,implicit-time-integration,0.20430379972170384 +3DCube,N8,12,advection-diffusion-equation_scalar,OpenFOAM,22117.4,OpenFOAM,explicit-time-integration,1.0 +3DCube,N8,13,advection-diffusion-equation_scalar,OpenFOAM,21761.4,OpenFOAM,implicit-time-integration,1.0163592415929121 +3DCube,N8,14,advection-diffusion-equation_scalar,SerialExecutor,116752.0,NeoN,explicit-time-integration,0.18943915307660683 +3DCube,N8,15,advection-diffusion-equation_scalar,SerialExecutor,219694.0,NeoN,implicit-time-integration,0.10067366427849646 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/DivOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/DivOperator.csv new file mode 100644 index 0000000..bab8c87 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/DivOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,40,DivOperator,OpenFOAM,79481.1,OpenFOAM,with Allocation,1.0 +2DSquare,N128,41,DivOperator,SerialExecutor,807814.0,NeoN,with Allocation,0.09839034728291414 +2DSquare,N128,42,DivOperator,SerialExecutor,655415.0,NeoN,No allocation,0.12126835669003609 +2DSquare,N128,43,DivOperator,GPUExecutor,908496.0,NeoN,with Allocation,0.08748646114017013 +2DSquare,N128,44,DivOperator,GPUExecutor,296662.0,NeoN,No allocation,0.26791803466571384 +2DSquare,N16,10,DivOperator,OpenFOAM,2119.64,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,DivOperator,SerialExecutor,77455.0,NeoN,with Allocation,0.027366083532373634 +2DSquare,N16,12,DivOperator,SerialExecutor,33473.0,NeoN,No allocation,0.06332387297224629 +2DSquare,N16,13,DivOperator,GPUExecutor,911724.0,NeoN,with Allocation,0.002324870245820007 +2DSquare,N16,14,DivOperator,GPUExecutor,288220.0,NeoN,No allocation,0.007354243286378461 +2DSquare,N256,90,DivOperator,OpenFOAM,458767.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,DivOperator,SerialExecutor,3103910.0,NeoN,with Allocation,0.1478029324303862 +2DSquare,N256,92,DivOperator,SerialExecutor,2581700.0,NeoN,No allocation,0.17769957779757525 +2DSquare,N256,93,DivOperator,GPUExecutor,937785.0,NeoN,with Allocation,0.4892027490309613 +2DSquare,N256,94,DivOperator,GPUExecutor,307254.0,NeoN,No allocation,1.4931196990112414 +2DSquare,N32,60,DivOperator,OpenFOAM,5044.17,OpenFOAM,with Allocation,1.0 +2DSquare,N32,61,DivOperator,SerialExecutor,111903.0,NeoN,with Allocation,0.04507627141363502 +2DSquare,N32,62,DivOperator,SerialExecutor,64474.2,NeoN,No allocation,0.07823548023860707 +2DSquare,N32,63,DivOperator,GPUExecutor,925981.0,NeoN,with Allocation,0.005447379589861995 +2DSquare,N32,64,DivOperator,GPUExecutor,293290.0,NeoN,No allocation,0.017198574789457535 +2DSquare,N512,100,DivOperator,OpenFOAM,2117330.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,101,DivOperator,SerialExecutor,12278800.0,NeoN,with Allocation,0.17243786037723555 +2DSquare,N512,102,DivOperator,SerialExecutor,10149800.0,NeoN,No allocation,0.2086080513901752 +2DSquare,N512,103,DivOperator,GPUExecutor,1069770.0,NeoN,with Allocation,1.9792385279078681 +2DSquare,N512,104,DivOperator,GPUExecutor,332312.0,NeoN,No allocation,6.371512313729267 +2DSquare,N64,110,DivOperator,OpenFOAM,21529.8,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,DivOperator,SerialExecutor,237329.0,NeoN,with Allocation,0.0907171057898529 +2DSquare,N64,112,DivOperator,SerialExecutor,182021.0,NeoN,No allocation,0.11828195647754929 +2DSquare,N64,113,DivOperator,GPUExecutor,923606.0,NeoN,with Allocation,0.023310589147320395 +2DSquare,N64,114,DivOperator,GPUExecutor,297903.0,NeoN,No allocation,0.07227117551686287 +2DSquare,N8,20,DivOperator,OpenFOAM,1130.43,OpenFOAM,with Allocation,1.0 +2DSquare,N8,21,DivOperator,SerialExecutor,69067.7,NeoN,with Allocation,0.016366984856886795 +2DSquare,N8,22,DivOperator,SerialExecutor,26699.0,NeoN,No allocation,0.04233978800704147 +2DSquare,N8,23,DivOperator,GPUExecutor,900676.0,NeoN,with Allocation,0.0012550906208225823 +2DSquare,N8,24,DivOperator,GPUExecutor,290654.0,NeoN,No allocation,0.0038892635229516885 +3DCube,N128,70,DivOperator,OpenFOAM,62981600.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,71,DivOperator,SerialExecutor,219861000.0,NeoN,with Allocation,0.2864609912626614 +3DCube,N128,72,DivOperator,SerialExecutor,136486000.0,NeoN,No allocation,0.4614509913104641 +3DCube,N128,73,DivOperator,GPUExecutor,2709260.0,NeoN,with Allocation,23.246790636557584 +3DCube,N128,74,DivOperator,GPUExecutor,981582.0,NeoN,No allocation,64.16336077882438 +3DCube,N16,80,DivOperator,OpenFOAM,30758.4,OpenFOAM,with Allocation,1.0 +3DCube,N16,81,DivOperator,SerialExecutor,330004.0,NeoN,with Allocation,0.09320614295584297 +3DCube,N16,82,DivOperator,SerialExecutor,263997.0,NeoN,No allocation,0.11651041489107831 +3DCube,N16,83,DivOperator,GPUExecutor,921118.0,NeoN,with Allocation,0.033392464374814086 +3DCube,N16,84,DivOperator,GPUExecutor,298595.0,NeoN,No allocation,0.10301043219076006 +3DCube,N32,50,DivOperator,OpenFOAM,307185.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,2334380.0,NeoN,with Allocation,0.13159168601513035 +3DCube,N32,52,DivOperator,SerialExecutor,1947820.0,NeoN,No allocation,0.15770707765604625 +3DCube,N32,53,DivOperator,GPUExecutor,957264.0,NeoN,with Allocation,0.32089893697036553 +3DCube,N32,54,DivOperator,GPUExecutor,317639.0,NeoN,No allocation,0.9670884242803938 +3DCube,N64,0,DivOperator,OpenFOAM,3089230.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,1,DivOperator,SerialExecutor,18606200.0,NeoN,with Allocation,0.16603229031183153 +3DCube,N64,2,DivOperator,SerialExecutor,15037100.0,NeoN,No allocation,0.20544054372186127 +3DCube,N64,3,DivOperator,GPUExecutor,1035800.0,NeoN,with Allocation,2.9824580034755743 +3DCube,N64,4,DivOperator,GPUExecutor,372129.0,NeoN,No allocation,8.301502973431257 +3DCube,N8,30,DivOperator,OpenFOAM,4328.18,OpenFOAM,with Allocation,1.0 +3DCube,N8,31,DivOperator,SerialExecutor,101899.0,NeoN,with Allocation,0.04247519602743894 +3DCube,N8,32,DivOperator,SerialExecutor,56989.3,NeoN,No allocation,0.07594723921859016 +3DCube,N8,33,DivOperator,GPUExecutor,1014200.0,NeoN,with Allocation,0.004267580358903569 +3DCube,N8,34,DivOperator,GPUExecutor,292194.0,NeoN,No allocation,0.0148126929368844 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/LaplacianOperator.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/LaplacianOperator.csv new file mode 100644 index 0000000..a56b009 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/LaplacianOperator.csv @@ -0,0 +1,61 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,45,LaplacianOperator,OpenFOAM,63266.2,OpenFOAM,with Allocation,1.0 +2DSquare,N128,46,LaplacianOperator,SerialExecutor,739609.0,NeoN,with Allocation,0.08554006238431387 +2DSquare,N128,47,LaplacianOperator,SerialExecutor,584058.0,NeoN,No allocation,0.10832177626194658 +2DSquare,N128,48,LaplacianOperator,GPUExecutor,623188.0,NeoN,with Allocation,0.10152024750155651 +2DSquare,N128,49,LaplacianOperator,GPUExecutor,20068.5,NeoN,No allocation,3.152512644193637 +2DSquare,N16,15,LaplacianOperator,OpenFOAM,2567.37,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,LaplacianOperator,SerialExecutor,59644.2,NeoN,with Allocation,0.04304475539951915 +2DSquare,N16,17,LaplacianOperator,SerialExecutor,10655.0,NeoN,No allocation,0.24095448146410134 +2DSquare,N16,18,LaplacianOperator,GPUExecutor,614495.0,NeoN,with Allocation,0.0041780160945166355 +2DSquare,N16,19,LaplacianOperator,GPUExecutor,18462.6,NeoN,No allocation,0.13905787917194762 +2DSquare,N256,95,LaplacianOperator,OpenFOAM,372055.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,LaplacianOperator,SerialExecutor,2871320.0,NeoN,with Allocation,0.12957629243692798 +2DSquare,N256,97,LaplacianOperator,SerialExecutor,2346090.0,NeoN,No allocation,0.15858513526761547 +2DSquare,N256,98,LaplacianOperator,GPUExecutor,630480.0,NeoN,with Allocation,0.590113881487121 +2DSquare,N256,99,LaplacianOperator,GPUExecutor,25135.4,NeoN,No allocation,14.80203219363925 +2DSquare,N32,65,LaplacianOperator,OpenFOAM,5005.02,OpenFOAM,with Allocation,1.0 +2DSquare,N32,66,LaplacianOperator,SerialExecutor,91751.6,NeoN,with Allocation,0.05454967542800344 +2DSquare,N32,67,LaplacianOperator,SerialExecutor,38241.0,NeoN,No allocation,0.13088099160586805 +2DSquare,N32,68,LaplacianOperator,GPUExecutor,630365.0,NeoN,with Allocation,0.007939876103527322 +2DSquare,N32,69,LaplacianOperator,GPUExecutor,18758.0,NeoN,No allocation,0.26682055656253334 +2DSquare,N512,105,LaplacianOperator,OpenFOAM,1543080.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,106,LaplacianOperator,SerialExecutor,11595000.0,NeoN,with Allocation,0.13308150064683053 +2DSquare,N512,107,LaplacianOperator,SerialExecutor,9355710.0,NeoN,No allocation,0.16493456936993559 +2DSquare,N512,108,LaplacianOperator,GPUExecutor,767287.0,NeoN,with Allocation,2.0110858127402134 +2DSquare,N512,109,LaplacianOperator,GPUExecutor,48431.3,NeoN,No allocation,31.861213719227027 +2DSquare,N64,115,LaplacianOperator,OpenFOAM,16304.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,LaplacianOperator,SerialExecutor,212660.0,NeoN,with Allocation,0.07666792062447099 +2DSquare,N64,117,LaplacianOperator,SerialExecutor,147383.0,NeoN,No allocation,0.11062469891371461 +2DSquare,N64,118,LaplacianOperator,GPUExecutor,636153.0,NeoN,with Allocation,0.025629369035436445 +2DSquare,N64,119,LaplacianOperator,GPUExecutor,19130.2,NeoN,No allocation,0.8522754597442787 +2DSquare,N8,25,LaplacianOperator,OpenFOAM,1726.42,OpenFOAM,with Allocation,1.0 +2DSquare,N8,26,LaplacianOperator,SerialExecutor,52172.9,NeoN,with Allocation,0.033090359171140574 +2DSquare,N8,27,LaplacianOperator,SerialExecutor,3806.59,NeoN,No allocation,0.45353452827859053 +2DSquare,N8,28,LaplacianOperator,GPUExecutor,608177.0,NeoN,with Allocation,0.0028386801868534985 +2DSquare,N8,29,LaplacianOperator,GPUExecutor,18419.7,NeoN,No allocation,0.09372682508401331 +3DCube,N128,75,LaplacianOperator,OpenFOAM,45681800.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,76,LaplacianOperator,SerialExecutor,199119000.0,NeoN,with Allocation,0.22941959330852404 +3DCube,N128,77,LaplacianOperator,SerialExecutor,114735000.0,NeoN,No allocation,0.39815052076524166 +3DCube,N128,78,LaplacianOperator,GPUExecutor,2261170.0,NeoN,with Allocation,20.2027269068668 +3DCube,N128,79,LaplacianOperator,GPUExecutor,427944.0,NeoN,No allocation,106.74714448619446 +3DCube,N16,85,LaplacianOperator,OpenFOAM,22944.5,OpenFOAM,with Allocation,1.0 +3DCube,N16,86,LaplacianOperator,SerialExecutor,290186.0,NeoN,with Allocation,0.07906825277580586 +3DCube,N16,87,LaplacianOperator,SerialExecutor,217373.0,NeoN,No allocation,0.10555358761207694 +3DCube,N16,88,LaplacianOperator,GPUExecutor,628476.0,NeoN,with Allocation,0.03650815623826526 +3DCube,N16,89,LaplacianOperator,GPUExecutor,19242.1,NeoN,No allocation,1.192411431184746 +3DCube,N32,55,LaplacianOperator,OpenFOAM,305007.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,2130120.0,NeoN,with Allocation,0.14318770773477552 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1715300.0,NeoN,No allocation,0.17781554247070483 +3DCube,N32,58,LaplacianOperator,GPUExecutor,639391.0,NeoN,with Allocation,0.47702735884615205 +3DCube,N32,59,LaplacianOperator,GPUExecutor,23190.7,NeoN,No allocation,13.152125636569831 +3DCube,N64,5,LaplacianOperator,OpenFOAM,2288010.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,6,LaplacianOperator,SerialExecutor,17147200.0,NeoN,with Allocation,0.13343344686012876 +3DCube,N64,7,LaplacianOperator,SerialExecutor,13752900.0,NeoN,No allocation,0.16636563924699518 +3DCube,N64,8,LaplacianOperator,GPUExecutor,738968.0,NeoN,with Allocation,3.0962233817973175 +3DCube,N64,9,LaplacianOperator,GPUExecutor,68830.4,NeoN,No allocation,33.24127129872847 +3DCube,N8,35,LaplacianOperator,OpenFOAM,5192.45,OpenFOAM,with Allocation,1.0 +3DCube,N8,36,LaplacianOperator,SerialExecutor,83409.0,NeoN,with Allocation,0.06225287439005383 +3DCube,N8,37,LaplacianOperator,SerialExecutor,29239.9,NeoN,No allocation,0.17758097667912678 +3DCube,N8,38,LaplacianOperator,GPUExecutor,720380.0,NeoN,with Allocation,0.007207931924817457 +3DCube,N8,39,LaplacianOperator,GPUExecutor,18955.5,NeoN,No allocation,0.27392841127904827 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/advection-diffusion-equation_scalar.csv b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/advection-diffusion-equation_scalar.csv new file mode 100644 index 0000000..4ae05d0 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/develop/advection-diffusion-equation_scalar.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,16,advection-diffusion-equation_scalar,OpenFOAM,192403.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N128,17,advection-diffusion-equation_scalar,OpenFOAM,260336.0,OpenFOAM,implicit-time-integration,0.7390564501259911 +2DSquare,N128,18,advection-diffusion-equation_scalar,SerialExecutor,346635.0,NeoN,explicit-time-integration,0.5550593563835158 +2DSquare,N128,19,advection-diffusion-equation_scalar,SerialExecutor,1303440.0,NeoN,implicit-time-integration,0.14761170441293808 +2DSquare,N16,4,advection-diffusion-equation_scalar,OpenFOAM,8817.19,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,5,advection-diffusion-equation_scalar,OpenFOAM,8821.23,OpenFOAM,implicit-time-integration,0.9995420139821772 +2DSquare,N16,6,advection-diffusion-equation_scalar,SerialExecutor,70862.9,NeoN,explicit-time-integration,0.1244260395778327 +2DSquare,N16,7,advection-diffusion-equation_scalar,SerialExecutor,109643.0,NeoN,implicit-time-integration,0.08041726329998268 +2DSquare,N256,36,advection-diffusion-equation_scalar,OpenFOAM,959998.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,37,advection-diffusion-equation_scalar,OpenFOAM,1429620.0,OpenFOAM,implicit-time-integration,0.6715057148053328 +2DSquare,N256,38,advection-diffusion-equation_scalar,SerialExecutor,1401550.0,NeoN,explicit-time-integration,0.6849545146445007 +2DSquare,N256,39,advection-diffusion-equation_scalar,SerialExecutor,5165590.0,NeoN,implicit-time-integration,0.18584479217282052 +2DSquare,N32,24,advection-diffusion-equation_scalar,OpenFOAM,17725.4,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N32,25,advection-diffusion-equation_scalar,OpenFOAM,15758.8,OpenFOAM,implicit-time-integration,1.1247937660227938 +2DSquare,N32,26,advection-diffusion-equation_scalar,SerialExecutor,86809.9,NeoN,explicit-time-integration,0.20418638887960938 +2DSquare,N32,27,advection-diffusion-equation_scalar,SerialExecutor,167843.0,NeoN,implicit-time-integration,0.10560702561322188 +2DSquare,N512,40,advection-diffusion-equation_scalar,OpenFOAM,4887550.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N512,41,advection-diffusion-equation_scalar,OpenFOAM,9235600.0,OpenFOAM,implicit-time-integration,0.5292076313395989 +2DSquare,N512,42,advection-diffusion-equation_scalar,SerialExecutor,6408760.0,NeoN,explicit-time-integration,0.7626358297080871 +2DSquare,N512,43,advection-diffusion-equation_scalar,SerialExecutor,22786900.0,NeoN,implicit-time-integration,0.2144894654384756 +2DSquare,N64,44,advection-diffusion-equation_scalar,OpenFOAM,51052.8,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,45,advection-diffusion-equation_scalar,OpenFOAM,57046.1,OpenFOAM,implicit-time-integration,0.8949393560646566 +2DSquare,N64,46,advection-diffusion-equation_scalar,SerialExecutor,122422.0,NeoN,explicit-time-integration,0.4170230840861937 +2DSquare,N64,47,advection-diffusion-equation_scalar,SerialExecutor,374430.0,NeoN,implicit-time-integration,0.1363480490345325 +2DSquare,N8,8,advection-diffusion-equation_scalar,OpenFOAM,5901.65,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N8,9,advection-diffusion-equation_scalar,OpenFOAM,4936.58,OpenFOAM,implicit-time-integration,1.1954936413468433 +2DSquare,N8,10,advection-diffusion-equation_scalar,SerialExecutor,68406.1,NeoN,explicit-time-integration,0.08627373874552122 +2DSquare,N8,11,advection-diffusion-equation_scalar,SerialExecutor,97161.3,NeoN,implicit-time-integration,0.06074074760218317 +3DCube,N128,28,advection-diffusion-equation_scalar,OpenFOAM,94091300.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N128,29,advection-diffusion-equation_scalar,OpenFOAM,181201000.0,OpenFOAM,implicit-time-integration,0.5192647943444021 +3DCube,N128,30,advection-diffusion-equation_scalar,SerialExecutor,157800000.0,NeoN,explicit-time-integration,0.5962693282636249 +3DCube,N128,31,advection-diffusion-equation_scalar,SerialExecutor,357261000.0,NeoN,implicit-time-integration,0.2633685176943467 +3DCube,N16,32,advection-diffusion-equation_scalar,OpenFOAM,70251.2,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,33,advection-diffusion-equation_scalar,OpenFOAM,80071.6,OpenFOAM,implicit-time-integration,0.8773547674831025 +3DCube,N16,34,advection-diffusion-equation_scalar,SerialExecutor,141458.0,NeoN,explicit-time-integration,0.49662231899220965 +3DCube,N16,35,advection-diffusion-equation_scalar,SerialExecutor,756714.0,NeoN,implicit-time-integration,0.0928371881582738 +3DCube,N32,20,advection-diffusion-equation_scalar,OpenFOAM,613862.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,21,advection-diffusion-equation_scalar,OpenFOAM,886660.0,OpenFOAM,implicit-time-integration,0.6923307694042813 +3DCube,N32,22,advection-diffusion-equation_scalar,SerialExecutor,910411.0,NeoN,explicit-time-integration,0.6742690938488222 +3DCube,N32,23,advection-diffusion-equation_scalar,SerialExecutor,3798630.0,NeoN,implicit-time-integration,0.16160089295351218 +3DCube,N64,0,advection-diffusion-equation_scalar,OpenFOAM,6418290.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,1,advection-diffusion-equation_scalar,OpenFOAM,11417700.0,OpenFOAM,implicit-time-integration,0.5621351060196011 +3DCube,N64,2,advection-diffusion-equation_scalar,SerialExecutor,7684030.0,NeoN,explicit-time-integration,0.8352765410858625 +3DCube,N64,3,advection-diffusion-equation_scalar,SerialExecutor,31890000.0,NeoN,implicit-time-integration,0.20126340545625587 +3DCube,N8,12,advection-diffusion-equation_scalar,OpenFOAM,15418.9,OpenFOAM,explicit-time-integration,1.0 +3DCube,N8,13,advection-diffusion-equation_scalar,OpenFOAM,14868.1,OpenFOAM,implicit-time-integration,1.0370457556782642 +3DCube,N8,14,advection-diffusion-equation_scalar,SerialExecutor,81473.4,NeoN,explicit-time-integration,0.1892507247764301 +3DCube,N8,15,advection-diffusion-equation_scalar,SerialExecutor,150837.0,NeoN,implicit-time-integration,0.10222226642004283 diff --git a/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log new file mode 100644 index 0000000..b167693 --- /dev/null +++ b/NeoFOAM/172387/neon-cluster-meta-runner-adapter-nvidia-h100/system-info.log @@ -0,0 +1,82 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Tue Dec 2 13:15:52 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 580.95.05 Driver Version: 580.95.05 CUDA Version: 13.0 | ++-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:CA:00.0 Off | 0 | +| N/A 35C P0 61W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/DivOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/DivOperator.csv new file mode 100644 index 0000000..04b3600 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/DivOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,DivOperator,OpenFOAM,5199.69,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,55784.8,NeoN,with Allocation,0.09320979908505542 +2DSquare,N16,2,DivOperator,SerialExecutor,28381.1,NeoN,No allocation,0.1832096007554323 +2DSquare,N16,3,DivOperator,GPUExecutor,1220650.0,NeoN,with Allocation,0.004259771433252775 +2DSquare,N16,4,DivOperator,GPUExecutor,636641.0,NeoN,No allocation,0.008167381616955238 +2DSquare,N256,75,DivOperator,OpenFOAM,342129.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,DivOperator,SerialExecutor,446198.0,NeoN,with Allocation,0.7667649787762384 +2DSquare,N256,77,DivOperator,SerialExecutor,419756.0,NeoN,No allocation,0.8150663718922422 +2DSquare,N256,78,DivOperator,GPUExecutor,1297600.0,NeoN,with Allocation,0.26366291615289766 +2DSquare,N256,79,DivOperator,GPUExecutor,694118.0,NeoN,No allocation,0.492897461238579 +2DSquare,N64,100,DivOperator,OpenFOAM,18106.7,OpenFOAM,with Allocation,1.0 +2DSquare,N64,101,DivOperator,SerialExecutor,46788.0,NeoN,with Allocation,0.38699452851158417 +2DSquare,N64,102,DivOperator,SerialExecutor,32473.7,NeoN,No allocation,0.5575804420192341 +2DSquare,N64,103,DivOperator,GPUExecutor,1240410.0,NeoN,with Allocation,0.014597350875920059 +2DSquare,N64,104,DivOperator,GPUExecutor,620246.0,NeoN,No allocation,0.029192771900181543 +3DCube,N16,25,DivOperator,OpenFOAM,27361.9,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,DivOperator,SerialExecutor,58387.2,NeoN,with Allocation,0.46862839800504225 +3DCube,N16,27,DivOperator,SerialExecutor,42727.3,NeoN,No allocation,0.6403844848609671 +3DCube,N16,28,DivOperator,GPUExecutor,1305390.0,NeoN,with Allocation,0.020960709060127626 +3DCube,N16,29,DivOperator,GPUExecutor,693440.0,NeoN,No allocation,0.03945820835256115 +3DCube,N32,50,DivOperator,OpenFOAM,266393.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,329055.0,NeoN,with Allocation,0.8095698287520323 +3DCube,N32,52,DivOperator,SerialExecutor,346668.0,NeoN,No allocation,0.7684383906215745 +3DCube,N32,53,DivOperator,GPUExecutor,1286530.0,NeoN,with Allocation,0.2070631854678865 +3DCube,N32,54,DivOperator,GPUExecutor,681088.0,NeoN,No allocation,0.3911286059951137 +3DCube,N64,125,DivOperator,OpenFOAM,1964280.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,126,DivOperator,SerialExecutor,2357800.0,NeoN,with Allocation,0.8330986512850963 +3DCube,N64,127,DivOperator,SerialExecutor,2138250.0,NeoN,No allocation,0.9186390740091196 +3DCube,N64,128,DivOperator,GPUExecutor,1489640.0,NeoN,with Allocation,1.3186273193523268 +3DCube,N64,129,DivOperator,GPUExecutor,807972.0,NeoN,No allocation,2.4311238508265136 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv new file mode 100644 index 0000000..18b24f0 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,15,FaceInterpolation,OpenFOAM,905.049,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,FaceInterpolation,SerialExecutor,13876.5,NeoN,with Allocation,0.0652217057615393 +2DSquare,N16,17,FaceInterpolation,SerialExecutor,561.419,NeoN,No allocation,1.6120740480817357 +2DSquare,N16,18,FaceInterpolation,GPUExecutor,609461.0,NeoN,with Allocation,0.0014849990401354638 +2DSquare,N16,19,FaceInterpolation,GPUExecutor,17080.8,NeoN,No allocation,0.05298633553463538 +2DSquare,N256,90,FaceInterpolation,OpenFOAM,132589.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,FaceInterpolation,SerialExecutor,222498.0,NeoN,with Allocation,0.5959109744806695 +2DSquare,N256,92,FaceInterpolation,SerialExecutor,132318.0,NeoN,No allocation,1.0020480962529663 +2DSquare,N256,93,FaceInterpolation,GPUExecutor,624503.0,NeoN,with Allocation,0.21231122989000853 +2DSquare,N256,94,FaceInterpolation,GPUExecutor,21087.7,NeoN,No allocation,6.287504090061979 +2DSquare,N64,115,FaceInterpolation,OpenFOAM,5151.39,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,FaceInterpolation,SerialExecutor,20769.2,NeoN,with Allocation,0.24803025634112053 +2DSquare,N64,117,FaceInterpolation,SerialExecutor,6390.65,NeoN,No allocation,0.806082323394334 +2DSquare,N64,118,FaceInterpolation,GPUExecutor,602837.0,NeoN,with Allocation,0.008545245232127425 +2DSquare,N64,119,FaceInterpolation,GPUExecutor,19122.1,NeoN,No allocation,0.2693945748636395 +3DCube,N16,40,FaceInterpolation,OpenFOAM,7024.47,OpenFOAM,with Allocation,1.0 +3DCube,N16,41,FaceInterpolation,SerialExecutor,26650.7,NeoN,with Allocation,0.26357544079517614 +3DCube,N16,42,FaceInterpolation,SerialExecutor,9558.07,NeoN,No allocation,0.7349255655168879 +3DCube,N16,43,FaceInterpolation,GPUExecutor,630720.0,NeoN,with Allocation,0.011137224124809742 +3DCube,N16,44,FaceInterpolation,GPUExecutor,19424.5,NeoN,No allocation,0.36162938556977015 +3DCube,N32,65,FaceInterpolation,OpenFOAM,91912.4,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,FaceInterpolation,SerialExecutor,175155.0,NeoN,with Allocation,0.5247489366561046 +3DCube,N32,67,FaceInterpolation,SerialExecutor,84904.5,NeoN,No allocation,1.0825386169166533 +3DCube,N32,68,FaceInterpolation,GPUExecutor,612813.0,NeoN,with Allocation,0.14998441612694247 +3DCube,N32,69,FaceInterpolation,GPUExecutor,19357.9,NeoN,No allocation,4.748056349087452 +3DCube,N64,140,FaceInterpolation,OpenFOAM,716476.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,141,FaceInterpolation,SerialExecutor,1156920.0,NeoN,with Allocation,0.6192960619576116 +3DCube,N64,142,FaceInterpolation,SerialExecutor,673911.0,NeoN,No allocation,1.06316115926287 +3DCube,N64,143,FaceInterpolation,GPUExecutor,730122.0,NeoN,with Allocation,0.9813099728538518 +3DCube,N64,144,FaceInterpolation,GPUExecutor,35780.2,NeoN,No allocation,20.024371020843933 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv new file mode 100644 index 0000000..0897a3c --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,20,FaceNormalGradient,OpenFOAM,981.39,OpenFOAM,with Allocation,1.0 +2DSquare,N16,21,FaceNormalGradient,SerialExecutor,13722.8,NeoN,with Allocation,0.07151528842510275 +2DSquare,N16,22,FaceNormalGradient,SerialExecutor,445.826,NeoN,No allocation,2.2012848061799892 +2DSquare,N16,23,FaceNormalGradient,GPUExecutor,603181.0,NeoN,with Allocation,0.001627024060771145 +2DSquare,N16,24,FaceNormalGradient,GPUExecutor,19654.7,NeoN,No allocation,0.04993156853068222 +2DSquare,N256,95,FaceNormalGradient,OpenFOAM,139223.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,FaceNormalGradient,SerialExecutor,209640.0,NeoN,with Allocation,0.6641051326082809 +2DSquare,N256,97,FaceNormalGradient,SerialExecutor,140070.0,NeoN,No allocation,0.9939530234882559 +2DSquare,N256,98,FaceNormalGradient,GPUExecutor,653865.0,NeoN,with Allocation,0.2129231569207711 +2DSquare,N256,99,FaceNormalGradient,GPUExecutor,28509.0,NeoN,No allocation,4.883475393735312 +2DSquare,N64,120,FaceNormalGradient,OpenFOAM,5705.04,OpenFOAM,with Allocation,1.0 +2DSquare,N64,121,FaceNormalGradient,SerialExecutor,19831.4,NeoN,with Allocation,0.28767711810563046 +2DSquare,N64,122,FaceNormalGradient,SerialExecutor,4708.16,NeoN,No allocation,1.211734520492082 +2DSquare,N64,123,FaceNormalGradient,GPUExecutor,609656.0,NeoN,with Allocation,0.00935780177673967 +2DSquare,N64,124,FaceNormalGradient,GPUExecutor,22696.1,NeoN,No allocation,0.2513665343384987 +3DCube,N16,45,FaceNormalGradient,OpenFOAM,7898.43,OpenFOAM,with Allocation,1.0 +3DCube,N16,46,FaceNormalGradient,SerialExecutor,24044.2,NeoN,with Allocation,0.32849626937057586 +3DCube,N16,47,FaceNormalGradient,SerialExecutor,7226.78,NeoN,No allocation,1.0929390406239017 +3DCube,N16,48,FaceNormalGradient,GPUExecutor,639261.0,NeoN,with Allocation,0.012355563689948237 +3DCube,N16,49,FaceNormalGradient,GPUExecutor,23662.7,NeoN,No allocation,0.3337924243640836 +3DCube,N32,70,FaceNormalGradient,OpenFOAM,88633.7,OpenFOAM,with Allocation,1.0 +3DCube,N32,71,FaceNormalGradient,SerialExecutor,183350.0,NeoN,with Allocation,0.48341259885464954 +3DCube,N32,72,FaceNormalGradient,SerialExecutor,101944.0,NeoN,No allocation,0.8694351800988778 +3DCube,N32,73,FaceNormalGradient,GPUExecutor,623710.0,NeoN,with Allocation,0.1421072293213192 +3DCube,N32,74,FaceNormalGradient,GPUExecutor,27226.4,NeoN,No allocation,3.2554322275438543 +3DCube,N64,145,FaceNormalGradient,OpenFOAM,732257.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,146,FaceNormalGradient,SerialExecutor,1111050.0,NeoN,with Allocation,0.6590675487151794 +3DCube,N64,147,FaceNormalGradient,SerialExecutor,764582.0,NeoN,No allocation,0.9577219971173792 +3DCube,N64,148,FaceNormalGradient,GPUExecutor,738052.0,NeoN,with Allocation,0.9921482497168221 +3DCube,N64,149,FaceNormalGradient,GPUExecutor,43430.6,NeoN,No allocation,16.860393363204746 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/GradOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/GradOperator.csv new file mode 100644 index 0000000..d9aac69 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/GradOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,10,GradOperator,OpenFOAM,3729.38,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,GradOperator,SerialExecutor,39087.5,NeoN,with Allocation,0.0954110649184522 +2DSquare,N16,12,GradOperator,SerialExecutor,25147.8,NeoN,No allocation,0.14829845950739232 +2DSquare,N16,13,GradOperator,GPUExecutor,1212150.0,NeoN,with Allocation,0.003076665429196057 +2DSquare,N16,14,GradOperator,GPUExecutor,633212.0,NeoN,No allocation,0.005889623064629224 +2DSquare,N256,85,GradOperator,OpenFOAM,549257.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,86,GradOperator,SerialExecutor,3165450.0,NeoN,with Allocation,0.1735162457154591 +2DSquare,N256,87,GradOperator,SerialExecutor,3048930.0,NeoN,No allocation,0.18014746156848468 +2DSquare,N256,88,GradOperator,GPUExecutor,1283030.0,NeoN,with Allocation,0.42809365330506693 +2DSquare,N256,89,GradOperator,GPUExecutor,687217.0,NeoN,No allocation,0.7992482723797578 +2DSquare,N64,110,GradOperator,OpenFOAM,27778.5,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,GradOperator,SerialExecutor,213986.0,NeoN,with Allocation,0.12981456730814164 +2DSquare,N64,112,GradOperator,SerialExecutor,198370.0,NeoN,No allocation,0.14003377526843777 +2DSquare,N64,113,GradOperator,GPUExecutor,1225950.0,NeoN,with Allocation,0.02265875443533586 +2DSquare,N64,114,GradOperator,GPUExecutor,648620.0,NeoN,No allocation,0.0428270790293238 +3DCube,N16,35,GradOperator,OpenFOAM,45475.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,36,GradOperator,SerialExecutor,306207.0,NeoN,with Allocation,0.14851130117861447 +3DCube,N16,37,GradOperator,SerialExecutor,288809.0,NeoN,No allocation,0.15745769695542727 +3DCube,N16,38,GradOperator,GPUExecutor,1272450.0,NeoN,with Allocation,0.03573830012967111 +3DCube,N16,39,GradOperator,GPUExecutor,678580.0,NeoN,No allocation,0.0670152377022606 +3DCube,N32,60,GradOperator,OpenFOAM,413647.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,GradOperator,SerialExecutor,2358270.0,NeoN,with Allocation,0.17540273166346518 +3DCube,N32,62,GradOperator,SerialExecutor,2283950.0,NeoN,No allocation,0.18111035705685327 +3DCube,N32,63,GradOperator,GPUExecutor,1261340.0,NeoN,with Allocation,0.32794250558929394 +3DCube,N32,64,GradOperator,GPUExecutor,693352.0,NeoN,No allocation,0.5965901879564781 +3DCube,N64,135,GradOperator,OpenFOAM,2875870.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,136,GradOperator,SerialExecutor,18607200.0,NeoN,with Allocation,0.1545568382131648 +3DCube,N64,137,GradOperator,SerialExecutor,18085500.0,NeoN,No allocation,0.1590152331978657 +3DCube,N64,138,GradOperator,GPUExecutor,1635590.0,NeoN,with Allocation,1.7583073997762275 +3DCube,N64,139,GradOperator,GPUExecutor,960374.0,NeoN,No allocation,2.9945312971821396 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv new file mode 100644 index 0000000..706c070 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,5,LaplacianOperator,OpenFOAM,3492.18,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,33885.0,NeoN,with Allocation,0.10305976095617529 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,19694.7,NeoN,No allocation,0.17731572453502717 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1213580.0,NeoN,with Allocation,0.0028775853260600867 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,629429.0,NeoN,No allocation,0.005548171437922307 +2DSquare,N256,80,LaplacianOperator,OpenFOAM,401517.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,81,LaplacianOperator,SerialExecutor,1637700.0,NeoN,with Allocation,0.245171276790621 +2DSquare,N256,82,LaplacianOperator,SerialExecutor,1619890.0,NeoN,No allocation,0.24786683046379693 +2DSquare,N256,83,LaplacianOperator,GPUExecutor,1259720.0,NeoN,with Allocation,0.31873511574000574 +2DSquare,N256,84,LaplacianOperator,GPUExecutor,689382.0,NeoN,No allocation,0.5824303506618972 +2DSquare,N64,105,LaplacianOperator,OpenFOAM,20507.1,OpenFOAM,with Allocation,1.0 +2DSquare,N64,106,LaplacianOperator,SerialExecutor,123406.0,NeoN,with Allocation,0.16617587475487414 +2DSquare,N64,107,LaplacianOperator,SerialExecutor,107059.0,NeoN,No allocation,0.19154951942386908 +2DSquare,N64,108,LaplacianOperator,GPUExecutor,1212490.0,NeoN,with Allocation,0.01691321165535386 +2DSquare,N64,109,LaplacianOperator,GPUExecutor,643839.0,NeoN,No allocation,0.03185128580281716 +3DCube,N16,30,LaplacianOperator,OpenFOAM,31484.9,OpenFOAM,with Allocation,1.0 +3DCube,N16,31,LaplacianOperator,SerialExecutor,171098.0,NeoN,with Allocation,0.18401676232334685 +3DCube,N16,32,LaplacianOperator,SerialExecutor,154054.0,NeoN,No allocation,0.20437573837745207 +3DCube,N16,33,LaplacianOperator,GPUExecutor,1263110.0,NeoN,with Allocation,0.02492649096278234 +3DCube,N16,34,LaplacianOperator,GPUExecutor,671199.0,NeoN,No allocation,0.04690844295060034 +3DCube,N32,55,LaplacianOperator,OpenFOAM,347666.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,1308190.0,NeoN,with Allocation,0.2657610897499599 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1290870.0,NeoN,No allocation,0.26932688806773725 +3DCube,N32,58,LaplacianOperator,GPUExecutor,1259640.0,NeoN,with Allocation,0.27600425518402083 +3DCube,N32,59,LaplacianOperator,GPUExecutor,656451.0,NeoN,No allocation,0.5296145485344679 +3DCube,N64,130,LaplacianOperator,OpenFOAM,2404360.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,131,LaplacianOperator,SerialExecutor,10214800.0,NeoN,with Allocation,0.23538003680933547 +3DCube,N64,132,LaplacianOperator,SerialExecutor,10009300.0,NeoN,No allocation,0.2402126022798797 +3DCube,N64,133,LaplacianOperator,GPUExecutor,1478240.0,NeoN,with Allocation,1.6265017859075657 +3DCube,N64,134,LaplacianOperator,GPUExecutor,829533.0,NeoN,No allocation,2.8984500917986384 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/Poisson.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/Poisson.csv new file mode 100644 index 0000000..5d906eb --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/Poisson.csv @@ -0,0 +1,19 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,Poisson,OpenFOAM,5212.18,OpenFOAM,Poisson,1.0 +2DSquare,N16,1,Poisson,SerialExecutor,20375.7,NeoN,Poisson,0.25580372698852066 +2DSquare,N16,2,Poisson,GPUExecutor,578973.0,NeoN,Poisson,0.009002457800277388 +2DSquare,N256,9,Poisson,OpenFOAM,773530.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,10,Poisson,SerialExecutor,502297.0,NeoN,Poisson,1.539985307497357 +2DSquare,N256,11,Poisson,GPUExecutor,684919.0,NeoN,Poisson,1.1293744223769526 +2DSquare,N64,12,Poisson,OpenFOAM,34518.6,OpenFOAM,Poisson,1.0 +2DSquare,N64,13,Poisson,SerialExecutor,30618.7,NeoN,Poisson,1.127369875272301 +2DSquare,N64,14,Poisson,GPUExecutor,558441.0,NeoN,Poisson,0.0618124385566246 +3DCube,N16,3,Poisson,OpenFOAM,54266.3,OpenFOAM,Poisson,1.0 +3DCube,N16,4,Poisson,SerialExecutor,35121.4,NeoN,Poisson,1.5451064023643704 +3DCube,N16,5,Poisson,GPUExecutor,637626.0,NeoN,Poisson,0.08510678673705276 +3DCube,N32,6,Poisson,OpenFOAM,657541.0,OpenFOAM,Poisson,1.0 +3DCube,N32,7,Poisson,SerialExecutor,340321.0,NeoN,Poisson,1.932119969088008 +3DCube,N32,8,Poisson,GPUExecutor,618961.0,NeoN,Poisson,1.0623302599032896 +3DCube,N64,15,Poisson,OpenFOAM,5233320.0,OpenFOAM,Poisson,1.0 +3DCube,N64,16,Poisson,SerialExecutor,4180100.0,NeoN,Poisson,1.2519604794143682 +3DCube,N64,17,Poisson,GPUExecutor,791556.0,NeoN,Poisson,6.611433682518988 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/momentum.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/momentum.csv new file mode 100644 index 0000000..a62536e --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/momentum.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,momentum,OpenFOAM,10299.6,OpenFOAM,without RHS,1.0 +2DSquare,N16,1,momentum,OpenFOAM,17110.2,OpenFOAM,with RHS,0.6019567275660133 +2DSquare,N16,2,momentum,SerialExecutor,70697.0,NeoN,without RHS,0.14568652135168395 +2DSquare,N16,3,momentum,SerialExecutor,116949.0,NeoN,with RHS,0.08806915835107611 +2DSquare,N16,4,momentum,GPUExecutor,1251000.0,NeoN,without RHS,0.008233093525179857 +2DSquare,N16,5,momentum,GPUExecutor,2119240.0,NeoN,with RHS,0.0048600441667767695 +2DSquare,N256,18,momentum,OpenFOAM,2330590.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,19,momentum,OpenFOAM,3167620.0,OpenFOAM,with RHS,0.7357542887088729 +2DSquare,N256,20,momentum,SerialExecutor,8098890.0,NeoN,without RHS,0.2877665951753882 +2DSquare,N256,21,momentum,SerialExecutor,15334000.0,NeoN,with RHS,0.15198839180905177 +2DSquare,N256,22,momentum,GPUExecutor,1695680.0,NeoN,without RHS,1.374427958105303 +2DSquare,N256,23,momentum,GPUExecutor,2955640.0,NeoN,with RHS,0.7885229594943904 +2DSquare,N64,24,momentum,OpenFOAM,78249.4,OpenFOAM,without RHS,1.0 +2DSquare,N64,25,momentum,OpenFOAM,131346.0,OpenFOAM,with RHS,0.5957501560763174 +2DSquare,N64,26,momentum,SerialExecutor,537700.0,NeoN,without RHS,0.1455261298121629 +2DSquare,N64,27,momentum,SerialExecutor,946437.0,NeoN,with RHS,0.08267787501967906 +2DSquare,N64,28,momentum,GPUExecutor,1321180.0,NeoN,without RHS,0.05922690322287651 +2DSquare,N64,29,momentum,GPUExecutor,2241640.0,NeoN,with RHS,0.03490721079209864 +3DCube,N16,6,momentum,OpenFOAM,116336.0,OpenFOAM,without RHS,1.0 +3DCube,N16,7,momentum,OpenFOAM,191385.0,OpenFOAM,with RHS,0.6078637301773911 +3DCube,N16,8,momentum,SerialExecutor,785355.0,NeoN,without RHS,0.14813173660319218 +3DCube,N16,9,momentum,SerialExecutor,1465220.0,NeoN,with RHS,0.07939831561130752 +3DCube,N16,10,momentum,GPUExecutor,1336910.0,NeoN,without RHS,0.08701857267878915 +3DCube,N16,11,momentum,GPUExecutor,2311630.0,NeoN,with RHS,0.050326393064634045 +3DCube,N32,12,momentum,OpenFOAM,1482740.0,OpenFOAM,without RHS,1.0 +3DCube,N32,13,momentum,OpenFOAM,2147640.0,OpenFOAM,with RHS,0.690404350822298 +3DCube,N32,14,momentum,SerialExecutor,6323660.0,NeoN,without RHS,0.23447497177267596 +3DCube,N32,15,momentum,SerialExecutor,11941100.0,NeoN,with RHS,0.12417114001222668 +3DCube,N32,16,momentum,GPUExecutor,1643210.0,NeoN,without RHS,0.9023435835955234 +3DCube,N32,17,momentum,GPUExecutor,2847590.0,NeoN,with RHS,0.5206999603173209 +3DCube,N64,30,momentum,OpenFOAM,14153900.0,OpenFOAM,without RHS,1.0 +3DCube,N64,31,momentum,OpenFOAM,21521600.0,OpenFOAM,with RHS,0.6576602111367185 +3DCube,N64,32,momentum,SerialExecutor,63825400.0,NeoN,without RHS,0.22175967561503726 +3DCube,N64,33,momentum,SerialExecutor,115339000.0,NeoN,with RHS,0.12271564691908202 +3DCube,N64,34,momentum,GPUExecutor,3829590.0,NeoN,without RHS,3.695930895996699 +3DCube,N64,35,momentum,GPUExecutor,7012390.0,NeoN,with RHS,2.018413123057902 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv new file mode 100644 index 0000000..8f04fcb --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv @@ -0,0 +1,55 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,pressureVelocityCoupling,CPU,1355.93,OpenFOAM,Compute rAU, +2DSquare,N16,1,pressureVelocityCoupling,CPU,4425.68,OpenFOAM,Compute HbyA, +2DSquare,N16,2,pressureVelocityCoupling,CPU,4505.78,OpenFOAM,constrainHbyA, +2DSquare,N16,3,pressureVelocityCoupling,SerialExecutor,16526.6,NeoN,Compute rAU, +2DSquare,N16,4,pressureVelocityCoupling,SerialExecutor,49757.2,NeoN,Compute HbyA, +2DSquare,N16,5,pressureVelocityCoupling,SerialExecutor,59.5414,NeoN,constrainHbyA, +2DSquare,N16,6,pressureVelocityCoupling,GPUExecutor,754700.0,NeoN,Compute rAU, +2DSquare,N16,7,pressureVelocityCoupling,GPUExecutor,2035510.0,NeoN,Compute HbyA, +2DSquare,N16,8,pressureVelocityCoupling,GPUExecutor,374.283,NeoN,constrainHbyA, +2DSquare,N256,27,pressureVelocityCoupling,CPU,101930.0,OpenFOAM,Compute rAU, +2DSquare,N256,28,pressureVelocityCoupling,CPU,1206210.0,OpenFOAM,Compute HbyA, +2DSquare,N256,29,pressureVelocityCoupling,CPU,1193790.0,OpenFOAM,constrainHbyA, +2DSquare,N256,30,pressureVelocityCoupling,SerialExecutor,738113.0,NeoN,Compute rAU, +2DSquare,N256,31,pressureVelocityCoupling,SerialExecutor,1433960.0,NeoN,Compute HbyA, +2DSquare,N256,32,pressureVelocityCoupling,SerialExecutor,60.6899,NeoN,constrainHbyA, +2DSquare,N256,33,pressureVelocityCoupling,GPUExecutor,859951.0,NeoN,Compute rAU, +2DSquare,N256,34,pressureVelocityCoupling,GPUExecutor,2261120.0,NeoN,Compute HbyA, +2DSquare,N256,35,pressureVelocityCoupling,GPUExecutor,367.298,NeoN,constrainHbyA, +2DSquare,N64,36,pressureVelocityCoupling,CPU,7130.91,OpenFOAM,Compute rAU, +2DSquare,N64,37,pressureVelocityCoupling,CPU,48166.8,OpenFOAM,Compute HbyA, +2DSquare,N64,38,pressureVelocityCoupling,CPU,48662.8,OpenFOAM,constrainHbyA, +2DSquare,N64,39,pressureVelocityCoupling,SerialExecutor,30770.7,NeoN,Compute rAU, +2DSquare,N64,40,pressureVelocityCoupling,SerialExecutor,92000.8,NeoN,Compute HbyA, +2DSquare,N64,41,pressureVelocityCoupling,SerialExecutor,59.4137,NeoN,constrainHbyA, +2DSquare,N64,42,pressureVelocityCoupling,GPUExecutor,764539.0,NeoN,Compute rAU, +2DSquare,N64,43,pressureVelocityCoupling,GPUExecutor,2096560.0,NeoN,Compute HbyA, +2DSquare,N64,44,pressureVelocityCoupling,GPUExecutor,373.997,NeoN,constrainHbyA, +3DCube,N16,9,pressureVelocityCoupling,CPU,10148.6,OpenFOAM,Compute rAU, +3DCube,N16,10,pressureVelocityCoupling,CPU,65118.7,OpenFOAM,Compute HbyA, +3DCube,N16,11,pressureVelocityCoupling,CPU,65331.5,OpenFOAM,constrainHbyA, +3DCube,N16,12,pressureVelocityCoupling,SerialExecutor,37589.3,NeoN,Compute rAU, +3DCube,N16,13,pressureVelocityCoupling,SerialExecutor,143964.0,NeoN,Compute HbyA, +3DCube,N16,14,pressureVelocityCoupling,SerialExecutor,255.691,NeoN,constrainHbyA, +3DCube,N16,15,pressureVelocityCoupling,GPUExecutor,846367.0,NeoN,Compute rAU, +3DCube,N16,16,pressureVelocityCoupling,GPUExecutor,2321580.0,NeoN,Compute HbyA, +3DCube,N16,17,pressureVelocityCoupling,GPUExecutor,22905.7,NeoN,constrainHbyA, +3DCube,N32,18,pressureVelocityCoupling,CPU,64998.3,OpenFOAM,Compute rAU, +3DCube,N32,19,pressureVelocityCoupling,CPU,740604.0,OpenFOAM,Compute HbyA, +3DCube,N32,20,pressureVelocityCoupling,CPU,742046.0,OpenFOAM,constrainHbyA, +3DCube,N32,21,pressureVelocityCoupling,SerialExecutor,640771.0,NeoN,Compute rAU, +3DCube,N32,22,pressureVelocityCoupling,SerialExecutor,1244020.0,NeoN,Compute HbyA, +3DCube,N32,23,pressureVelocityCoupling,SerialExecutor,1820.5,NeoN,constrainHbyA, +3DCube,N32,24,pressureVelocityCoupling,GPUExecutor,794517.0,NeoN,Compute rAU, +3DCube,N32,25,pressureVelocityCoupling,GPUExecutor,2235320.0,NeoN,Compute HbyA, +3DCube,N32,26,pressureVelocityCoupling,GPUExecutor,23031.0,NeoN,constrainHbyA, +3DCube,N64,45,pressureVelocityCoupling,CPU,666964.0,OpenFOAM,Compute rAU, +3DCube,N64,46,pressureVelocityCoupling,CPU,5867290.0,OpenFOAM,Compute HbyA, +3DCube,N64,47,pressureVelocityCoupling,CPU,7237630.0,OpenFOAM,constrainHbyA, +3DCube,N64,48,pressureVelocityCoupling,SerialExecutor,4341420.0,NeoN,Compute rAU, +3DCube,N64,49,pressureVelocityCoupling,SerialExecutor,10987600.0,NeoN,Compute HbyA, +3DCube,N64,50,pressureVelocityCoupling,SerialExecutor,8029.88,NeoN,constrainHbyA, +3DCube,N64,51,pressureVelocityCoupling,GPUExecutor,1040490.0,NeoN,Compute rAU, +3DCube,N64,52,pressureVelocityCoupling,GPUExecutor,2936930.0,NeoN,Compute HbyA, +3DCube,N64,53,pressureVelocityCoupling,GPUExecutor,23556.4,NeoN,constrainHbyA, diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv new file mode 100644 index 0000000..3f367b2 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,scalarAdvection,OpenFOAM,8597.36,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,scalarAdvection,OpenFOAM,7672.31,OpenFOAM,implicit-time-integration,1.1205699456878047 +2DSquare,N16,2,scalarAdvection,SerialExecutor,21171.5,NeoN,explicit-time-integration,0.40608176085775693 +2DSquare,N16,3,scalarAdvection,SerialExecutor,47759.3,NeoN,implicit-time-integration,0.18001436369461027 +2DSquare,N16,4,scalarAdvection,GPUExecutor,596046.0,NeoN,explicit-time-integration,0.014423987410367657 +2DSquare,N16,5,scalarAdvection,GPUExecutor,1226710.0,NeoN,implicit-time-integration,0.007008469809490426 +2DSquare,N256,18,scalarAdvection,OpenFOAM,995670.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,19,scalarAdvection,OpenFOAM,1477840.0,OpenFOAM,implicit-time-integration,0.6737332864180154 +2DSquare,N256,20,scalarAdvection,SerialExecutor,643084.0,NeoN,explicit-time-integration,1.5482736314385057 +2DSquare,N256,21,scalarAdvection,SerialExecutor,3970400.0,NeoN,implicit-time-integration,0.25077322184162804 +2DSquare,N256,22,scalarAdvection,GPUExecutor,712138.0,NeoN,explicit-time-integration,1.3981419331646394 +2DSquare,N256,23,scalarAdvection,GPUExecutor,1427470.0,NeoN,implicit-time-integration,0.6975067777256264 +2DSquare,N64,24,scalarAdvection,OpenFOAM,49009.8,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,25,scalarAdvection,OpenFOAM,54978.3,OpenFOAM,implicit-time-integration,0.8914389859271749 +2DSquare,N64,26,scalarAdvection,SerialExecutor,34224.9,NeoN,explicit-time-integration,1.4319924966910056 +2DSquare,N64,27,scalarAdvection,SerialExecutor,257862.0,NeoN,implicit-time-integration,0.19006212625357752 +2DSquare,N64,28,scalarAdvection,GPUExecutor,579638.0,NeoN,explicit-time-integration,0.08455242754960855 +2DSquare,N64,29,scalarAdvection,GPUExecutor,1189490.0,NeoN,implicit-time-integration,0.04120236403836939 +3DCube,N16,6,scalarAdvection,OpenFOAM,67596.8,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,7,scalarAdvection,OpenFOAM,77221.0,OpenFOAM,implicit-time-integration,0.8753680993512127 +3DCube,N16,8,scalarAdvection,SerialExecutor,38547.1,NeoN,explicit-time-integration,1.7536157064993219 +3DCube,N16,9,scalarAdvection,SerialExecutor,382933.0,NeoN,implicit-time-integration,0.1765238305395461 +3DCube,N16,10,scalarAdvection,GPUExecutor,589283.0,NeoN,explicit-time-integration,0.11471024957448289 +3DCube,N16,11,scalarAdvection,GPUExecutor,1237960.0,NeoN,implicit-time-integration,0.05460337975378849 +3DCube,N32,12,scalarAdvection,OpenFOAM,789076.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,13,scalarAdvection,OpenFOAM,1080210.0,OpenFOAM,implicit-time-integration,0.7304838873922663 +3DCube,N32,14,scalarAdvection,SerialExecutor,556215.0,NeoN,explicit-time-integration,1.4186528590563001 +3DCube,N32,15,scalarAdvection,SerialExecutor,3056060.0,NeoN,implicit-time-integration,0.25820042800206805 +3DCube,N32,16,scalarAdvection,GPUExecutor,616662.0,NeoN,explicit-time-integration,1.2795923861045435 +3DCube,N32,17,scalarAdvection,GPUExecutor,1323380.0,NeoN,implicit-time-integration,0.59625806646617 +3DCube,N64,30,scalarAdvection,OpenFOAM,7567010.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,31,scalarAdvection,OpenFOAM,12539500.0,OpenFOAM,implicit-time-integration,0.6034538857211212 +3DCube,N64,32,scalarAdvection,SerialExecutor,3138550.0,NeoN,explicit-time-integration,2.4109891510410857 +3DCube,N64,33,scalarAdvection,SerialExecutor,25016100.0,NeoN,implicit-time-integration,0.3024855992740675 +3DCube,N64,34,scalarAdvection,GPUExecutor,869239.0,NeoN,explicit-time-integration,8.705327303537922 +3DCube,N64,35,scalarAdvection,GPUExecutor,1971070.0,NeoN,implicit-time-integration,3.8390366653644974 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/system-info.log b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/DivOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/DivOperator.csv new file mode 100644 index 0000000..8ee4f1e --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/DivOperator.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,36,DivOperator,OpenFOAM,84360.4,OpenFOAM,with Allocation,1.0 +2DSquare,N128,37,DivOperator,SerialExecutor,553848.0,NeoN,with Allocation,0.15231688116595166 +2DSquare,N128,38,DivOperator,SerialExecutor,484060.0,NeoN,No allocation,0.1742767425525761 +2DSquare,N16,18,DivOperator,OpenFOAM,2028.59,OpenFOAM,with Allocation,1.0 +2DSquare,N16,19,DivOperator,SerialExecutor,23332.6,NeoN,with Allocation,0.08694230390097975 +2DSquare,N16,20,DivOperator,SerialExecutor,17536.5,NeoN,No allocation,0.11567815698685598 +2DSquare,N256,54,DivOperator,OpenFOAM,593126.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,55,DivOperator,SerialExecutor,2302470.0,NeoN,with Allocation,0.2576042250279048 +2DSquare,N256,56,DivOperator,SerialExecutor,1937330.0,NeoN,No allocation,0.30615641114317127 +2DSquare,N32,12,DivOperator,OpenFOAM,4967.17,OpenFOAM,with Allocation,1.0 +2DSquare,N32,13,DivOperator,SerialExecutor,47184.4,NeoN,with Allocation,0.1052714456472902 +2DSquare,N32,14,DivOperator,SerialExecutor,39475.0,NeoN,No allocation,0.1258307789740342 +2DSquare,N512,24,DivOperator,OpenFOAM,2546700.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,25,DivOperator,SerialExecutor,9093820.0,NeoN,with Allocation,0.28004732884530376 +2DSquare,N512,26,DivOperator,SerialExecutor,7717730.0,NeoN,No allocation,0.3299804476186651 +2DSquare,N64,6,DivOperator,OpenFOAM,19787.3,OpenFOAM,with Allocation,1.0 +2DSquare,N64,7,DivOperator,SerialExecutor,136215.0,NeoN,with Allocation,0.14526520574092427 +2DSquare,N64,8,DivOperator,SerialExecutor,124624.0,NeoN,No allocation,0.1587759982025934 +2DSquare,N8,60,DivOperator,OpenFOAM,1097.82,OpenFOAM,with Allocation,1.0 +2DSquare,N8,61,DivOperator,SerialExecutor,17743.0,NeoN,with Allocation,0.0618734148678352 +2DSquare,N8,62,DivOperator,SerialExecutor,11452.0,NeoN,No allocation,0.0958627314006287 +3DCube,N128,30,DivOperator,OpenFOAM,59658800.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,31,DivOperator,SerialExecutor,172360000.0,NeoN,with Allocation,0.3461290322580645 +3DCube,N128,32,DivOperator,SerialExecutor,111892000.0,NeoN,No allocation,0.5331819969256069 +3DCube,N16,48,DivOperator,OpenFOAM,28109.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,49,DivOperator,SerialExecutor,204437.0,NeoN,with Allocation,0.13749565880931533 +3DCube,N16,50,DivOperator,SerialExecutor,188026.0,NeoN,No allocation,0.1494963462499867 +3DCube,N32,42,DivOperator,OpenFOAM,327878.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,43,DivOperator,SerialExecutor,1760610.0,NeoN,with Allocation,0.1862297726356206 +3DCube,N32,44,DivOperator,SerialExecutor,1514240.0,NeoN,No allocation,0.21652974429416738 +3DCube,N64,66,DivOperator,OpenFOAM,3495400.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,67,DivOperator,SerialExecutor,13709600.0,NeoN,with Allocation,0.25496002800956996 +3DCube,N64,68,DivOperator,SerialExecutor,11700000.0,NeoN,No allocation,0.29875213675213674 +3DCube,N8,0,DivOperator,OpenFOAM,4414.33,OpenFOAM,with Allocation,1.0 +3DCube,N8,1,DivOperator,SerialExecutor,40724.6,NeoN,with Allocation,0.10839468036518468 +3DCube,N8,2,DivOperator,SerialExecutor,34294.1,NeoN,No allocation,0.12871980894672844 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceInterpolation.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceInterpolation.csv new file mode 100644 index 0000000..beb2c90 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceInterpolation.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,99,FaceInterpolation,OpenFOAM,19285.1,OpenFOAM,with Allocation,1.0 +2DSquare,N128,100,FaceInterpolation,SerialExecutor,33603.4,NeoN,with Allocation,0.5739032359820732 +2DSquare,N128,101,FaceInterpolation,SerialExecutor,18179.3,NeoN,No allocation,1.060827424598307 +2DSquare,N16,54,FaceInterpolation,OpenFOAM,859.746,OpenFOAM,with Allocation,1.0 +2DSquare,N16,55,FaceInterpolation,SerialExecutor,9181.35,NeoN,with Allocation,0.09364047770752666 +2DSquare,N16,56,FaceInterpolation,SerialExecutor,440.139,NeoN,No allocation,1.953351100447813 +2DSquare,N256,144,FaceInterpolation,OpenFOAM,155270.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,145,FaceInterpolation,SerialExecutor,231694.0,NeoN,with Allocation,0.6701511476343798 +2DSquare,N256,146,FaceInterpolation,SerialExecutor,140132.0,NeoN,No allocation,1.1080267176662004 +2DSquare,N32,39,FaceInterpolation,OpenFOAM,1787.36,OpenFOAM,with Allocation,1.0 +2DSquare,N32,40,FaceInterpolation,SerialExecutor,11006.5,NeoN,with Allocation,0.16239131422341344 +2DSquare,N32,41,FaceInterpolation,SerialExecutor,1305.5,NeoN,No allocation,1.3690999617004977 +2DSquare,N512,69,FaceInterpolation,OpenFOAM,450996.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,70,FaceInterpolation,SerialExecutor,862633.0,NeoN,with Allocation,0.5228132937181861 +2DSquare,N512,71,FaceInterpolation,SerialExecutor,565333.0,NeoN,No allocation,0.7977528288636963 +2DSquare,N64,24,FaceInterpolation,OpenFOAM,5347.85,OpenFOAM,with Allocation,1.0 +2DSquare,N64,25,FaceInterpolation,SerialExecutor,15442.4,NeoN,with Allocation,0.3463095114749003 +2DSquare,N64,26,FaceInterpolation,SerialExecutor,4662.17,NeoN,No allocation,1.1470731440509463 +2DSquare,N8,159,FaceInterpolation,OpenFOAM,621.335,OpenFOAM,with Allocation,1.0 +2DSquare,N8,160,FaceInterpolation,SerialExecutor,8885.75,NeoN,with Allocation,0.06992487972315224 +2DSquare,N8,161,FaceInterpolation,SerialExecutor,235.413,NeoN,No allocation,2.6393402233521512 +3DCube,N128,84,FaceInterpolation,OpenFOAM,11272400.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,85,FaceInterpolation,SerialExecutor,15972200.0,NeoN,with Allocation,0.7057512427843378 +3DCube,N128,86,FaceInterpolation,SerialExecutor,8343780.0,NeoN,No allocation,1.350994393428398 +3DCube,N16,129,FaceInterpolation,OpenFOAM,7286.66,OpenFOAM,with Allocation,1.0 +3DCube,N16,130,FaceInterpolation,SerialExecutor,19675.9,NeoN,with Allocation,0.3703342667933868 +3DCube,N16,131,FaceInterpolation,SerialExecutor,7146.57,NeoN,No allocation,1.0196024106669352 +3DCube,N32,114,FaceInterpolation,OpenFOAM,81014.8,OpenFOAM,with Allocation,1.0 +3DCube,N32,115,FaceInterpolation,SerialExecutor,162538.0,NeoN,with Allocation,0.49843605802950697 +3DCube,N32,116,FaceInterpolation,SerialExecutor,94849.4,NeoN,No allocation,0.8541414073257185 +3DCube,N64,174,FaceInterpolation,OpenFOAM,812710.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,175,FaceInterpolation,SerialExecutor,1075200.0,NeoN,with Allocation,0.7558686755952381 +3DCube,N64,176,FaceInterpolation,SerialExecutor,653939.0,NeoN,No allocation,1.2427917588643589 +3DCube,N8,9,FaceInterpolation,OpenFOAM,1634.5,OpenFOAM,with Allocation,1.0 +3DCube,N8,10,FaceInterpolation,SerialExecutor,11071.7,NeoN,with Allocation,0.1476286387817589 +3DCube,N8,11,FaceInterpolation,SerialExecutor,1062.69,NeoN,No allocation,1.5380778966584798 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceNormalGradient.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceNormalGradient.csv new file mode 100644 index 0000000..d1db0dd --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/FaceNormalGradient.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,102,FaceNormalGradient,OpenFOAM,18435.9,OpenFOAM,with Allocation,1.0 +2DSquare,N128,103,FaceNormalGradient,SerialExecutor,33113.7,NeoN,with Allocation,0.556745395410359 +2DSquare,N128,104,FaceNormalGradient,SerialExecutor,17967.3,NeoN,No allocation,1.026080713295821 +2DSquare,N16,57,FaceNormalGradient,OpenFOAM,968.776,OpenFOAM,with Allocation,1.0 +2DSquare,N16,58,FaceNormalGradient,SerialExecutor,9461.17,NeoN,with Allocation,0.10239494692516887 +2DSquare,N16,59,FaceNormalGradient,SerialExecutor,392.471,NeoN,No allocation,2.4684014869888475 +2DSquare,N256,147,FaceNormalGradient,OpenFOAM,129162.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,148,FaceNormalGradient,SerialExecutor,188902.0,NeoN,with Allocation,0.6837513631406761 +2DSquare,N256,149,FaceNormalGradient,SerialExecutor,124806.0,NeoN,No allocation,1.0349021681649921 +2DSquare,N32,42,FaceNormalGradient,OpenFOAM,1841.27,OpenFOAM,with Allocation,1.0 +2DSquare,N32,43,FaceNormalGradient,SerialExecutor,10842.7,NeoN,with Allocation,0.1698165586062512 +2DSquare,N32,44,FaceNormalGradient,SerialExecutor,1280.18,NeoN,No allocation,1.438289927978878 +2DSquare,N512,72,FaceNormalGradient,OpenFOAM,537550.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,73,FaceNormalGradient,SerialExecutor,705789.0,NeoN,with Allocation,0.7616298922199127 +2DSquare,N512,74,FaceNormalGradient,SerialExecutor,539874.0,NeoN,No allocation,0.995695291864398 +2DSquare,N64,27,FaceNormalGradient,OpenFOAM,5265.41,OpenFOAM,with Allocation,1.0 +2DSquare,N64,28,FaceNormalGradient,SerialExecutor,15313.6,NeoN,with Allocation,0.343838809946714 +2DSquare,N64,29,FaceNormalGradient,SerialExecutor,4670.59,NeoN,No allocation,1.1273543599416775 +2DSquare,N8,162,FaceNormalGradient,OpenFOAM,756.308,OpenFOAM,with Allocation,1.0 +2DSquare,N8,163,FaceNormalGradient,SerialExecutor,8914.73,NeoN,with Allocation,0.08483801528481513 +2DSquare,N8,164,FaceNormalGradient,SerialExecutor,203.236,NeoN,No allocation,3.721328898423508 +3DCube,N128,87,FaceNormalGradient,OpenFOAM,11313600.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,88,FaceNormalGradient,SerialExecutor,14825200.0,NeoN,with Allocation,0.7631330437363408 +3DCube,N128,89,FaceNormalGradient,SerialExecutor,8560000.0,NeoN,No allocation,1.3216822429906543 +3DCube,N16,132,FaceNormalGradient,OpenFOAM,7745.47,OpenFOAM,with Allocation,1.0 +3DCube,N16,133,FaceNormalGradient,SerialExecutor,19666.8,NeoN,with Allocation,0.39383478756076234 +3DCube,N16,134,FaceNormalGradient,SerialExecutor,7170.19,NeoN,No allocation,1.0802321835265176 +3DCube,N32,117,FaceNormalGradient,OpenFOAM,89618.5,OpenFOAM,with Allocation,1.0 +3DCube,N32,118,FaceNormalGradient,SerialExecutor,170094.0,NeoN,with Allocation,0.5268763154491046 +3DCube,N32,119,FaceNormalGradient,SerialExecutor,85428.0,NeoN,No allocation,1.0490530036990213 +3DCube,N64,177,FaceNormalGradient,OpenFOAM,819891.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,178,FaceNormalGradient,SerialExecutor,1218230.0,NeoN,with Allocation,0.6730182313684608 +3DCube,N64,179,FaceNormalGradient,SerialExecutor,744102.0,NeoN,No allocation,1.1018529717699992 +3DCube,N8,12,FaceNormalGradient,OpenFOAM,1801.66,OpenFOAM,with Allocation,1.0 +3DCube,N8,13,FaceNormalGradient,SerialExecutor,10837.9,NeoN,with Allocation,0.16623700163315772 +3DCube,N8,14,FaceNormalGradient,SerialExecutor,982.275,NeoN,No allocation,1.8341706752182434 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/GradOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/GradOperator.csv new file mode 100644 index 0000000..3f93edf --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/GradOperator.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,96,GradOperator,OpenFOAM,119461.0,OpenFOAM,with Allocation,1.0 +2DSquare,N128,97,GradOperator,SerialExecutor,833036.0,NeoN,with Allocation,0.14340436667803072 +2DSquare,N128,98,GradOperator,SerialExecutor,800520.0,NeoN,No allocation,0.14922925098685855 +2DSquare,N16,51,GradOperator,OpenFOAM,3596.84,OpenFOAM,with Allocation,1.0 +2DSquare,N16,52,GradOperator,SerialExecutor,31061.3,NeoN,with Allocation,0.11579811533966705 +2DSquare,N16,53,GradOperator,SerialExecutor,20794.2,NeoN,No allocation,0.17297323292071828 +2DSquare,N256,141,GradOperator,OpenFOAM,555567.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,142,GradOperator,SerialExecutor,3314700.0,NeoN,with Allocation,0.16760702326002352 +2DSquare,N256,143,GradOperator,SerialExecutor,3224840.0,NeoN,No allocation,0.1722773843043376 +2DSquare,N32,36,GradOperator,OpenFOAM,8843.06,OpenFOAM,with Allocation,1.0 +2DSquare,N32,37,GradOperator,SerialExecutor,68134.1,NeoN,with Allocation,0.12978904836198024 +2DSquare,N32,38,GradOperator,SerialExecutor,57727.1,NeoN,No allocation,0.15318732449750636 +2DSquare,N512,66,GradOperator,OpenFOAM,2015650.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,67,GradOperator,SerialExecutor,13184400.0,NeoN,with Allocation,0.15288143563605472 +2DSquare,N512,68,GradOperator,SerialExecutor,12865700.0,NeoN,No allocation,0.15666850618310701 +2DSquare,N64,21,GradOperator,OpenFOAM,28827.0,OpenFOAM,with Allocation,1.0 +2DSquare,N64,22,GradOperator,SerialExecutor,214194.0,NeoN,with Allocation,0.1345836017815625 +2DSquare,N64,23,GradOperator,SerialExecutor,202846.0,NeoN,No allocation,0.142112735769993 +2DSquare,N8,156,GradOperator,OpenFOAM,1901.7,OpenFOAM,with Allocation,1.0 +2DSquare,N8,157,GradOperator,SerialExecutor,21306.9,NeoN,with Allocation,0.08925277726933528 +2DSquare,N8,158,GradOperator,SerialExecutor,11888.7,NeoN,No allocation,0.1599586161649297 +3DCube,N128,81,GradOperator,OpenFOAM,45928600.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,82,GradOperator,SerialExecutor,172686000.0,NeoN,with Allocation,0.26596597292195084 +3DCube,N128,83,GradOperator,SerialExecutor,165175000.0,NeoN,No allocation,0.27806023914030575 +3DCube,N16,126,GradOperator,OpenFOAM,47119.7,OpenFOAM,with Allocation,1.0 +3DCube,N16,127,GradOperator,SerialExecutor,312235.0,NeoN,with Allocation,0.15091101253863276 +3DCube,N16,128,GradOperator,SerialExecutor,299942.0,NeoN,No allocation,0.15709603856745635 +3DCube,N32,111,GradOperator,OpenFOAM,410905.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,112,GradOperator,SerialExecutor,2488670.0,NeoN,with Allocation,0.16511027978799922 +3DCube,N32,113,GradOperator,SerialExecutor,2439910.0,NeoN,No allocation,0.16840990036517742 +3DCube,N64,171,GradOperator,OpenFOAM,2977950.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,172,GradOperator,SerialExecutor,19703500.0,NeoN,with Allocation,0.15113812266856141 +3DCube,N64,173,GradOperator,SerialExecutor,19268500.0,NeoN,No allocation,0.15455017256143447 +3DCube,N8,6,GradOperator,OpenFOAM,9461.48,OpenFOAM,with Allocation,1.0 +3DCube,N8,7,GradOperator,SerialExecutor,55967.9,NeoN,with Allocation,0.16905190296580716 +3DCube,N8,8,GradOperator,SerialExecutor,46037.9,NeoN,No allocation,0.20551502131939117 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/LaplacianOperator.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/LaplacianOperator.csv new file mode 100644 index 0000000..d9dd837 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/LaplacianOperator.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,39,LaplacianOperator,OpenFOAM,70530.8,OpenFOAM,with Allocation,1.0 +2DSquare,N128,40,LaplacianOperator,SerialExecutor,1701810.0,NeoN,with Allocation,0.04144457959466686 +2DSquare,N128,41,LaplacianOperator,SerialExecutor,454632.0,NeoN,No allocation,0.15513822168259164 +2DSquare,N16,21,LaplacianOperator,OpenFOAM,2709.27,OpenFOAM,with Allocation,1.0 +2DSquare,N16,22,LaplacianOperator,SerialExecutor,49644.9,NeoN,with Allocation,0.054572977284675764 +2DSquare,N16,23,LaplacianOperator,SerialExecutor,7582.19,NeoN,No allocation,0.3573202465250805 +2DSquare,N256,57,LaplacianOperator,OpenFOAM,428804.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,58,LaplacianOperator,SerialExecutor,7015030.0,NeoN,with Allocation,0.06112646702865134 +2DSquare,N256,59,LaplacianOperator,SerialExecutor,1867490.0,NeoN,No allocation,0.22961515188836354 +2DSquare,N32,15,LaplacianOperator,OpenFOAM,5374.06,OpenFOAM,with Allocation,1.0 +2DSquare,N32,16,LaplacianOperator,SerialExecutor,122222.0,NeoN,with Allocation,0.04396966176302139 +2DSquare,N32,17,LaplacianOperator,SerialExecutor,28878.0,NeoN,No allocation,0.18609529745827275 +2DSquare,N512,27,LaplacianOperator,OpenFOAM,1799340.0,OpenFOAM,with Allocation,1.0 +2DSquare,N512,28,LaplacianOperator,SerialExecutor,28120900.0,NeoN,with Allocation,0.0639858610499664 +2DSquare,N512,29,LaplacianOperator,SerialExecutor,7387230.0,NeoN,No allocation,0.24357438444450763 +2DSquare,N64,9,LaplacianOperator,OpenFOAM,16501.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,10,LaplacianOperator,SerialExecutor,420369.0,NeoN,with Allocation,0.03925408391199161 +2DSquare,N64,11,LaplacianOperator,SerialExecutor,112695.0,NeoN,No allocation,0.1464235325435911 +2DSquare,N8,63,LaplacianOperator,OpenFOAM,1832.02,OpenFOAM,with Allocation,1.0 +2DSquare,N8,64,LaplacianOperator,SerialExecutor,29204.1,NeoN,with Allocation,0.06273160275440777 +2DSquare,N8,65,LaplacianOperator,SerialExecutor,2242.14,NeoN,No allocation,0.8170854629951743 +3DCube,N128,33,LaplacianOperator,OpenFOAM,46356000.0,OpenFOAM,with Allocation,1.0 +3DCube,N128,34,LaplacianOperator,SerialExecutor,441804000.0,NeoN,with Allocation,0.10492435559659939 +3DCube,N128,35,LaplacianOperator,SerialExecutor,97205100.0,NeoN,No allocation,0.47688855831638466 +3DCube,N16,51,LaplacianOperator,OpenFOAM,24707.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,52,LaplacianOperator,SerialExecutor,603373.0,NeoN,with Allocation,0.040948468028897546 +3DCube,N16,53,LaplacianOperator,SerialExecutor,173675.0,NeoN,No allocation,0.1422611199078739 +3DCube,N32,45,LaplacianOperator,OpenFOAM,338335.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,46,LaplacianOperator,SerialExecutor,5140740.0,NeoN,with Allocation,0.0658144547283076 +3DCube,N32,47,LaplacianOperator,SerialExecutor,1410470.0,NeoN,No allocation,0.23987394272831042 +3DCube,N64,69,LaplacianOperator,OpenFOAM,2613280.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,70,LaplacianOperator,SerialExecutor,41928500.0,NeoN,with Allocation,0.06232705677522449 +3DCube,N64,71,LaplacianOperator,SerialExecutor,11123800.0,NeoN,No allocation,0.23492691346482317 +3DCube,N8,3,LaplacianOperator,OpenFOAM,5271.94,OpenFOAM,with Allocation,1.0 +3DCube,N8,4,LaplacianOperator,SerialExecutor,92753.2,NeoN,with Allocation,0.05683836245002868 +3DCube,N8,5,LaplacianOperator,SerialExecutor,22933.3,NeoN,No allocation,0.22988143878116102 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/Poisson.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/Poisson.csv new file mode 100644 index 0000000..acfc203 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/Poisson.csv @@ -0,0 +1,25 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,12,Poisson,OpenFOAM,165142.0,OpenFOAM,Poisson,1.0 +2DSquare,N128,13,Poisson,SerialExecutor,97011.3,NeoN,Poisson,1.7022965365890366 +2DSquare,N16,6,Poisson,OpenFOAM,5215.53,OpenFOAM,Poisson,1.0 +2DSquare,N16,7,Poisson,SerialExecutor,17860.8,NeoN,Poisson,0.2920098763773179 +2DSquare,N256,18,Poisson,OpenFOAM,818148.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,19,Poisson,SerialExecutor,501971.0,NeoN,Poisson,1.629871048327493 +2DSquare,N32,4,Poisson,OpenFOAM,11131.5,OpenFOAM,Poisson,1.0 +2DSquare,N32,5,Poisson,SerialExecutor,20615.2,NeoN,Poisson,0.5399656564088633 +2DSquare,N512,8,Poisson,OpenFOAM,3220400.0,OpenFOAM,Poisson,1.0 +2DSquare,N512,9,Poisson,SerialExecutor,1988540.0,NeoN,Poisson,1.6194796182123568 +2DSquare,N64,2,Poisson,OpenFOAM,41996.2,OpenFOAM,Poisson,1.0 +2DSquare,N64,3,Poisson,SerialExecutor,28762.6,NeoN,Poisson,1.4600974877097341 +2DSquare,N8,20,Poisson,OpenFOAM,3209.31,OpenFOAM,Poisson,1.0 +2DSquare,N8,21,Poisson,SerialExecutor,16794.7,NeoN,Poisson,0.1910906416905333 +3DCube,N128,10,Poisson,OpenFOAM,86786000.0,OpenFOAM,Poisson,1.0 +3DCube,N128,11,Poisson,SerialExecutor,74572800.0,NeoN,Poisson,1.163775532097494 +3DCube,N16,16,Poisson,OpenFOAM,52973.2,OpenFOAM,Poisson,1.0 +3DCube,N16,17,Poisson,SerialExecutor,32947.0,NeoN,Poisson,1.6078307584909095 +3DCube,N32,14,Poisson,OpenFOAM,590198.0,OpenFOAM,Poisson,1.0 +3DCube,N32,15,Poisson,SerialExecutor,370701.0,NeoN,Poisson,1.5921133204388442 +3DCube,N64,22,Poisson,OpenFOAM,4625820.0,OpenFOAM,Poisson,1.0 +3DCube,N64,23,Poisson,SerialExecutor,2509390.0,NeoN,Poisson,1.8434041739227462 +3DCube,N8,0,Poisson,OpenFOAM,10642.1,OpenFOAM,Poisson,1.0 +3DCube,N8,1,Poisson,SerialExecutor,19310.1,NeoN,Poisson,0.5511157373602416 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/momentum.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/momentum.csv new file mode 100644 index 0000000..0656695 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/momentum.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,24,momentum,OpenFOAM,433441.0,OpenFOAM,without RHS,1.0 +2DSquare,N128,25,momentum,OpenFOAM,680059.0,OpenFOAM,with RHS,0.6373579351203351 +2DSquare,N128,26,momentum,SerialExecutor,2192180.0,NeoN,without RHS,0.19772144623160506 +2DSquare,N128,27,momentum,SerialExecutor,4057920.0,NeoN,with RHS,0.10681358922797887 +2DSquare,N16,12,momentum,OpenFOAM,10445.6,OpenFOAM,without RHS,1.0 +2DSquare,N16,13,momentum,OpenFOAM,15180.3,OpenFOAM,with RHS,0.6881023431684486 +2DSquare,N16,14,momentum,SerialExecutor,66171.4,NeoN,without RHS,0.15785671755471398 +2DSquare,N16,15,momentum,SerialExecutor,107258.0,NeoN,with RHS,0.09738760745119246 +2DSquare,N256,36,momentum,OpenFOAM,2290000.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,37,momentum,OpenFOAM,3267300.0,OpenFOAM,with RHS,0.7008845223885165 +2DSquare,N256,38,momentum,SerialExecutor,8479590.0,NeoN,without RHS,0.2700602269685209 +2DSquare,N256,39,momentum,SerialExecutor,15980000.0,NeoN,with RHS,0.14330413016270338 +2DSquare,N32,8,momentum,OpenFOAM,23634.9,OpenFOAM,without RHS,1.0 +2DSquare,N32,9,momentum,OpenFOAM,35774.7,OpenFOAM,with RHS,0.6606596281729826 +2DSquare,N32,10,momentum,SerialExecutor,156152.0,NeoN,without RHS,0.15135829192069267 +2DSquare,N32,11,momentum,SerialExecutor,277227.0,NeoN,with RHS,0.0852546829854235 +2DSquare,N512,16,momentum,OpenFOAM,9888590.0,OpenFOAM,without RHS,1.0 +2DSquare,N512,17,momentum,OpenFOAM,14620700.0,OpenFOAM,with RHS,0.6763417620223382 +2DSquare,N512,18,momentum,SerialExecutor,37640500.0,NeoN,without RHS,0.26271144113388506 +2DSquare,N512,19,momentum,SerialExecutor,68520000.0,NeoN,with RHS,0.14431684179801518 +2DSquare,N64,4,momentum,OpenFOAM,80162.5,OpenFOAM,without RHS,1.0 +2DSquare,N64,5,momentum,OpenFOAM,128199.0,OpenFOAM,with RHS,0.6252973892152045 +2DSquare,N64,6,momentum,SerialExecutor,532849.0,NeoN,without RHS,0.1504413070119302 +2DSquare,N64,7,momentum,SerialExecutor,979213.0,NeoN,with RHS,0.08186421136157301 +2DSquare,N8,40,momentum,OpenFOAM,6377.38,OpenFOAM,without RHS,1.0 +2DSquare,N8,41,momentum,OpenFOAM,9104.54,OpenFOAM,with RHS,0.7004615279849393 +2DSquare,N8,42,momentum,SerialExecutor,42834.4,NeoN,without RHS,0.14888454139663448 +2DSquare,N8,43,momentum,SerialExecutor,63610.9,NeoN,with RHS,0.1002560881861442 +3DCube,N128,20,momentum,OpenFOAM,247766000.0,OpenFOAM,without RHS,1.0 +3DCube,N128,21,momentum,OpenFOAM,348226000.0,OpenFOAM,with RHS,0.711509192306146 +3DCube,N128,22,momentum,SerialExecutor,612350000.0,NeoN,without RHS,0.4046150077570017 +3DCube,N128,23,momentum,SerialExecutor,1086940000.0,NeoN,with RHS,0.22794818481240914 +3DCube,N16,32,momentum,OpenFOAM,121316.0,OpenFOAM,without RHS,1.0 +3DCube,N16,33,momentum,OpenFOAM,211430.0,OpenFOAM,with RHS,0.573788014945845 +3DCube,N16,34,momentum,SerialExecutor,822362.0,NeoN,without RHS,0.14752140784715248 +3DCube,N16,35,momentum,SerialExecutor,1545020.0,NeoN,with RHS,0.07852066639914046 +3DCube,N32,28,momentum,OpenFOAM,1436020.0,OpenFOAM,without RHS,1.0 +3DCube,N32,29,momentum,OpenFOAM,2063560.0,OpenFOAM,with RHS,0.695894473628099 +3DCube,N32,30,momentum,SerialExecutor,6345990.0,NeoN,without RHS,0.2262877817330314 +3DCube,N32,31,momentum,SerialExecutor,12087400.0,NeoN,with RHS,0.11880305111107434 +3DCube,N64,44,momentum,OpenFOAM,13019500.0,OpenFOAM,without RHS,1.0 +3DCube,N64,45,momentum,OpenFOAM,19819000.0,OpenFOAM,with RHS,0.6569201271507139 +3DCube,N64,46,momentum,SerialExecutor,64757900.0,NeoN,without RHS,0.2010488295636517 +3DCube,N64,47,momentum,SerialExecutor,117074000.0,NeoN,with RHS,0.11120744144728975 +3DCube,N8,0,momentum,OpenFOAM,21444.2,OpenFOAM,without RHS,1.0 +3DCube,N8,1,momentum,OpenFOAM,33247.4,OpenFOAM,with RHS,0.6449887810776181 +3DCube,N8,2,momentum,SerialExecutor,132070.0,NeoN,without RHS,0.1623699553267207 +3DCube,N8,3,momentum,SerialExecutor,232818.0,NeoN,with RHS,0.09210713948234243 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/pressureVelocityCoupling.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/pressureVelocityCoupling.csv new file mode 100644 index 0000000..d3ba4b9 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/pressureVelocityCoupling.csv @@ -0,0 +1,73 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,36,pressureVelocityCoupling,CPU,25142.8,OpenFOAM,Compute rAU, +2DSquare,N128,37,pressureVelocityCoupling,CPU,244183.0,OpenFOAM,Compute HbyA, +2DSquare,N128,38,pressureVelocityCoupling,CPU,246184.0,OpenFOAM,constrainHbyA, +2DSquare,N128,39,pressureVelocityCoupling,SerialExecutor,211735.0,NeoN,Compute rAU, +2DSquare,N128,40,pressureVelocityCoupling,SerialExecutor,355663.0,NeoN,Compute HbyA, +2DSquare,N128,41,pressureVelocityCoupling,SerialExecutor,60.2221,NeoN,constrainHbyA, +2DSquare,N16,18,pressureVelocityCoupling,CPU,1362.51,OpenFOAM,Compute rAU, +2DSquare,N16,19,pressureVelocityCoupling,CPU,4644.38,OpenFOAM,Compute HbyA, +2DSquare,N16,20,pressureVelocityCoupling,CPU,4510.01,OpenFOAM,constrainHbyA, +2DSquare,N16,21,pressureVelocityCoupling,SerialExecutor,11357.7,NeoN,Compute rAU, +2DSquare,N16,22,pressureVelocityCoupling,SerialExecutor,35537.7,NeoN,Compute HbyA, +2DSquare,N16,23,pressureVelocityCoupling,SerialExecutor,60.2576,NeoN,constrainHbyA, +2DSquare,N256,54,pressureVelocityCoupling,CPU,101244.0,OpenFOAM,Compute rAU, +2DSquare,N256,55,pressureVelocityCoupling,CPU,1245500.0,OpenFOAM,Compute HbyA, +2DSquare,N256,56,pressureVelocityCoupling,CPU,1322560.0,OpenFOAM,constrainHbyA, +2DSquare,N256,57,pressureVelocityCoupling,SerialExecutor,667475.0,NeoN,Compute rAU, +2DSquare,N256,58,pressureVelocityCoupling,SerialExecutor,1515070.0,NeoN,Compute HbyA, +2DSquare,N256,59,pressureVelocityCoupling,SerialExecutor,60.5364,NeoN,constrainHbyA, +2DSquare,N32,12,pressureVelocityCoupling,CPU,2494.4,OpenFOAM,Compute rAU, +2DSquare,N32,13,pressureVelocityCoupling,CPU,14165.8,OpenFOAM,Compute HbyA, +2DSquare,N32,14,pressureVelocityCoupling,CPU,14191.0,OpenFOAM,constrainHbyA, +2DSquare,N32,15,pressureVelocityCoupling,SerialExecutor,14936.7,NeoN,Compute rAU, +2DSquare,N32,16,pressureVelocityCoupling,SerialExecutor,45367.0,NeoN,Compute HbyA, +2DSquare,N32,17,pressureVelocityCoupling,SerialExecutor,60.5086,NeoN,constrainHbyA, +2DSquare,N512,24,pressureVelocityCoupling,CPU,558251.0,OpenFOAM,Compute rAU, +2DSquare,N512,25,pressureVelocityCoupling,CPU,5635510.0,OpenFOAM,Compute HbyA, +2DSquare,N512,26,pressureVelocityCoupling,CPU,5467760.0,OpenFOAM,constrainHbyA, +2DSquare,N512,27,pressureVelocityCoupling,SerialExecutor,2730270.0,NeoN,Compute rAU, +2DSquare,N512,28,pressureVelocityCoupling,SerialExecutor,5955750.0,NeoN,Compute HbyA, +2DSquare,N512,29,pressureVelocityCoupling,SerialExecutor,61.6859,NeoN,constrainHbyA, +2DSquare,N64,6,pressureVelocityCoupling,CPU,7408.84,OpenFOAM,Compute rAU, +2DSquare,N64,7,pressureVelocityCoupling,CPU,52811.0,OpenFOAM,Compute HbyA, +2DSquare,N64,8,pressureVelocityCoupling,CPU,52793.7,OpenFOAM,constrainHbyA, +2DSquare,N64,9,pressureVelocityCoupling,SerialExecutor,26925.6,NeoN,Compute rAU, +2DSquare,N64,10,pressureVelocityCoupling,SerialExecutor,85108.2,NeoN,Compute HbyA, +2DSquare,N64,11,pressureVelocityCoupling,SerialExecutor,58.9861,NeoN,constrainHbyA, +2DSquare,N8,60,pressureVelocityCoupling,CPU,1023.33,OpenFOAM,Compute rAU, +2DSquare,N8,61,pressureVelocityCoupling,CPU,2204.37,OpenFOAM,Compute HbyA, +2DSquare,N8,62,pressureVelocityCoupling,CPU,2140.92,OpenFOAM,constrainHbyA, +2DSquare,N8,63,pressureVelocityCoupling,SerialExecutor,10386.0,NeoN,Compute rAU, +2DSquare,N8,64,pressureVelocityCoupling,SerialExecutor,30508.1,NeoN,Compute HbyA, +2DSquare,N8,65,pressureVelocityCoupling,SerialExecutor,60.5651,NeoN,constrainHbyA, +3DCube,N128,30,pressureVelocityCoupling,CPU,5301770.0,OpenFOAM,Compute rAU, +3DCube,N128,31,pressureVelocityCoupling,CPU,94564400.0,OpenFOAM,Compute HbyA, +3DCube,N128,32,pressureVelocityCoupling,CPU,95032100.0,OpenFOAM,constrainHbyA, +3DCube,N128,33,pressureVelocityCoupling,SerialExecutor,88367800.0,NeoN,Compute rAU, +3DCube,N128,34,pressureVelocityCoupling,SerialExecutor,162857000.0,NeoN,Compute HbyA, +3DCube,N128,35,pressureVelocityCoupling,SerialExecutor,32948.6,NeoN,constrainHbyA, +3DCube,N16,48,pressureVelocityCoupling,CPU,10492.2,OpenFOAM,Compute rAU, +3DCube,N16,49,pressureVelocityCoupling,CPU,69958.8,OpenFOAM,Compute HbyA, +3DCube,N16,50,pressureVelocityCoupling,CPU,70899.1,OpenFOAM,constrainHbyA, +3DCube,N16,51,pressureVelocityCoupling,SerialExecutor,36443.8,NeoN,Compute rAU, +3DCube,N16,52,pressureVelocityCoupling,SerialExecutor,121726.0,NeoN,Compute HbyA, +3DCube,N16,53,pressureVelocityCoupling,SerialExecutor,270.071,NeoN,constrainHbyA, +3DCube,N32,42,pressureVelocityCoupling,CPU,70537.2,OpenFOAM,Compute rAU, +3DCube,N32,43,pressureVelocityCoupling,CPU,721623.0,OpenFOAM,Compute HbyA, +3DCube,N32,44,pressureVelocityCoupling,CPU,739790.0,OpenFOAM,constrainHbyA, +3DCube,N32,45,pressureVelocityCoupling,SerialExecutor,588121.0,NeoN,Compute rAU, +3DCube,N32,46,pressureVelocityCoupling,SerialExecutor,1078850.0,NeoN,Compute HbyA, +3DCube,N32,47,pressureVelocityCoupling,SerialExecutor,1862.15,NeoN,constrainHbyA, +3DCube,N64,66,pressureVelocityCoupling,CPU,673090.0,OpenFOAM,Compute rAU, +3DCube,N64,67,pressureVelocityCoupling,CPU,7614650.0,OpenFOAM,Compute HbyA, +3DCube,N64,68,pressureVelocityCoupling,CPU,7533420.0,OpenFOAM,constrainHbyA, +3DCube,N64,69,pressureVelocityCoupling,SerialExecutor,3801310.0,NeoN,Compute rAU, +3DCube,N64,70,pressureVelocityCoupling,SerialExecutor,8744690.0,NeoN,Compute HbyA, +3DCube,N64,71,pressureVelocityCoupling,SerialExecutor,6982.32,NeoN,constrainHbyA, +3DCube,N8,0,pressureVelocityCoupling,CPU,2548.06,OpenFOAM,Compute rAU, +3DCube,N8,1,pressureVelocityCoupling,CPU,11084.5,OpenFOAM,Compute HbyA, +3DCube,N8,2,pressureVelocityCoupling,CPU,10609.5,OpenFOAM,constrainHbyA, +3DCube,N8,3,pressureVelocityCoupling,SerialExecutor,13520.8,NeoN,Compute rAU, +3DCube,N8,4,pressureVelocityCoupling,SerialExecutor,42769.7,NeoN,Compute HbyA, +3DCube,N8,5,pressureVelocityCoupling,SerialExecutor,129.954,NeoN,constrainHbyA, diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/scalarAdvection.csv b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/scalarAdvection.csv new file mode 100644 index 0000000..182e9b1 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/scalarAdvection.csv @@ -0,0 +1,49 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N128,24,scalarAdvection,OpenFOAM,222292.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N128,25,scalarAdvection,OpenFOAM,288422.0,OpenFOAM,implicit-time-integration,0.7707179064010373 +2DSquare,N128,26,scalarAdvection,SerialExecutor,158405.0,NeoN,explicit-time-integration,1.4033142893216755 +2DSquare,N128,27,scalarAdvection,SerialExecutor,1029040.0,NeoN,implicit-time-integration,0.21601881365155873 +2DSquare,N16,12,scalarAdvection,OpenFOAM,8150.44,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,13,scalarAdvection,OpenFOAM,7641.13,OpenFOAM,implicit-time-integration,1.066653754091345 +2DSquare,N16,14,scalarAdvection,SerialExecutor,21643.7,NeoN,explicit-time-integration,0.37657332156701484 +2DSquare,N16,15,scalarAdvection,SerialExecutor,41376.9,NeoN,implicit-time-integration,0.19698044077734192 +2DSquare,N256,36,scalarAdvection,OpenFOAM,1071030.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,37,scalarAdvection,OpenFOAM,1508060.0,OpenFOAM,implicit-time-integration,0.7102038380435791 +2DSquare,N256,38,scalarAdvection,SerialExecutor,695649.0,NeoN,explicit-time-integration,1.5396126494827134 +2DSquare,N256,39,scalarAdvection,SerialExecutor,4209240.0,NeoN,implicit-time-integration,0.2544473586680731 +2DSquare,N32,8,scalarAdvection,OpenFOAM,16987.6,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N32,9,scalarAdvection,OpenFOAM,16110.9,OpenFOAM,implicit-time-integration,1.0544165751137429 +2DSquare,N32,10,scalarAdvection,SerialExecutor,22377.3,NeoN,explicit-time-integration,0.7591443114227364 +2DSquare,N32,11,scalarAdvection,SerialExecutor,86246.3,NeoN,implicit-time-integration,0.19696613072097002 +2DSquare,N512,16,scalarAdvection,OpenFOAM,4740500.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N512,17,scalarAdvection,OpenFOAM,7093520.0,OpenFOAM,implicit-time-integration,0.6682859849552831 +2DSquare,N512,18,scalarAdvection,SerialExecutor,2411950.0,NeoN,explicit-time-integration,1.9654221687845934 +2DSquare,N512,19,scalarAdvection,SerialExecutor,16657300.0,NeoN,implicit-time-integration,0.28458993954602485 +2DSquare,N64,4,scalarAdvection,OpenFOAM,51102.8,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,5,scalarAdvection,OpenFOAM,56699.8,OpenFOAM,implicit-time-integration,0.9012871297605988 +2DSquare,N64,6,scalarAdvection,SerialExecutor,32860.0,NeoN,explicit-time-integration,1.555167376749848 +2DSquare,N64,7,scalarAdvection,SerialExecutor,264296.0,NeoN,implicit-time-integration,0.1933544208009202 +2DSquare,N8,40,scalarAdvection,OpenFOAM,5863.93,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N8,41,scalarAdvection,OpenFOAM,4760.22,OpenFOAM,implicit-time-integration,1.2318611324686675 +2DSquare,N8,42,scalarAdvection,SerialExecutor,16201.6,NeoN,explicit-time-integration,0.36193524096385543 +2DSquare,N8,43,scalarAdvection,SerialExecutor,29401.3,NeoN,implicit-time-integration,0.19944458238241167 +3DCube,N128,20,scalarAdvection,OpenFOAM,98687000.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N128,21,scalarAdvection,OpenFOAM,188698000.0,OpenFOAM,implicit-time-integration,0.5229891148819807 +3DCube,N128,22,scalarAdvection,SerialExecutor,84665100.0,NeoN,explicit-time-integration,1.1656160566750644 +3DCube,N128,23,scalarAdvection,SerialExecutor,267519000.0,NeoN,implicit-time-integration,0.36889716244453663 +3DCube,N16,32,scalarAdvection,OpenFOAM,75215.3,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,33,scalarAdvection,OpenFOAM,83487.5,OpenFOAM,implicit-time-integration,0.9009169037281031 +3DCube,N16,34,scalarAdvection,SerialExecutor,40324.8,NeoN,explicit-time-integration,1.8652367773677736 +3DCube,N16,35,scalarAdvection,SerialExecutor,395375.0,NeoN,implicit-time-integration,0.19023787543471388 +3DCube,N32,28,scalarAdvection,OpenFOAM,688393.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,29,scalarAdvection,OpenFOAM,1105600.0,OpenFOAM,implicit-time-integration,0.622642004341534 +3DCube,N32,30,scalarAdvection,SerialExecutor,479129.0,NeoN,explicit-time-integration,1.4367592026364506 +3DCube,N32,31,scalarAdvection,SerialExecutor,3189440.0,NeoN,implicit-time-integration,0.21583506822514298 +3DCube,N64,44,scalarAdvection,OpenFOAM,6459410.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,45,scalarAdvection,OpenFOAM,10026000.0,OpenFOAM,implicit-time-integration,0.6442659086375424 +3DCube,N64,46,scalarAdvection,SerialExecutor,3307230.0,NeoN,explicit-time-integration,1.9531178660087143 +3DCube,N64,47,scalarAdvection,SerialExecutor,25447600.0,NeoN,implicit-time-integration,0.25383179553278107 +3DCube,N8,0,scalarAdvection,OpenFOAM,15471.6,OpenFOAM,explicit-time-integration,1.0 +3DCube,N8,1,scalarAdvection,OpenFOAM,14777.4,OpenFOAM,implicit-time-integration,1.0469771407690123 +3DCube,N8,2,scalarAdvection,SerialExecutor,20081.7,NeoN,explicit-time-integration,0.7704327820851821 +3DCube,N8,3,scalarAdvection,SerialExecutor,73875.6,NeoN,implicit-time-integration,0.20942774068840048 diff --git a/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/system-info.log b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/system-info.log new file mode 100644 index 0000000..889cd65 --- /dev/null +++ b/NeoFOAM/201/neon-cluster-meta-runner-adapter-intel/system-info.log @@ -0,0 +1,62 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 52 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 224 +On-line CPU(s) list: 0-223 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Platinum 8480+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 56 +Socket(s): 2 +Stepping: 8 +CPU(s) scaling MHz: 36% +CPU max MHz: 3800.0000 +CPU min MHz: 800.0000 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 5.3 MiB (112 instances) +L1i cache: 3.5 MiB (112 instances) +L2 cache: 224 MiB (112 instances) +L3 cache: 210 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0-55,112-167 +NUMA node1 CPU(s): 56-111,168-223 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +No Intel GPU found or Level Zero runtime not available + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +No GPU compiler available diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/DivOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/DivOperator.csv new file mode 100644 index 0000000..343f3f5 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/DivOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,DivOperator,OpenFOAM,5154.7,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,55128.4,NeoN,with Allocation,0.09350352994101044 +2DSquare,N16,2,DivOperator,SerialExecutor,29370.1,NeoN,No allocation,0.17550842523518817 +2DSquare,N16,3,DivOperator,GPUExecutor,1358570.0,NeoN,with Allocation,0.003794210088548989 +2DSquare,N16,4,DivOperator,GPUExecutor,624519.0,NeoN,No allocation,0.00825387218002975 +2DSquare,N256,75,DivOperator,OpenFOAM,345425.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,DivOperator,SerialExecutor,403941.0,NeoN,with Allocation,0.855137260144427 +2DSquare,N256,77,DivOperator,SerialExecutor,380763.0,NeoN,No allocation,0.9071916126304289 +2DSquare,N256,78,DivOperator,GPUExecutor,1271310.0,NeoN,with Allocation,0.27170792332318633 +2DSquare,N256,79,DivOperator,GPUExecutor,664859.0,NeoN,No allocation,0.5195462496559421 +2DSquare,N64,100,DivOperator,OpenFOAM,18085.4,OpenFOAM,with Allocation,1.0 +2DSquare,N64,101,DivOperator,SerialExecutor,46940.4,NeoN,with Allocation,0.3852843179862123 +2DSquare,N64,102,DivOperator,SerialExecutor,32729.4,NeoN,No allocation,0.5525735271651787 +2DSquare,N64,103,DivOperator,GPUExecutor,1232920.0,NeoN,with Allocation,0.014668753852642508 +2DSquare,N64,104,DivOperator,GPUExecutor,623171.0,NeoN,No allocation,0.0290215687186984 +3DCube,N16,25,DivOperator,OpenFOAM,27268.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,DivOperator,SerialExecutor,56364.1,NeoN,with Allocation,0.483786665625815 +3DCube,N16,27,DivOperator,SerialExecutor,40901.1,NeoN,No allocation,0.6666862260428204 +3DCube,N16,28,DivOperator,GPUExecutor,1242940.0,NeoN,with Allocation,0.021938468469918097 +3DCube,N16,29,DivOperator,GPUExecutor,642872.0,NeoN,No allocation,0.042416219714033275 +3DCube,N32,50,DivOperator,OpenFOAM,254994.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,318782.0,NeoN,with Allocation,0.7999008726967018 +3DCube,N32,52,DivOperator,SerialExecutor,289743.0,NeoN,No allocation,0.8800695789026827 +3DCube,N32,53,DivOperator,GPUExecutor,1247350.0,NeoN,with Allocation,0.20442858860784863 +3DCube,N32,54,DivOperator,GPUExecutor,672377.0,NeoN,No allocation,0.3792425975308495 +3DCube,N64,125,DivOperator,OpenFOAM,2082780.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,126,DivOperator,SerialExecutor,2474800.0,NeoN,with Allocation,0.8415952804267012 +3DCube,N64,127,DivOperator,SerialExecutor,2250970.0,NeoN,No allocation,0.9252811010364421 +3DCube,N64,128,DivOperator,GPUExecutor,1492800.0,NeoN,with Allocation,1.395217041800643 +3DCube,N64,129,DivOperator,GPUExecutor,809823.0,NeoN,No allocation,2.5718953400928353 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv new file mode 100644 index 0000000..bb9191a --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,15,FaceInterpolation,OpenFOAM,876.643,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,FaceInterpolation,SerialExecutor,13628.3,NeoN,with Allocation,0.06432519096292275 +2DSquare,N16,17,FaceInterpolation,SerialExecutor,559.213,NeoN,No allocation,1.5676370184527186 +2DSquare,N16,18,FaceInterpolation,GPUExecutor,587884.0,NeoN,with Allocation,0.0014911836348667424 +2DSquare,N16,19,FaceInterpolation,GPUExecutor,16301.8,NeoN,No allocation,0.05377584070470746 +2DSquare,N256,90,FaceInterpolation,OpenFOAM,156217.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,FaceInterpolation,SerialExecutor,233153.0,NeoN,with Allocation,0.6700192577406252 +2DSquare,N256,92,FaceInterpolation,SerialExecutor,151931.0,NeoN,No allocation,1.028210174355464 +2DSquare,N256,93,FaceInterpolation,GPUExecutor,608197.0,NeoN,with Allocation,0.2568526316308696 +2DSquare,N256,94,FaceInterpolation,GPUExecutor,21675.8,NeoN,No allocation,7.206977366463983 +2DSquare,N64,115,FaceInterpolation,OpenFOAM,4890.3,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,FaceInterpolation,SerialExecutor,21378.6,NeoN,with Allocation,0.2287474390278129 +2DSquare,N64,117,FaceInterpolation,SerialExecutor,5408.21,NeoN,No allocation,0.9042363369765597 +2DSquare,N64,118,FaceInterpolation,GPUExecutor,624638.0,NeoN,with Allocation,0.007829014565236185 +2DSquare,N64,119,FaceInterpolation,GPUExecutor,18846.3,NeoN,No allocation,0.25948329380302765 +3DCube,N16,40,FaceInterpolation,OpenFOAM,7123.6,OpenFOAM,with Allocation,1.0 +3DCube,N16,41,FaceInterpolation,SerialExecutor,25652.5,NeoN,with Allocation,0.27769613098138585 +3DCube,N16,42,FaceInterpolation,SerialExecutor,8361.05,NeoN,No allocation,0.8519982538078352 +3DCube,N16,43,FaceInterpolation,GPUExecutor,612543.0,NeoN,with Allocation,0.01162955090499769 +3DCube,N16,44,FaceInterpolation,GPUExecutor,17433.1,NeoN,No allocation,0.40862497203595466 +3DCube,N32,65,FaceInterpolation,OpenFOAM,81250.9,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,FaceInterpolation,SerialExecutor,147011.0,NeoN,with Allocation,0.5526858534395385 +3DCube,N32,67,FaceInterpolation,SerialExecutor,77143.0,NeoN,No allocation,1.053250456943598 +3DCube,N32,68,FaceInterpolation,GPUExecutor,609272.0,NeoN,with Allocation,0.13335735106816002 +3DCube,N32,69,FaceInterpolation,GPUExecutor,20016.2,NeoN,No allocation,4.059257001828518 +3DCube,N64,140,FaceInterpolation,OpenFOAM,626415.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,141,FaceInterpolation,SerialExecutor,1041430.0,NeoN,with Allocation,0.6014950596775588 +3DCube,N64,142,FaceInterpolation,SerialExecutor,667697.0,NeoN,No allocation,0.9381725543173026 +3DCube,N64,143,FaceInterpolation,GPUExecutor,827979.0,NeoN,with Allocation,0.7565590431641382 +3DCube,N64,144,FaceInterpolation,GPUExecutor,36098.5,NeoN,No allocation,17.352937102649694 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv new file mode 100644 index 0000000..bbb4c2f --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,20,FaceNormalGradient,OpenFOAM,919.772,OpenFOAM,with Allocation,1.0 +2DSquare,N16,21,FaceNormalGradient,SerialExecutor,14306.2,NeoN,with Allocation,0.06429184549356223 +2DSquare,N16,22,FaceNormalGradient,SerialExecutor,444.354,NeoN,No allocation,2.069908226324057 +2DSquare,N16,23,FaceNormalGradient,GPUExecutor,595386.0,NeoN,with Allocation,0.001544833099871344 +2DSquare,N16,24,FaceNormalGradient,GPUExecutor,19525.9,NeoN,No allocation,0.047105229464454904 +2DSquare,N256,95,FaceNormalGradient,OpenFOAM,133594.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,FaceNormalGradient,SerialExecutor,244382.0,NeoN,with Allocation,0.5466605560147638 +2DSquare,N256,97,FaceNormalGradient,SerialExecutor,145036.0,NeoN,No allocation,0.9211092418434044 +2DSquare,N256,98,FaceNormalGradient,GPUExecutor,621618.0,NeoN,with Allocation,0.21491333906032323 +2DSquare,N256,99,FaceNormalGradient,GPUExecutor,28059.1,NeoN,No allocation,4.761164827097092 +2DSquare,N64,120,FaceNormalGradient,OpenFOAM,5161.61,OpenFOAM,with Allocation,1.0 +2DSquare,N64,121,FaceNormalGradient,SerialExecutor,20405.5,NeoN,with Allocation,0.2529519002229791 +2DSquare,N64,122,FaceNormalGradient,SerialExecutor,4625.38,NeoN,No allocation,1.1159320963899182 +2DSquare,N64,123,FaceNormalGradient,GPUExecutor,744868.0,NeoN,with Allocation,0.0069295633588770085 +2DSquare,N64,124,FaceNormalGradient,GPUExecutor,22290.7,NeoN,No allocation,0.23155890124581102 +3DCube,N16,45,FaceNormalGradient,OpenFOAM,7703.56,OpenFOAM,with Allocation,1.0 +3DCube,N16,46,FaceNormalGradient,SerialExecutor,23922.4,NeoN,with Allocation,0.32202287395913454 +3DCube,N16,47,FaceNormalGradient,SerialExecutor,7228.33,NeoN,No allocation,1.0657454764793528 +3DCube,N16,48,FaceNormalGradient,GPUExecutor,619272.0,NeoN,with Allocation,0.012439703393662236 +3DCube,N16,49,FaceNormalGradient,GPUExecutor,23152.9,NeoN,No allocation,0.3327254901113899 +3DCube,N32,70,FaceNormalGradient,OpenFOAM,71785.6,OpenFOAM,with Allocation,1.0 +3DCube,N32,71,FaceNormalGradient,SerialExecutor,155199.0,NeoN,with Allocation,0.46253906275169304 +3DCube,N32,72,FaceNormalGradient,SerialExecutor,79464.7,NeoN,No allocation,0.9033646386382885 +3DCube,N32,73,FaceNormalGradient,GPUExecutor,610835.0,NeoN,with Allocation,0.11752044332757619 +3DCube,N32,74,FaceNormalGradient,GPUExecutor,28091.2,NeoN,No allocation,2.5554479694708663 +3DCube,N64,145,FaceNormalGradient,OpenFOAM,724734.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,146,FaceNormalGradient,SerialExecutor,1247960.0,NeoN,with Allocation,0.5807349594538287 +3DCube,N64,147,FaceNormalGradient,SerialExecutor,749402.0,NeoN,No allocation,0.9670830875818319 +3DCube,N64,148,FaceNormalGradient,GPUExecutor,743455.0,NeoN,with Allocation,0.974818919773221 +3DCube,N64,149,FaceNormalGradient,GPUExecutor,44539.2,NeoN,No allocation,16.271823472356935 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/GradOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/GradOperator.csv new file mode 100644 index 0000000..ef6505d --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/GradOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,10,GradOperator,OpenFOAM,3483.53,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,GradOperator,SerialExecutor,39553.5,NeoN,with Allocation,0.0880713464042373 +2DSquare,N16,12,GradOperator,SerialExecutor,25134.9,NeoN,No allocation,0.13859335028187897 +2DSquare,N16,13,GradOperator,GPUExecutor,1201200.0,NeoN,with Allocation,0.002900041625041625 +2DSquare,N16,14,GradOperator,GPUExecutor,633100.0,NeoN,No allocation,0.0055023377033643975 +2DSquare,N256,85,GradOperator,OpenFOAM,570938.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,86,GradOperator,SerialExecutor,3226090.0,NeoN,with Allocation,0.17697522387782114 +2DSquare,N256,87,GradOperator,SerialExecutor,3099200.0,NeoN,No allocation,0.1842210893133712 +2DSquare,N256,88,GradOperator,GPUExecutor,1272760.0,NeoN,with Allocation,0.44858260787579746 +2DSquare,N256,89,GradOperator,GPUExecutor,672139.0,NeoN,No allocation,0.8494344175832678 +2DSquare,N64,110,GradOperator,OpenFOAM,27817.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,GradOperator,SerialExecutor,216669.0,NeoN,with Allocation,0.12838569430790744 +2DSquare,N64,112,GradOperator,SerialExecutor,200240.0,NeoN,No allocation,0.13891929684378745 +2DSquare,N64,113,GradOperator,GPUExecutor,1254680.0,NeoN,with Allocation,0.022170752701884146 +2DSquare,N64,114,GradOperator,GPUExecutor,654710.0,NeoN,No allocation,0.04248781903438163 +3DCube,N16,35,GradOperator,OpenFOAM,45127.0,OpenFOAM,with Allocation,1.0 +3DCube,N16,36,GradOperator,SerialExecutor,309326.0,NeoN,with Allocation,0.14588815683130418 +3DCube,N16,37,GradOperator,SerialExecutor,291863.0,NeoN,No allocation,0.15461706348526535 +3DCube,N16,38,GradOperator,GPUExecutor,1242090.0,NeoN,with Allocation,0.03633150576850309 +3DCube,N16,39,GradOperator,GPUExecutor,660366.0,NeoN,No allocation,0.06833634681373663 +3DCube,N32,60,GradOperator,OpenFOAM,412030.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,GradOperator,SerialExecutor,2394960.0,NeoN,with Allocation,0.1720404516150583 +3DCube,N32,62,GradOperator,SerialExecutor,2323430.0,NeoN,No allocation,0.17733695441653075 +3DCube,N32,63,GradOperator,GPUExecutor,1260600.0,NeoN,with Allocation,0.32685229255909887 +3DCube,N32,64,GradOperator,GPUExecutor,679111.0,NeoN,No allocation,0.6067196673297885 +3DCube,N64,135,GradOperator,OpenFOAM,3163280.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,136,GradOperator,SerialExecutor,22694800.0,NeoN,with Allocation,0.1393834711035127 +3DCube,N64,137,GradOperator,SerialExecutor,18436500.0,NeoN,No allocation,0.17157703468662708 +3DCube,N64,138,GradOperator,GPUExecutor,1617960.0,NeoN,with Allocation,1.9551039580706568 +3DCube,N64,139,GradOperator,GPUExecutor,941451.0,NeoN,No allocation,3.3600049285624 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv new file mode 100644 index 0000000..f4bbf4d --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,5,LaplacianOperator,OpenFOAM,3378.21,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,33322.5,NeoN,with Allocation,0.1013792482556831 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,19545.0,NeoN,No allocation,0.1728426707597851 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1212960.0,NeoN,with Allocation,0.0027850959635931935 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,621977.0,NeoN,No allocation,0.005431406627576261 +2DSquare,N256,80,LaplacianOperator,OpenFOAM,460361.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,81,LaplacianOperator,SerialExecutor,1619330.0,NeoN,with Allocation,0.2842910339461382 +2DSquare,N256,82,LaplacianOperator,SerialExecutor,1593170.0,NeoN,No allocation,0.28895911924025686 +2DSquare,N256,83,LaplacianOperator,GPUExecutor,1275670.0,NeoN,with Allocation,0.36087781322755885 +2DSquare,N256,84,LaplacianOperator,GPUExecutor,772854.0,NeoN,No allocation,0.5956636052863801 +2DSquare,N64,105,LaplacianOperator,OpenFOAM,20307.0,OpenFOAM,with Allocation,1.0 +2DSquare,N64,106,LaplacianOperator,SerialExecutor,122535.0,NeoN,with Allocation,0.16572407883461868 +2DSquare,N64,107,LaplacianOperator,SerialExecutor,107679.0,NeoN,No allocation,0.18858830412615274 +2DSquare,N64,108,LaplacianOperator,GPUExecutor,1230470.0,NeoN,with Allocation,0.016503449901257242 +2DSquare,N64,109,LaplacianOperator,GPUExecutor,628093.0,NeoN,No allocation,0.03233119936060424 +3DCube,N16,30,LaplacianOperator,OpenFOAM,31026.6,OpenFOAM,with Allocation,1.0 +3DCube,N16,31,LaplacianOperator,SerialExecutor,171677.0,NeoN,with Allocation,0.18072659703978983 +3DCube,N16,32,LaplacianOperator,SerialExecutor,154072.0,NeoN,No allocation,0.20137727815566747 +3DCube,N16,33,LaplacianOperator,GPUExecutor,1236110.0,NeoN,with Allocation,0.0251001933484884 +3DCube,N16,34,LaplacianOperator,GPUExecutor,654259.0,NeoN,No allocation,0.047422503931929094 +3DCube,N32,55,LaplacianOperator,OpenFOAM,303843.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,1311720.0,NeoN,with Allocation,0.23163708718324033 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1271480.0,NeoN,No allocation,0.23896797432912825 +3DCube,N32,58,LaplacianOperator,GPUExecutor,1234730.0,NeoN,with Allocation,0.2460805196277729 +3DCube,N32,59,LaplacianOperator,GPUExecutor,659453.0,NeoN,No allocation,0.46075004587135093 +3DCube,N64,130,LaplacianOperator,OpenFOAM,2630230.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,131,LaplacianOperator,SerialExecutor,10354500.0,NeoN,with Allocation,0.25401805978077163 +3DCube,N64,132,LaplacianOperator,SerialExecutor,10126600.0,NeoN,No allocation,0.25973475796417356 +3DCube,N64,133,LaplacianOperator,GPUExecutor,1505450.0,NeoN,with Allocation,1.747138729283603 +3DCube,N64,134,LaplacianOperator,GPUExecutor,832013.0,NeoN,No allocation,3.1612847395413293 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/Poisson.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/Poisson.csv new file mode 100644 index 0000000..f938446 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/Poisson.csv @@ -0,0 +1,19 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,Poisson,OpenFOAM,5218.27,OpenFOAM,Poisson,1.0 +2DSquare,N16,1,Poisson,SerialExecutor,37636.8,NeoN,Poisson,0.13864807847638483 +2DSquare,N16,2,Poisson,GPUExecutor,1456880.0,NeoN,Poisson,0.003581811817033661 +2DSquare,N256,9,Poisson,OpenFOAM,793669.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,10,Poisson,SerialExecutor,656527.0,NeoN,Poisson,1.2088901141918003 +2DSquare,N256,11,Poisson,GPUExecutor,1631180.0,NeoN,Poisson,0.4865612623989995 +2DSquare,N64,12,Poisson,OpenFOAM,34114.4,OpenFOAM,Poisson,1.0 +2DSquare,N64,13,Poisson,SerialExecutor,52594.3,NeoN,Poisson,0.6486330267728632 +2DSquare,N64,14,Poisson,GPUExecutor,1448530.0,NeoN,Poisson,0.02355104830414282 +3DCube,N16,3,Poisson,OpenFOAM,49450.5,OpenFOAM,Poisson,1.0 +3DCube,N16,4,Poisson,SerialExecutor,61512.3,NeoN,Poisson,0.8039123882540564 +3DCube,N16,5,Poisson,GPUExecutor,1536530.0,NeoN,Poisson,0.03218323104657898 +3DCube,N32,6,Poisson,OpenFOAM,592816.0,OpenFOAM,Poisson,1.0 +3DCube,N32,7,Poisson,SerialExecutor,556693.0,NeoN,Poisson,1.0648885471884864 +3DCube,N32,8,Poisson,GPUExecutor,1547190.0,NeoN,Poisson,0.38315656124974956 +3DCube,N64,15,Poisson,OpenFOAM,6110460.0,OpenFOAM,Poisson,1.0 +3DCube,N64,16,Poisson,SerialExecutor,5306020.0,NeoN,Poisson,1.151608927218518 +3DCube,N64,17,Poisson,GPUExecutor,1903710.0,NeoN,Poisson,3.2097640922199284 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv new file mode 100644 index 0000000..c04dbd3 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,DivOperator,OpenFOAM,2649.97,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,27827.1,NeoN,with Allocation,0.0952298299140047 +2DSquare,N16,2,DivOperator,SerialExecutor,14432.0,NeoN,No allocation,0.183617655210643 +2DSquare,N16,3,DivOperator,GPUExecutor,1286540.0,NeoN,with Allocation,0.0020597649509537207 +2DSquare,N16,4,DivOperator,GPUExecutor,682550.0,NeoN,No allocation,0.0038824554977657313 +2DSquare,N256,75,DivOperator,OpenFOAM,367428.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,DivOperator,SerialExecutor,434016.0,NeoN,with Allocation,0.8465770847157709 +2DSquare,N256,77,DivOperator,SerialExecutor,383009.0,NeoN,No allocation,0.9593194937977959 +2DSquare,N256,78,DivOperator,GPUExecutor,1282210.0,NeoN,with Allocation,0.28655836407452756 +2DSquare,N256,79,DivOperator,GPUExecutor,664301.0,NeoN,No allocation,0.5531046919995605 +2DSquare,N64,100,DivOperator,OpenFOAM,18064.1,OpenFOAM,with Allocation,1.0 +2DSquare,N64,101,DivOperator,SerialExecutor,47352.8,NeoN,with Allocation,0.3814790255275295 +2DSquare,N64,102,DivOperator,SerialExecutor,32774.1,NeoN,No allocation,0.5511699787332069 +2DSquare,N64,103,DivOperator,GPUExecutor,1214730.0,NeoN,with Allocation,0.01487087665571773 +2DSquare,N64,104,DivOperator,GPUExecutor,803289.0,NeoN,No allocation,0.022487672556203306 +3DCube,N16,25,DivOperator,OpenFOAM,27294.9,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,DivOperator,SerialExecutor,56939.8,NeoN,with Allocation,0.47936417058015657 +3DCube,N16,27,DivOperator,SerialExecutor,41045.9,NeoN,No allocation,0.6649848096886656 +3DCube,N16,28,DivOperator,GPUExecutor,1297730.0,NeoN,with Allocation,0.021032803433688057 +3DCube,N16,29,DivOperator,GPUExecutor,692883.0,NeoN,No allocation,0.03939323089179559 +3DCube,N32,50,DivOperator,OpenFOAM,290436.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,392538.0,NeoN,with Allocation,0.7398926982865354 +3DCube,N32,52,DivOperator,SerialExecutor,341834.0,NeoN,No allocation,0.8496404687655412 +3DCube,N32,53,DivOperator,GPUExecutor,1287030.0,NeoN,with Allocation,0.22566373744201768 +3DCube,N32,54,DivOperator,GPUExecutor,666642.0,NeoN,No allocation,0.4356701197944324 +3DCube,N64,125,DivOperator,OpenFOAM,2172460.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,126,DivOperator,SerialExecutor,2444890.0,NeoN,with Allocation,0.8885716739812425 +3DCube,N64,127,DivOperator,SerialExecutor,2231850.0,NeoN,No allocation,0.9733897887402827 +3DCube,N64,128,DivOperator,GPUExecutor,1465820.0,NeoN,with Allocation,1.4820782906496022 +3DCube,N64,129,DivOperator,GPUExecutor,820091.0,NeoN,No allocation,2.6490474837548517 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv new file mode 100644 index 0000000..169e94a --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,15,FaceInterpolation,OpenFOAM,924.165,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,FaceInterpolation,SerialExecutor,14142.5,NeoN,with Allocation,0.06534665016793353 +2DSquare,N16,17,FaceInterpolation,SerialExecutor,548.12,NeoN,No allocation,1.6860632708166094 +2DSquare,N16,18,FaceInterpolation,GPUExecutor,661785.0,NeoN,with Allocation,0.0013964731748226386 +2DSquare,N16,19,FaceInterpolation,GPUExecutor,19317.1,NeoN,No allocation,0.04784180855304368 +2DSquare,N256,90,FaceInterpolation,OpenFOAM,157056.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,FaceInterpolation,SerialExecutor,252150.0,NeoN,with Allocation,0.6228673408685307 +2DSquare,N256,92,FaceInterpolation,SerialExecutor,144316.0,NeoN,No allocation,1.0882784999584245 +2DSquare,N256,93,FaceInterpolation,GPUExecutor,611884.0,NeoN,with Allocation,0.2566761020062626 +2DSquare,N256,94,FaceInterpolation,GPUExecutor,22078.1,NeoN,No allocation,7.113655613481233 +2DSquare,N64,115,FaceInterpolation,OpenFOAM,5345.21,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,FaceInterpolation,SerialExecutor,21927.2,NeoN,with Allocation,0.24377075048341784 +2DSquare,N64,117,FaceInterpolation,SerialExecutor,5616.23,NeoN,No allocation,0.9517434293111215 +2DSquare,N64,118,FaceInterpolation,GPUExecutor,712500.0,NeoN,with Allocation,0.007502049122807017 +2DSquare,N64,119,FaceInterpolation,GPUExecutor,20509.6,NeoN,No allocation,0.26061990482505754 +3DCube,N16,40,FaceInterpolation,OpenFOAM,7119.75,OpenFOAM,with Allocation,1.0 +3DCube,N16,41,FaceInterpolation,SerialExecutor,25769.0,NeoN,with Allocation,0.2762912802204199 +3DCube,N16,42,FaceInterpolation,SerialExecutor,8249.56,NeoN,No allocation,0.8630460291215531 +3DCube,N16,43,FaceInterpolation,GPUExecutor,609757.0,NeoN,with Allocation,0.011676372718968375 +3DCube,N16,44,FaceInterpolation,GPUExecutor,18310.2,NeoN,No allocation,0.38884064619720154 +3DCube,N32,65,FaceInterpolation,OpenFOAM,111024.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,FaceInterpolation,SerialExecutor,205663.0,NeoN,with Allocation,0.5398345837608126 +3DCube,N32,67,FaceInterpolation,SerialExecutor,80450.3,NeoN,No allocation,1.3800321440690713 +3DCube,N32,68,FaceInterpolation,GPUExecutor,613511.0,NeoN,with Allocation,0.18096497047322704 +3DCube,N32,69,FaceInterpolation,GPUExecutor,19848.9,NeoN,No allocation,5.59345857956864 +3DCube,N64,140,FaceInterpolation,OpenFOAM,656297.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,141,FaceInterpolation,SerialExecutor,1097580.0,NeoN,with Allocation,0.5979491244373987 +3DCube,N64,142,FaceInterpolation,SerialExecutor,711710.0,NeoN,No allocation,0.9221410405923761 +3DCube,N64,143,FaceInterpolation,GPUExecutor,728806.0,NeoN,with Allocation,0.9005098750559134 +3DCube,N64,144,FaceInterpolation,GPUExecutor,35740.2,NeoN,No allocation,18.362991813140386 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv new file mode 100644 index 0000000..b0e1e78 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,20,FaceNormalGradient,OpenFOAM,913.351,OpenFOAM,with Allocation,1.0 +2DSquare,N16,21,FaceNormalGradient,SerialExecutor,14062.1,NeoN,with Allocation,0.06495125194672204 +2DSquare,N16,22,FaceNormalGradient,SerialExecutor,447.105,NeoN,No allocation,2.0428109728139923 +2DSquare,N16,23,FaceNormalGradient,GPUExecutor,663627.0,NeoN,with Allocation,0.0013763017478191815 +2DSquare,N16,24,FaceNormalGradient,GPUExecutor,21927.2,NeoN,No allocation,0.041653790725674045 +2DSquare,N256,95,FaceNormalGradient,OpenFOAM,187042.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,FaceNormalGradient,SerialExecutor,234365.0,NeoN,with Allocation,0.7980799180765046 +2DSquare,N256,97,FaceNormalGradient,SerialExecutor,170131.0,NeoN,No allocation,1.0993998742145759 +2DSquare,N256,98,FaceNormalGradient,GPUExecutor,637013.0,NeoN,with Allocation,0.2936235210270434 +2DSquare,N256,99,FaceNormalGradient,GPUExecutor,27619.2,NeoN,No allocation,6.772172981114587 +2DSquare,N64,120,FaceNormalGradient,OpenFOAM,5509.81,OpenFOAM,with Allocation,1.0 +2DSquare,N64,121,FaceNormalGradient,SerialExecutor,20197.4,NeoN,with Allocation,0.2727979838989177 +2DSquare,N64,122,FaceNormalGradient,SerialExecutor,4705.61,NeoN,No allocation,1.170902390975878 +2DSquare,N64,123,FaceNormalGradient,GPUExecutor,722459.0,NeoN,with Allocation,0.007626467384308314 +2DSquare,N64,124,FaceNormalGradient,GPUExecutor,24383.7,NeoN,No allocation,0.2259628358288529 +3DCube,N16,45,FaceNormalGradient,OpenFOAM,7916.21,OpenFOAM,with Allocation,1.0 +3DCube,N16,46,FaceNormalGradient,SerialExecutor,24087.9,NeoN,with Allocation,0.3286384450284167 +3DCube,N16,47,FaceNormalGradient,SerialExecutor,7214.97,NeoN,No allocation,1.0971923653182203 +3DCube,N16,48,FaceNormalGradient,GPUExecutor,618116.0,NeoN,with Allocation,0.012806997392075274 +3DCube,N16,49,FaceNormalGradient,GPUExecutor,22826.2,NeoN,No allocation,0.3468036729722862 +3DCube,N32,70,FaceNormalGradient,OpenFOAM,101301.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,71,FaceNormalGradient,SerialExecutor,201883.0,NeoN,with Allocation,0.5017807343857581 +3DCube,N32,72,FaceNormalGradient,SerialExecutor,94377.2,NeoN,No allocation,1.0733630580267268 +3DCube,N32,73,FaceNormalGradient,GPUExecutor,621744.0,NeoN,with Allocation,0.16293040222342314 +3DCube,N32,74,FaceNormalGradient,GPUExecutor,27926.1,NeoN,No allocation,3.6274667783901084 +3DCube,N64,145,FaceNormalGradient,OpenFOAM,681148.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,146,FaceNormalGradient,SerialExecutor,1111300.0,NeoN,with Allocation,0.6129290020696482 +3DCube,N64,147,FaceNormalGradient,SerialExecutor,755437.0,NeoN,No allocation,0.9016608929665876 +3DCube,N64,148,FaceNormalGradient,GPUExecutor,871578.0,NeoN,with Allocation,0.7815112359421647 +3DCube,N64,149,FaceNormalGradient,GPUExecutor,45596.8,NeoN,No allocation,14.938504456453083 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv new file mode 100644 index 0000000..3238054 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,10,GradOperator,OpenFOAM,3724.76,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,GradOperator,SerialExecutor,40324.2,NeoN,with Allocation,0.09237033840720958 +2DSquare,N16,12,GradOperator,SerialExecutor,25420.4,NeoN,No allocation,0.14652641185819262 +2DSquare,N16,13,GradOperator,GPUExecutor,1288900.0,NeoN,with Allocation,0.0028898750872837307 +2DSquare,N16,14,GradOperator,GPUExecutor,715350.0,NeoN,No allocation,0.005206905710491368 +2DSquare,N256,85,GradOperator,OpenFOAM,564734.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,86,GradOperator,SerialExecutor,3187840.0,NeoN,with Allocation,0.17715255470789 +2DSquare,N256,87,GradOperator,SerialExecutor,3083140.0,NeoN,No allocation,0.18316845813034763 +2DSquare,N256,88,GradOperator,GPUExecutor,1487330.0,NeoN,with Allocation,0.37969650312976944 +2DSquare,N256,89,GradOperator,GPUExecutor,694339.0,NeoN,No allocation,0.8133404576150842 +2DSquare,N64,110,GradOperator,OpenFOAM,27805.8,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,GradOperator,SerialExecutor,216986.0,NeoN,with Allocation,0.12814559464665923 +2DSquare,N64,112,GradOperator,SerialExecutor,202218.0,NeoN,No allocation,0.13750407975551138 +2DSquare,N64,113,GradOperator,GPUExecutor,1513980.0,NeoN,with Allocation,0.018366028613323822 +2DSquare,N64,114,GradOperator,GPUExecutor,813079.0,NeoN,No allocation,0.03419815294700761 +3DCube,N16,35,GradOperator,OpenFOAM,48844.1,OpenFOAM,with Allocation,1.0 +3DCube,N16,36,GradOperator,SerialExecutor,314151.0,NeoN,with Allocation,0.1554796897033592 +3DCube,N16,37,GradOperator,SerialExecutor,294278.0,NeoN,No allocation,0.1659794480049477 +3DCube,N16,38,GradOperator,GPUExecutor,1272700.0,NeoN,with Allocation,0.0383783295356329 +3DCube,N16,39,GradOperator,GPUExecutor,676321.0,NeoN,No allocation,0.07222029184366595 +3DCube,N32,60,GradOperator,OpenFOAM,495503.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,GradOperator,SerialExecutor,2425910.0,NeoN,with Allocation,0.20425448594548026 +3DCube,N32,62,GradOperator,SerialExecutor,2339820.0,NeoN,No allocation,0.21176970878101734 +3DCube,N32,63,GradOperator,GPUExecutor,1262920.0,NeoN,with Allocation,0.3923471003705698 +3DCube,N32,64,GradOperator,GPUExecutor,677907.0,NeoN,No allocation,0.7309306438788802 +3DCube,N64,135,GradOperator,OpenFOAM,3495850.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,136,GradOperator,SerialExecutor,22300300.0,NeoN,with Allocation,0.15676246507894512 +3DCube,N64,137,GradOperator,SerialExecutor,18501600.0,NeoN,No allocation,0.1889485233709517 +3DCube,N64,138,GradOperator,GPUExecutor,1623280.0,NeoN,with Allocation,2.153571780592381 +3DCube,N64,139,GradOperator,GPUExecutor,952701.0,NeoN,No allocation,3.6694093949728193 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv new file mode 100644 index 0000000..21d6333 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,5,LaplacianOperator,OpenFOAM,4055.59,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,33953.5,NeoN,with Allocation,0.11944541799814452 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,19869.7,NeoN,No allocation,0.20410927190647066 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1318220.0,NeoN,with Allocation,0.003076565368451397 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,682790.0,NeoN,No allocation,0.00593973256784663 +2DSquare,N256,80,LaplacianOperator,OpenFOAM,441740.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,81,LaplacianOperator,SerialExecutor,1623870.0,NeoN,with Allocation,0.27202916489620477 +2DSquare,N256,82,LaplacianOperator,SerialExecutor,1586590.0,NeoN,No allocation,0.27842101614153625 +2DSquare,N256,83,LaplacianOperator,GPUExecutor,1260860.0,NeoN,with Allocation,0.3503481750551211 +2DSquare,N256,84,LaplacianOperator,GPUExecutor,653297.0,NeoN,No allocation,0.6761702564071165 +2DSquare,N64,105,LaplacianOperator,OpenFOAM,21000.5,OpenFOAM,with Allocation,1.0 +2DSquare,N64,106,LaplacianOperator,SerialExecutor,123199.0,NeoN,with Allocation,0.17045998749989855 +2DSquare,N64,107,LaplacianOperator,SerialExecutor,107074.0,NeoN,No allocation,0.19613071333843884 +2DSquare,N64,108,LaplacianOperator,GPUExecutor,1453320.0,NeoN,with Allocation,0.014450017890072386 +2DSquare,N64,109,LaplacianOperator,GPUExecutor,779575.0,NeoN,No allocation,0.026938395920854313 +3DCube,N16,30,LaplacianOperator,OpenFOAM,31893.6,OpenFOAM,with Allocation,1.0 +3DCube,N16,31,LaplacianOperator,SerialExecutor,171177.0,NeoN,with Allocation,0.1863194237543595 +3DCube,N16,32,LaplacianOperator,SerialExecutor,154457.0,NeoN,No allocation,0.20648853726279806 +3DCube,N16,33,LaplacianOperator,GPUExecutor,1301050.0,NeoN,with Allocation,0.024513738903193572 +3DCube,N16,34,LaplacianOperator,GPUExecutor,700199.0,NeoN,No allocation,0.04554933668856996 +3DCube,N32,55,LaplacianOperator,OpenFOAM,369449.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,1348680.0,NeoN,with Allocation,0.27393377228104515 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1295260.0,NeoN,No allocation,0.2852315365254852 +3DCube,N32,58,LaplacianOperator,GPUExecutor,1257570.0,NeoN,with Allocation,0.29378006790874467 +3DCube,N32,59,LaplacianOperator,GPUExecutor,667493.0,NeoN,No allocation,0.5534874523028706 +3DCube,N64,130,LaplacianOperator,OpenFOAM,2582510.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,131,LaplacianOperator,SerialExecutor,10313700.0,NeoN,with Allocation,0.2503960751233796 +3DCube,N64,132,LaplacianOperator,SerialExecutor,10136200.0,NeoN,No allocation,0.2547808843550838 +3DCube,N64,133,LaplacianOperator,GPUExecutor,1504240.0,NeoN,with Allocation,1.7168204541828431 +3DCube,N64,134,LaplacianOperator,GPUExecutor,837261.0,NeoN,No allocation,3.084474255936918 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv new file mode 100644 index 0000000..35d13ab --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv @@ -0,0 +1,19 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,Poisson,OpenFOAM,5271.75,OpenFOAM,Poisson,1.0 +2DSquare,N16,1,Poisson,SerialExecutor,37214.5,NeoN,Poisson,0.14165849332921307 +2DSquare,N16,2,Poisson,GPUExecutor,1361910.0,NeoN,Poisson,0.003870850496728859 +2DSquare,N256,9,Poisson,OpenFOAM,789825.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,10,Poisson,SerialExecutor,764648.0,NeoN,Poisson,1.0329262614954855 +2DSquare,N256,11,Poisson,GPUExecutor,1577640.0,NeoN,Poisson,0.5006370274587358 +2DSquare,N64,12,Poisson,OpenFOAM,34825.7,OpenFOAM,Poisson,1.0 +2DSquare,N64,13,Poisson,SerialExecutor,51935.6,NeoN,Poisson,0.6705554571430772 +2DSquare,N64,14,Poisson,GPUExecutor,1432320.0,NeoN,Poisson,0.0243141895665773 +3DCube,N16,3,Poisson,OpenFOAM,48969.2,OpenFOAM,Poisson,1.0 +3DCube,N16,4,Poisson,SerialExecutor,59750.9,NeoN,Poisson,0.8195558560624191 +3DCube,N16,5,Poisson,GPUExecutor,1412890.0,NeoN,Poisson,0.03465889064258364 +3DCube,N32,6,Poisson,OpenFOAM,591977.0,OpenFOAM,Poisson,1.0 +3DCube,N32,7,Poisson,SerialExecutor,512153.0,NeoN,Poisson,1.1558596747456327 +3DCube,N32,8,Poisson,GPUExecutor,1579100.0,NeoN,Poisson,0.37488252802229116 +3DCube,N64,15,Poisson,OpenFOAM,5021560.0,OpenFOAM,Poisson,1.0 +3DCube,N64,16,Poisson,SerialExecutor,4100120.0,NeoN,Poisson,1.2247348858082203 +3DCube,N64,17,Poisson,GPUExecutor,1740810.0,NeoN,Poisson,2.8846111867463997 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv new file mode 100644 index 0000000..ee2b591 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,momentum,OpenFOAM,10284.1,OpenFOAM,without RHS,1.0 +2DSquare,N16,1,momentum,OpenFOAM,15535.0,OpenFOAM,with RHS,0.6619954940457032 +2DSquare,N16,2,momentum,SerialExecutor,88267.0,NeoN,without RHS,0.1165112669514088 +2DSquare,N16,3,momentum,SerialExecutor,140098.0,NeoN,with RHS,0.07340647261202872 +2DSquare,N16,4,momentum,GPUExecutor,2078340.0,NeoN,without RHS,0.004948227912661066 +2DSquare,N16,5,momentum,GPUExecutor,3165820.0,NeoN,with RHS,0.003248479067034765 +2DSquare,N256,18,momentum,OpenFOAM,2343310.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,19,momentum,OpenFOAM,3337890.0,OpenFOAM,with RHS,0.7020333204509436 +2DSquare,N256,20,momentum,SerialExecutor,10502300.0,NeoN,without RHS,0.22312350627957686 +2DSquare,N256,21,momentum,SerialExecutor,15776100.0,NeoN,with RHS,0.14853544285343018 +2DSquare,N256,22,momentum,GPUExecutor,2550720.0,NeoN,without RHS,0.9186857044285535 +2DSquare,N256,23,momentum,GPUExecutor,4185920.0,NeoN,with RHS,0.5598076408531458 +2DSquare,N64,24,momentum,OpenFOAM,77761.0,OpenFOAM,without RHS,1.0 +2DSquare,N64,25,momentum,OpenFOAM,124499.0,OpenFOAM,with RHS,0.6245913621796159 +2DSquare,N64,26,momentum,SerialExecutor,550614.0,NeoN,without RHS,0.14122597681860613 +2DSquare,N64,27,momentum,SerialExecutor,1014950.0,NeoN,with RHS,0.07661559682742992 +2DSquare,N64,28,momentum,GPUExecutor,2149590.0,NeoN,without RHS,0.03617480542801185 +2DSquare,N64,29,momentum,GPUExecutor,3245180.0,NeoN,with RHS,0.023961999026248158 +3DCube,N16,6,momentum,OpenFOAM,118308.0,OpenFOAM,without RHS,1.0 +3DCube,N16,7,momentum,OpenFOAM,197934.0,OpenFOAM,with RHS,0.5977143896450332 +3DCube,N16,8,momentum,SerialExecutor,826421.0,NeoN,without RHS,0.14315705917444016 +3DCube,N16,9,momentum,SerialExecutor,1535900.0,NeoN,with RHS,0.07702845237320138 +3DCube,N16,10,momentum,GPUExecutor,2255650.0,NeoN,without RHS,0.05244962649347195 +3DCube,N16,11,momentum,GPUExecutor,3425020.0,NeoN,with RHS,0.03454228004508003 +3DCube,N32,12,momentum,OpenFOAM,1423830.0,OpenFOAM,without RHS,1.0 +3DCube,N32,13,momentum,OpenFOAM,2014050.0,OpenFOAM,with RHS,0.7069486854844715 +3DCube,N32,14,momentum,SerialExecutor,6349310.0,NeoN,without RHS,0.22424956412586564 +3DCube,N32,15,momentum,SerialExecutor,11944000.0,NeoN,with RHS,0.11920880776959143 +3DCube,N32,16,momentum,GPUExecutor,2491380.0,NeoN,without RHS,0.5715025407605423 +3DCube,N32,17,momentum,GPUExecutor,3955270.0,NeoN,with RHS,0.35998301000943045 +3DCube,N64,30,momentum,OpenFOAM,14828600.0,OpenFOAM,without RHS,1.0 +3DCube,N64,31,momentum,OpenFOAM,21687500.0,OpenFOAM,with RHS,0.6837394812680115 +3DCube,N64,32,momentum,SerialExecutor,65738100.0,NeoN,without RHS,0.2255708637761055 +3DCube,N64,33,momentum,SerialExecutor,119459000.0,NeoN,with RHS,0.12413129190768381 +3DCube,N64,34,momentum,GPUExecutor,4724800.0,NeoN,without RHS,3.138460887233322 +3DCube,N64,35,momentum,GPUExecutor,8207740.0,NeoN,with RHS,1.8066605423661082 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv new file mode 100644 index 0000000..5d67eb7 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv @@ -0,0 +1,55 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,pressureVelocityCoupling,CPU,1407.56,OpenFOAM,Compute rAU, +2DSquare,N16,1,pressureVelocityCoupling,CPU,4453.16,OpenFOAM,Compute HbyA, +2DSquare,N16,2,pressureVelocityCoupling,CPU,4360.5,OpenFOAM,constrainHbyA, +2DSquare,N16,3,pressureVelocityCoupling,SerialExecutor,12972.1,NeoN,Compute rAU, +2DSquare,N16,4,pressureVelocityCoupling,SerialExecutor,55272.4,NeoN,Compute HbyA, +2DSquare,N16,5,pressureVelocityCoupling,SerialExecutor,59.9028,NeoN,constrainHbyA, +2DSquare,N16,6,pressureVelocityCoupling,GPUExecutor,604513.0,NeoN,Compute rAU, +2DSquare,N16,7,pressureVelocityCoupling,GPUExecutor,1906030.0,NeoN,Compute HbyA, +2DSquare,N16,8,pressureVelocityCoupling,GPUExecutor,370.477,NeoN,constrainHbyA, +2DSquare,N256,27,pressureVelocityCoupling,CPU,103783.0,OpenFOAM,Compute rAU, +2DSquare,N256,28,pressureVelocityCoupling,CPU,1287790.0,OpenFOAM,Compute HbyA, +2DSquare,N256,29,pressureVelocityCoupling,CPU,1264110.0,OpenFOAM,constrainHbyA, +2DSquare,N256,30,pressureVelocityCoupling,SerialExecutor,346812.0,NeoN,Compute rAU, +2DSquare,N256,31,pressureVelocityCoupling,SerialExecutor,3590520.0,NeoN,Compute HbyA, +2DSquare,N256,32,pressureVelocityCoupling,SerialExecutor,116.942,NeoN,constrainHbyA, +2DSquare,N256,33,pressureVelocityCoupling,GPUExecutor,798589.0,NeoN,Compute rAU, +2DSquare,N256,34,pressureVelocityCoupling,GPUExecutor,2772680.0,NeoN,Compute HbyA, +2DSquare,N256,35,pressureVelocityCoupling,GPUExecutor,367.382,NeoN,constrainHbyA, +2DSquare,N64,36,pressureVelocityCoupling,CPU,7044.3,OpenFOAM,Compute rAU, +2DSquare,N64,37,pressureVelocityCoupling,CPU,48163.0,OpenFOAM,Compute HbyA, +2DSquare,N64,38,pressureVelocityCoupling,CPU,47623.1,OpenFOAM,constrainHbyA, +2DSquare,N64,39,pressureVelocityCoupling,SerialExecutor,18025.1,NeoN,Compute rAU, +2DSquare,N64,40,pressureVelocityCoupling,SerialExecutor,238079.0,NeoN,Compute HbyA, +2DSquare,N64,41,pressureVelocityCoupling,SerialExecutor,62.284,NeoN,constrainHbyA, +2DSquare,N64,42,pressureVelocityCoupling,GPUExecutor,729000.0,NeoN,Compute rAU, +2DSquare,N64,43,pressureVelocityCoupling,GPUExecutor,2254980.0,NeoN,Compute HbyA, +2DSquare,N64,44,pressureVelocityCoupling,GPUExecutor,371.443,NeoN,constrainHbyA, +3DCube,N16,9,pressureVelocityCoupling,CPU,10025.5,OpenFOAM,Compute rAU, +3DCube,N16,10,pressureVelocityCoupling,CPU,64253.9,OpenFOAM,Compute HbyA, +3DCube,N16,11,pressureVelocityCoupling,CPU,62997.3,OpenFOAM,constrainHbyA, +3DCube,N16,12,pressureVelocityCoupling,SerialExecutor,19451.5,NeoN,Compute rAU, +3DCube,N16,13,pressureVelocityCoupling,SerialExecutor,330056.0,NeoN,Compute HbyA, +3DCube,N16,14,pressureVelocityCoupling,SerialExecutor,255.097,NeoN,constrainHbyA, +3DCube,N16,15,pressureVelocityCoupling,GPUExecutor,617873.0,NeoN,Compute rAU, +3DCube,N16,16,pressureVelocityCoupling,GPUExecutor,2013740.0,NeoN,Compute HbyA, +3DCube,N16,17,pressureVelocityCoupling,GPUExecutor,20407.2,NeoN,constrainHbyA, +3DCube,N32,18,pressureVelocityCoupling,CPU,64163.0,OpenFOAM,Compute rAU, +3DCube,N32,19,pressureVelocityCoupling,CPU,700012.0,OpenFOAM,Compute HbyA, +3DCube,N32,20,pressureVelocityCoupling,CPU,671073.0,OpenFOAM,constrainHbyA, +3DCube,N32,21,pressureVelocityCoupling,SerialExecutor,160214.0,NeoN,Compute rAU, +3DCube,N32,22,pressureVelocityCoupling,SerialExecutor,2619930.0,NeoN,Compute HbyA, +3DCube,N32,23,pressureVelocityCoupling,SerialExecutor,1848.05,NeoN,constrainHbyA, +3DCube,N32,24,pressureVelocityCoupling,GPUExecutor,627926.0,NeoN,Compute rAU, +3DCube,N32,25,pressureVelocityCoupling,GPUExecutor,2059880.0,NeoN,Compute HbyA, +3DCube,N32,26,pressureVelocityCoupling,GPUExecutor,24666.5,NeoN,constrainHbyA, +3DCube,N64,45,pressureVelocityCoupling,CPU,677189.0,OpenFOAM,Compute rAU, +3DCube,N64,46,pressureVelocityCoupling,CPU,5937740.0,OpenFOAM,Compute HbyA, +3DCube,N64,47,pressureVelocityCoupling,CPU,7348830.0,OpenFOAM,constrainHbyA, +3DCube,N64,48,pressureVelocityCoupling,SerialExecutor,1008310.0,NeoN,Compute rAU, +3DCube,N64,49,pressureVelocityCoupling,SerialExecutor,21536900.0,NeoN,Compute HbyA, +3DCube,N64,50,pressureVelocityCoupling,SerialExecutor,7019.49,NeoN,constrainHbyA, +3DCube,N64,51,pressureVelocityCoupling,GPUExecutor,715141.0,NeoN,Compute rAU, +3DCube,N64,52,pressureVelocityCoupling,GPUExecutor,2521120.0,NeoN,Compute HbyA, +3DCube,N64,53,pressureVelocityCoupling,GPUExecutor,22519.3,NeoN,constrainHbyA, diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv new file mode 100644 index 0000000..89081c1 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,scalarAdvection,OpenFOAM,8466.59,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,scalarAdvection,OpenFOAM,7624.52,OpenFOAM,implicit-time-integration,1.110442362273297 +2DSquare,N16,2,scalarAdvection,SerialExecutor,36787.7,NeoN,explicit-time-integration,0.23014730466976735 +2DSquare,N16,3,scalarAdvection,SerialExecutor,64193.0,NeoN,implicit-time-integration,0.1318927297368872 +2DSquare,N16,4,scalarAdvection,GPUExecutor,1403210.0,NeoN,explicit-time-integration,0.006033729805232289 +2DSquare,N16,5,scalarAdvection,GPUExecutor,2003850.0,NeoN,implicit-time-integration,0.00422516156398932 +2DSquare,N256,18,scalarAdvection,OpenFOAM,978542.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,19,scalarAdvection,OpenFOAM,1444790.0,OpenFOAM,implicit-time-integration,0.6772901252085078 +2DSquare,N256,20,scalarAdvection,SerialExecutor,822079.0,NeoN,explicit-time-integration,1.1903259905678165 +2DSquare,N256,21,scalarAdvection,SerialExecutor,4190800.0,NeoN,implicit-time-integration,0.2334976615443352 +2DSquare,N256,22,scalarAdvection,GPUExecutor,1842310.0,NeoN,explicit-time-integration,0.5311494808148466 +2DSquare,N256,23,scalarAdvection,GPUExecutor,2747520.0,NeoN,implicit-time-integration,0.3561546412764966 +2DSquare,N64,24,scalarAdvection,OpenFOAM,51729.1,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,25,scalarAdvection,OpenFOAM,54881.9,OpenFOAM,implicit-time-integration,0.9425530092799265 +2DSquare,N64,26,scalarAdvection,SerialExecutor,56425.7,NeoN,explicit-time-integration,0.916764878415332 +2DSquare,N64,27,scalarAdvection,SerialExecutor,281280.0,NeoN,implicit-time-integration,0.18390607224118316 +2DSquare,N64,28,scalarAdvection,GPUExecutor,1420030.0,NeoN,explicit-time-integration,0.036428174052660856 +2DSquare,N64,29,scalarAdvection,GPUExecutor,2027870.0,NeoN,implicit-time-integration,0.02550908095686607 +3DCube,N16,6,scalarAdvection,OpenFOAM,69104.8,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,7,scalarAdvection,OpenFOAM,78148.1,OpenFOAM,implicit-time-integration,0.8842799760966678 +3DCube,N16,8,scalarAdvection,SerialExecutor,64523.5,NeoN,explicit-time-integration,1.0710020380171565 +3DCube,N16,9,scalarAdvection,SerialExecutor,419267.0,NeoN,implicit-time-integration,0.16482289328757094 +3DCube,N16,10,scalarAdvection,GPUExecutor,1503270.0,NeoN,explicit-time-integration,0.04596965282351141 +3DCube,N16,11,scalarAdvection,GPUExecutor,2138630.0,NeoN,implicit-time-integration,0.03231264875177099 +3DCube,N32,12,scalarAdvection,OpenFOAM,808764.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,13,scalarAdvection,OpenFOAM,1079470.0,OpenFOAM,implicit-time-integration,0.7492232299183859 +3DCube,N32,14,scalarAdvection,SerialExecutor,729658.0,NeoN,explicit-time-integration,1.1084151753287157 +3DCube,N32,15,scalarAdvection,SerialExecutor,3245440.0,NeoN,implicit-time-integration,0.24920010845986984 +3DCube,N32,16,scalarAdvection,GPUExecutor,1741800.0,NeoN,explicit-time-integration,0.46432655873234585 +3DCube,N32,17,scalarAdvection,GPUExecutor,2265820.0,NeoN,implicit-time-integration,0.3569409750112542 +3DCube,N64,30,scalarAdvection,OpenFOAM,7201020.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,31,scalarAdvection,OpenFOAM,10521100.0,OpenFOAM,implicit-time-integration,0.6844360380568572 +3DCube,N64,32,scalarAdvection,SerialExecutor,5247760.0,NeoN,explicit-time-integration,1.3722083326981416 +3DCube,N64,33,scalarAdvection,SerialExecutor,26544800.0,NeoN,implicit-time-integration,0.27127799041620204 +3DCube,N64,34,scalarAdvection,GPUExecutor,1814490.0,NeoN,explicit-time-integration,3.9686192814509864 +3DCube,N64,35,scalarAdvection,GPUExecutor,2905460.0,NeoN,implicit-time-integration,2.4784440329586364 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/momentum.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/momentum.csv new file mode 100644 index 0000000..5a53f4a --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/momentum.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,momentum,OpenFOAM,11026.1,OpenFOAM,without RHS,1.0 +2DSquare,N16,1,momentum,OpenFOAM,15929.2,OpenFOAM,with RHS,0.692194209376491 +2DSquare,N16,2,momentum,SerialExecutor,88960.2,NeoN,without RHS,0.1239441907729524 +2DSquare,N16,3,momentum,SerialExecutor,141184.0,NeoN,with RHS,0.07809737647325476 +2DSquare,N16,4,momentum,GPUExecutor,2438450.0,NeoN,without RHS,0.004521765875863766 +2DSquare,N16,5,momentum,GPUExecutor,3914990.0,NeoN,with RHS,0.0028163801184677355 +2DSquare,N256,18,momentum,OpenFOAM,2330070.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,19,momentum,OpenFOAM,3322690.0,OpenFOAM,with RHS,0.7012601235745736 +2DSquare,N256,20,momentum,SerialExecutor,8439360.0,NeoN,without RHS,0.2760955807075418 +2DSquare,N256,21,momentum,SerialExecutor,15853700.0,NeoN,with RHS,0.14697326176223846 +2DSquare,N256,22,momentum,GPUExecutor,2765060.0,NeoN,without RHS,0.842683341410313 +2DSquare,N256,23,momentum,GPUExecutor,4228760.0,NeoN,with RHS,0.5510054957008674 +2DSquare,N64,24,momentum,OpenFOAM,78735.4,OpenFOAM,without RHS,1.0 +2DSquare,N64,25,momentum,OpenFOAM,122248.0,OpenFOAM,with RHS,0.644062888554414 +2DSquare,N64,26,momentum,SerialExecutor,553220.0,NeoN,without RHS,0.14232204186399622 +2DSquare,N64,27,momentum,SerialExecutor,1009420.0,NeoN,with RHS,0.07800063402746131 +2DSquare,N64,28,momentum,GPUExecutor,2286880.0,NeoN,without RHS,0.034429178618904356 +2DSquare,N64,29,momentum,GPUExecutor,3490300.0,NeoN,with RHS,0.02255834741999255 +3DCube,N16,6,momentum,OpenFOAM,115752.0,OpenFOAM,without RHS,1.0 +3DCube,N16,7,momentum,OpenFOAM,193859.0,OpenFOAM,with RHS,0.5970937640243682 +3DCube,N16,8,momentum,SerialExecutor,823292.0,NeoN,without RHS,0.14059653197164554 +3DCube,N16,9,momentum,SerialExecutor,1543790.0,NeoN,with RHS,0.07497910985302406 +3DCube,N16,10,momentum,GPUExecutor,2716510.0,NeoN,without RHS,0.04261055545534528 +3DCube,N16,11,momentum,GPUExecutor,4096990.0,NeoN,with RHS,0.028252936912220923 +3DCube,N32,12,momentum,OpenFOAM,1247780.0,OpenFOAM,without RHS,1.0 +3DCube,N32,13,momentum,OpenFOAM,1889580.0,OpenFOAM,with RHS,0.6603478021570931 +3DCube,N32,14,momentum,SerialExecutor,6303760.0,NeoN,without RHS,0.19794218053986826 +3DCube,N32,15,momentum,SerialExecutor,11871800.0,NeoN,with RHS,0.10510453343216698 +3DCube,N32,16,momentum,GPUExecutor,2681460.0,NeoN,without RHS,0.4653360482722099 +3DCube,N32,17,momentum,GPUExecutor,4142540.0,NeoN,with RHS,0.3012113341090249 +3DCube,N64,30,momentum,OpenFOAM,14228700.0,OpenFOAM,without RHS,1.0 +3DCube,N64,31,momentum,OpenFOAM,21947600.0,OpenFOAM,with RHS,0.6483032313328109 +3DCube,N64,32,momentum,SerialExecutor,65756500.0,NeoN,without RHS,0.21638469200763422 +3DCube,N64,33,momentum,SerialExecutor,118593000.0,NeoN,with RHS,0.11997925678581367 +3DCube,N64,34,momentum,GPUExecutor,4887160.0,NeoN,without RHS,2.911445502091194 +3DCube,N64,35,momentum,GPUExecutor,8367510.0,NeoN,with RHS,1.700470032303517 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv new file mode 100644 index 0000000..731ba7d --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv @@ -0,0 +1,55 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,pressureVelocityCoupling,CPU,1400.01,OpenFOAM,Compute rAU, +2DSquare,N16,1,pressureVelocityCoupling,CPU,4833.05,OpenFOAM,Compute HbyA, +2DSquare,N16,2,pressureVelocityCoupling,CPU,4434.59,OpenFOAM,constrainHbyA, +2DSquare,N16,3,pressureVelocityCoupling,SerialExecutor,13133.7,NeoN,Compute rAU, +2DSquare,N16,4,pressureVelocityCoupling,SerialExecutor,55613.7,NeoN,Compute HbyA, +2DSquare,N16,5,pressureVelocityCoupling,SerialExecutor,59.0559,NeoN,constrainHbyA, +2DSquare,N16,6,pressureVelocityCoupling,GPUExecutor,612818.0,NeoN,Compute rAU, +2DSquare,N16,7,pressureVelocityCoupling,GPUExecutor,1904740.0,NeoN,Compute HbyA, +2DSquare,N16,8,pressureVelocityCoupling,GPUExecutor,369.917,NeoN,constrainHbyA, +2DSquare,N256,27,pressureVelocityCoupling,CPU,97778.1,OpenFOAM,Compute rAU, +2DSquare,N256,28,pressureVelocityCoupling,CPU,1153280.0,OpenFOAM,Compute HbyA, +2DSquare,N256,29,pressureVelocityCoupling,CPU,1139890.0,OpenFOAM,constrainHbyA, +2DSquare,N256,30,pressureVelocityCoupling,SerialExecutor,248480.0,NeoN,Compute rAU, +2DSquare,N256,31,pressureVelocityCoupling,SerialExecutor,3530050.0,NeoN,Compute HbyA, +2DSquare,N256,32,pressureVelocityCoupling,SerialExecutor,58.7114,NeoN,constrainHbyA, +2DSquare,N256,33,pressureVelocityCoupling,GPUExecutor,632358.0,NeoN,Compute rAU, +2DSquare,N256,34,pressureVelocityCoupling,GPUExecutor,2075890.0,NeoN,Compute HbyA, +2DSquare,N256,35,pressureVelocityCoupling,GPUExecutor,375.981,NeoN,constrainHbyA, +2DSquare,N64,36,pressureVelocityCoupling,CPU,7032.71,OpenFOAM,Compute rAU, +2DSquare,N64,37,pressureVelocityCoupling,CPU,48099.5,OpenFOAM,Compute HbyA, +2DSquare,N64,38,pressureVelocityCoupling,CPU,47920.5,OpenFOAM,constrainHbyA, +2DSquare,N64,39,pressureVelocityCoupling,SerialExecutor,17886.4,NeoN,Compute rAU, +2DSquare,N64,40,pressureVelocityCoupling,SerialExecutor,238052.0,NeoN,Compute HbyA, +2DSquare,N64,41,pressureVelocityCoupling,SerialExecutor,60.6268,NeoN,constrainHbyA, +2DSquare,N64,42,pressureVelocityCoupling,GPUExecutor,598688.0,NeoN,Compute rAU, +2DSquare,N64,43,pressureVelocityCoupling,GPUExecutor,1905160.0,NeoN,Compute HbyA, +2DSquare,N64,44,pressureVelocityCoupling,GPUExecutor,366.768,NeoN,constrainHbyA, +3DCube,N16,9,pressureVelocityCoupling,CPU,10046.6,OpenFOAM,Compute rAU, +3DCube,N16,10,pressureVelocityCoupling,CPU,63491.6,OpenFOAM,Compute HbyA, +3DCube,N16,11,pressureVelocityCoupling,CPU,62597.8,OpenFOAM,constrainHbyA, +3DCube,N16,12,pressureVelocityCoupling,SerialExecutor,18878.9,NeoN,Compute rAU, +3DCube,N16,13,pressureVelocityCoupling,SerialExecutor,332247.0,NeoN,Compute HbyA, +3DCube,N16,14,pressureVelocityCoupling,SerialExecutor,263.612,NeoN,constrainHbyA, +3DCube,N16,15,pressureVelocityCoupling,GPUExecutor,627595.0,NeoN,Compute rAU, +3DCube,N16,16,pressureVelocityCoupling,GPUExecutor,2012540.0,NeoN,Compute HbyA, +3DCube,N16,17,pressureVelocityCoupling,GPUExecutor,20961.2,NeoN,constrainHbyA, +3DCube,N32,18,pressureVelocityCoupling,CPU,130960.0,OpenFOAM,Compute rAU, +3DCube,N32,19,pressureVelocityCoupling,CPU,711337.0,OpenFOAM,Compute HbyA, +3DCube,N32,20,pressureVelocityCoupling,CPU,713408.0,OpenFOAM,constrainHbyA, +3DCube,N32,21,pressureVelocityCoupling,SerialExecutor,173466.0,NeoN,Compute rAU, +3DCube,N32,22,pressureVelocityCoupling,SerialExecutor,2613040.0,NeoN,Compute HbyA, +3DCube,N32,23,pressureVelocityCoupling,SerialExecutor,1843.55,NeoN,constrainHbyA, +3DCube,N32,24,pressureVelocityCoupling,GPUExecutor,616414.0,NeoN,Compute rAU, +3DCube,N32,25,pressureVelocityCoupling,GPUExecutor,2042050.0,NeoN,Compute HbyA, +3DCube,N32,26,pressureVelocityCoupling,GPUExecutor,22044.2,NeoN,constrainHbyA, +3DCube,N64,45,pressureVelocityCoupling,CPU,786588.0,OpenFOAM,Compute rAU, +3DCube,N64,46,pressureVelocityCoupling,CPU,6401720.0,OpenFOAM,Compute HbyA, +3DCube,N64,47,pressureVelocityCoupling,CPU,7778800.0,OpenFOAM,constrainHbyA, +3DCube,N64,48,pressureVelocityCoupling,SerialExecutor,1875670.0,NeoN,Compute rAU, +3DCube,N64,49,pressureVelocityCoupling,SerialExecutor,22057800.0,NeoN,Compute HbyA, +3DCube,N64,50,pressureVelocityCoupling,SerialExecutor,7120.8,NeoN,constrainHbyA, +3DCube,N64,51,pressureVelocityCoupling,GPUExecutor,713991.0,NeoN,Compute rAU, +3DCube,N64,52,pressureVelocityCoupling,GPUExecutor,2509340.0,NeoN,Compute HbyA, +3DCube,N64,53,pressureVelocityCoupling,GPUExecutor,22712.1,NeoN,constrainHbyA, diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv new file mode 100644 index 0000000..8c978d6 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,scalarAdvection,OpenFOAM,8453.22,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,scalarAdvection,OpenFOAM,7685.3,OpenFOAM,implicit-time-integration,1.0999206276918272 +2DSquare,N16,2,scalarAdvection,SerialExecutor,37559.6,NeoN,explicit-time-integration,0.22506150225242014 +2DSquare,N16,3,scalarAdvection,SerialExecutor,63878.5,NeoN,implicit-time-integration,0.1323327880272705 +2DSquare,N16,4,scalarAdvection,GPUExecutor,1382350.0,NeoN,explicit-time-integration,0.006115108330017723 +2DSquare,N16,5,scalarAdvection,GPUExecutor,2005540.0,NeoN,implicit-time-integration,0.00421493463107193 +2DSquare,N256,18,scalarAdvection,OpenFOAM,966406.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,19,scalarAdvection,OpenFOAM,1457170.0,OpenFOAM,implicit-time-integration,0.6632074500573029 +2DSquare,N256,20,scalarAdvection,SerialExecutor,840248.0,NeoN,explicit-time-integration,1.1501437670782912 +2DSquare,N256,21,scalarAdvection,SerialExecutor,4161680.0,NeoN,implicit-time-integration,0.23221535533726764 +2DSquare,N256,22,scalarAdvection,GPUExecutor,1555160.0,NeoN,explicit-time-integration,0.6214190179788575 +2DSquare,N256,23,scalarAdvection,GPUExecutor,2362390.0,NeoN,implicit-time-integration,0.4090797878419736 +2DSquare,N64,24,scalarAdvection,OpenFOAM,51764.5,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,25,scalarAdvection,OpenFOAM,57837.5,OpenFOAM,implicit-time-integration,0.8949989193862113 +2DSquare,N64,26,scalarAdvection,SerialExecutor,56336.9,NeoN,explicit-time-integration,0.9188382747364515 +2DSquare,N64,27,scalarAdvection,SerialExecutor,280505.0,NeoN,implicit-time-integration,0.18454038252437568 +2DSquare,N64,28,scalarAdvection,GPUExecutor,1546810.0,NeoN,explicit-time-integration,0.03346532541165366 +2DSquare,N64,29,scalarAdvection,GPUExecutor,2251350.0,NeoN,implicit-time-integration,0.022992648855131366 +3DCube,N16,6,scalarAdvection,OpenFOAM,67851.1,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,7,scalarAdvection,OpenFOAM,79297.3,OpenFOAM,implicit-time-integration,0.8556546061467415 +3DCube,N16,8,scalarAdvection,SerialExecutor,67439.6,NeoN,explicit-time-integration,1.0061017562381747 +3DCube,N16,9,scalarAdvection,SerialExecutor,426501.0,NeoN,implicit-time-integration,0.15908778642957463 +3DCube,N16,10,scalarAdvection,GPUExecutor,1548190.0,NeoN,explicit-time-integration,0.043826080778199064 +3DCube,N16,11,scalarAdvection,GPUExecutor,2305660.0,NeoN,implicit-time-integration,0.02942805964452695 +3DCube,N32,12,scalarAdvection,OpenFOAM,714182.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,13,scalarAdvection,OpenFOAM,1012590.0,OpenFOAM,implicit-time-integration,0.7053022447387393 +3DCube,N32,14,scalarAdvection,SerialExecutor,649268.0,NeoN,explicit-time-integration,1.0999802854907372 +3DCube,N32,15,scalarAdvection,SerialExecutor,3176620.0,NeoN,implicit-time-integration,0.22482449899578796 +3DCube,N32,16,scalarAdvection,GPUExecutor,1470540.0,NeoN,explicit-time-integration,0.48565968963782014 +3DCube,N32,17,scalarAdvection,GPUExecutor,2219830.0,NeoN,implicit-time-integration,0.32172824045084536 +3DCube,N64,30,scalarAdvection,OpenFOAM,7532520.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,31,scalarAdvection,OpenFOAM,10646100.0,OpenFOAM,implicit-time-integration,0.7075379716515907 +3DCube,N64,32,scalarAdvection,SerialExecutor,5304200.0,NeoN,explicit-time-integration,1.4201048225934165 +3DCube,N64,33,scalarAdvection,SerialExecutor,27307100.0,NeoN,implicit-time-integration,0.27584474367472195 +3DCube,N64,34,scalarAdvection,GPUExecutor,1952090.0,NeoN,explicit-time-integration,3.8586950396754247 +3DCube,N64,35,scalarAdvection,GPUExecutor,3132930.0,NeoN,implicit-time-integration,2.4043052350355736 diff --git a/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/system-info.log b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/NeoFOAM/218/neon-cluster-meta-runner-adapter-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/DivOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/DivOperator.csv new file mode 100644 index 0000000..e395867 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/DivOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,DivOperator,OpenFOAM,2816.78,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,28190.7,NeoN,with Allocation,0.0999187675368118 +2DSquare,N16,2,DivOperator,SerialExecutor,14631.7,NeoN,No allocation,0.1925121482807876 +2DSquare,N16,3,DivOperator,GPUExecutor,1258100.0,NeoN,with Allocation,0.002238915825451077 +2DSquare,N16,4,DivOperator,GPUExecutor,655868.0,NeoN,No allocation,0.004294736135929791 +2DSquare,N256,75,DivOperator,OpenFOAM,349404.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,DivOperator,SerialExecutor,420126.0,NeoN,with Allocation,0.8316647862784022 +2DSquare,N256,77,DivOperator,SerialExecutor,392968.0,NeoN,No allocation,0.8891411005476273 +2DSquare,N256,78,DivOperator,GPUExecutor,1285290.0,NeoN,with Allocation,0.2718483766309549 +2DSquare,N256,79,DivOperator,GPUExecutor,664898.0,NeoN,No allocation,0.5255001519029987 +2DSquare,N64,100,DivOperator,OpenFOAM,18561.7,OpenFOAM,with Allocation,1.0 +2DSquare,N64,101,DivOperator,SerialExecutor,46618.7,NeoN,with Allocation,0.39815996585061364 +2DSquare,N64,102,DivOperator,SerialExecutor,32622.6,NeoN,No allocation,0.5689828523784125 +2DSquare,N64,103,DivOperator,GPUExecutor,1208030.0,NeoN,with Allocation,0.015365264107679445 +2DSquare,N64,104,DivOperator,GPUExecutor,626222.0,NeoN,No allocation,0.029640766373586366 +3DCube,N16,25,DivOperator,OpenFOAM,29064.4,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,DivOperator,SerialExecutor,56881.9,NeoN,with Allocation,0.5109604285370215 +3DCube,N16,27,DivOperator,SerialExecutor,41897.4,NeoN,No allocation,0.6937041439325591 +3DCube,N16,28,DivOperator,GPUExecutor,1343230.0,NeoN,with Allocation,0.021637694214691455 +3DCube,N16,29,DivOperator,GPUExecutor,675534.0,NeoN,No allocation,0.0430243333422152 +3DCube,N32,50,DivOperator,OpenFOAM,252405.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,327080.0,NeoN,with Allocation,0.7716919408095879 +3DCube,N32,52,DivOperator,SerialExecutor,292655.0,NeoN,No allocation,0.8624660436349968 +3DCube,N32,53,DivOperator,GPUExecutor,1250600.0,NeoN,with Allocation,0.20182712298096914 +3DCube,N32,54,DivOperator,GPUExecutor,651342.0,NeoN,No allocation,0.38751531453522114 +3DCube,N64,125,DivOperator,OpenFOAM,2086900.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,126,DivOperator,SerialExecutor,2572400.0,NeoN,with Allocation,0.8112657440522469 +3DCube,N64,127,DivOperator,SerialExecutor,2317750.0,NeoN,No allocation,0.9003990939488729 +3DCube,N64,128,DivOperator,GPUExecutor,1806730.0,NeoN,with Allocation,1.1550702097158956 +3DCube,N64,129,DivOperator,GPUExecutor,959012.0,NeoN,No allocation,2.176093729796916 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv new file mode 100644 index 0000000..93b27fe --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceInterpolation.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,15,FaceInterpolation,OpenFOAM,939.114,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,FaceInterpolation,SerialExecutor,13894.8,NeoN,with Allocation,0.06758744278435098 +2DSquare,N16,17,FaceInterpolation,SerialExecutor,534.302,NeoN,No allocation,1.7576464246811727 +2DSquare,N16,18,FaceInterpolation,GPUExecutor,634875.0,NeoN,with Allocation,0.0014792108682811578 +2DSquare,N16,19,FaceInterpolation,GPUExecutor,17233.4,NeoN,No allocation,0.05449383174533174 +2DSquare,N256,90,FaceInterpolation,OpenFOAM,119728.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,FaceInterpolation,SerialExecutor,286706.0,NeoN,with Allocation,0.4175985155525172 +2DSquare,N256,92,FaceInterpolation,SerialExecutor,172363.0,NeoN,No allocation,0.6946270371251371 +2DSquare,N256,93,FaceInterpolation,GPUExecutor,640132.0,NeoN,with Allocation,0.18703642373760412 +2DSquare,N256,94,FaceInterpolation,GPUExecutor,21893.5,NeoN,No allocation,5.468655080274967 +2DSquare,N64,115,FaceInterpolation,OpenFOAM,5115.67,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,FaceInterpolation,SerialExecutor,21676.0,NeoN,with Allocation,0.23600618195238973 +2DSquare,N64,117,FaceInterpolation,SerialExecutor,5202.45,NeoN,No allocation,0.9833193975915194 +2DSquare,N64,118,FaceInterpolation,GPUExecutor,593408.0,NeoN,with Allocation,0.008620830861734255 +2DSquare,N64,119,FaceInterpolation,GPUExecutor,23239.5,NeoN,No allocation,0.22012822995331224 +3DCube,N16,40,FaceInterpolation,OpenFOAM,7311.74,OpenFOAM,with Allocation,1.0 +3DCube,N16,41,FaceInterpolation,SerialExecutor,26722.0,NeoN,with Allocation,0.27362248334705486 +3DCube,N16,42,FaceInterpolation,SerialExecutor,7863.9,NeoN,No allocation,0.9297854754002467 +3DCube,N16,43,FaceInterpolation,GPUExecutor,663644.0,NeoN,with Allocation,0.011017563633514353 +3DCube,N16,44,FaceInterpolation,GPUExecutor,19072.9,NeoN,No allocation,0.38335753870675143 +3DCube,N32,65,FaceInterpolation,OpenFOAM,72568.5,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,FaceInterpolation,SerialExecutor,150509.0,NeoN,with Allocation,0.48215389112943413 +3DCube,N32,67,FaceInterpolation,SerialExecutor,79833.9,NeoN,No allocation,0.9089935478537313 +3DCube,N32,68,FaceInterpolation,GPUExecutor,641075.0,NeoN,with Allocation,0.1131981437429318 +3DCube,N32,69,FaceInterpolation,GPUExecutor,19489.2,NeoN,No allocation,3.723523797795702 +3DCube,N64,140,FaceInterpolation,OpenFOAM,667998.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,141,FaceInterpolation,SerialExecutor,1109620.0,NeoN,with Allocation,0.6020060921756998 +3DCube,N64,142,FaceInterpolation,SerialExecutor,651273.0,NeoN,No allocation,1.0256804750081763 +3DCube,N64,143,FaceInterpolation,GPUExecutor,851580.0,NeoN,with Allocation,0.7844218981187909 +3DCube,N64,144,FaceInterpolation,GPUExecutor,37261.4,NeoN,No allocation,17.92734572506669 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv new file mode 100644 index 0000000..2b9b78d --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/FaceNormalGradient.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,20,FaceNormalGradient,OpenFOAM,1039.51,OpenFOAM,with Allocation,1.0 +2DSquare,N16,21,FaceNormalGradient,SerialExecutor,14035.2,NeoN,with Allocation,0.07406449498404012 +2DSquare,N16,22,FaceNormalGradient,SerialExecutor,446.124,NeoN,No allocation,2.3300920820220385 +2DSquare,N16,23,FaceNormalGradient,GPUExecutor,624609.0,NeoN,with Allocation,0.0016642571592788448 +2DSquare,N16,24,FaceNormalGradient,GPUExecutor,22620.5,NeoN,No allocation,0.045954333458588445 +2DSquare,N256,95,FaceNormalGradient,OpenFOAM,162503.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,FaceNormalGradient,SerialExecutor,287916.0,NeoN,with Allocation,0.5644111476958558 +2DSquare,N256,97,FaceNormalGradient,SerialExecutor,166621.0,NeoN,No allocation,0.9752852281525138 +2DSquare,N256,98,FaceNormalGradient,GPUExecutor,629240.0,NeoN,with Allocation,0.2582528129171699 +2DSquare,N256,99,FaceNormalGradient,GPUExecutor,29882.9,NeoN,No allocation,5.437992965876806 +2DSquare,N64,120,FaceNormalGradient,OpenFOAM,5143.72,OpenFOAM,with Allocation,1.0 +2DSquare,N64,121,FaceNormalGradient,SerialExecutor,20086.3,NeoN,with Allocation,0.25608101043995163 +2DSquare,N64,122,FaceNormalGradient,SerialExecutor,4620.32,NeoN,No allocation,1.1132821969041107 +2DSquare,N64,123,FaceNormalGradient,GPUExecutor,604953.0,NeoN,with Allocation,0.008502677067474663 +2DSquare,N64,124,FaceNormalGradient,GPUExecutor,23681.3,NeoN,No allocation,0.21720598109056516 +3DCube,N16,45,FaceNormalGradient,OpenFOAM,8419.79,OpenFOAM,with Allocation,1.0 +3DCube,N16,46,FaceNormalGradient,SerialExecutor,24764.6,NeoN,with Allocation,0.3399929738416934 +3DCube,N16,47,FaceNormalGradient,SerialExecutor,7228.31,NeoN,No allocation,1.1648352104433817 +3DCube,N16,48,FaceNormalGradient,GPUExecutor,649182.0,NeoN,with Allocation,0.012969845128176692 +3DCube,N16,49,FaceNormalGradient,GPUExecutor,23955.5,NeoN,No allocation,0.3514762789338566 +3DCube,N32,70,FaceNormalGradient,OpenFOAM,80441.1,OpenFOAM,with Allocation,1.0 +3DCube,N32,71,FaceNormalGradient,SerialExecutor,149816.0,NeoN,with Allocation,0.5369326373685054 +3DCube,N32,72,FaceNormalGradient,SerialExecutor,77226.2,NeoN,No allocation,1.0416296541847199 +3DCube,N32,73,FaceNormalGradient,GPUExecutor,614582.0,NeoN,with Allocation,0.1308874975186387 +3DCube,N32,74,FaceNormalGradient,GPUExecutor,27262.0,NeoN,No allocation,2.9506675959210624 +3DCube,N64,145,FaceNormalGradient,OpenFOAM,682548.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,146,FaceNormalGradient,SerialExecutor,1172320.0,NeoN,with Allocation,0.5822198717073837 +3DCube,N64,147,FaceNormalGradient,SerialExecutor,707180.0,NeoN,No allocation,0.965168698209791 +3DCube,N64,148,FaceNormalGradient,GPUExecutor,870290.0,NeoN,with Allocation,0.7842765055326385 +3DCube,N64,149,FaceNormalGradient,GPUExecutor,44921.9,NeoN,No allocation,15.194103544151071 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/GradOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/GradOperator.csv new file mode 100644 index 0000000..5f92061 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/GradOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,10,GradOperator,OpenFOAM,3816.69,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,GradOperator,SerialExecutor,39554.8,NeoN,with Allocation,0.09649119702286447 +2DSquare,N16,12,GradOperator,SerialExecutor,25455.9,NeoN,No allocation,0.14993341425759843 +2DSquare,N16,13,GradOperator,GPUExecutor,1270000.0,NeoN,with Allocation,0.0030052677165354333 +2DSquare,N16,14,GradOperator,GPUExecutor,659409.0,NeoN,No allocation,0.005788046568973126 +2DSquare,N256,85,GradOperator,OpenFOAM,505380.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,86,GradOperator,SerialExecutor,3223740.0,NeoN,with Allocation,0.1567682257253997 +2DSquare,N256,87,GradOperator,SerialExecutor,3094690.0,NeoN,No allocation,0.16330553302592504 +2DSquare,N256,88,GradOperator,GPUExecutor,1274470.0,NeoN,with Allocation,0.3965413073669839 +2DSquare,N256,89,GradOperator,GPUExecutor,680990.0,NeoN,No allocation,0.7421254350284145 +2DSquare,N64,110,GradOperator,OpenFOAM,27934.2,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,GradOperator,SerialExecutor,217629.0,NeoN,with Allocation,0.12835697448409908 +2DSquare,N64,112,GradOperator,SerialExecutor,200712.0,NeoN,No allocation,0.1391755350950616 +2DSquare,N64,113,GradOperator,GPUExecutor,1224470.0,NeoN,with Allocation,0.02281329881499751 +2DSquare,N64,114,GradOperator,GPUExecutor,634337.0,NeoN,No allocation,0.04403684476863245 +3DCube,N16,35,GradOperator,OpenFOAM,45247.8,OpenFOAM,with Allocation,1.0 +3DCube,N16,36,GradOperator,SerialExecutor,313198.0,NeoN,with Allocation,0.14447027120224268 +3DCube,N16,37,GradOperator,SerialExecutor,294621.0,NeoN,No allocation,0.15357968372926575 +3DCube,N16,38,GradOperator,GPUExecutor,1322210.0,NeoN,with Allocation,0.034221341541812576 +3DCube,N16,39,GradOperator,GPUExecutor,703059.0,NeoN,No allocation,0.0643584677815091 +3DCube,N32,60,GradOperator,OpenFOAM,387425.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,GradOperator,SerialExecutor,2428580.0,NeoN,with Allocation,0.15952737813866538 +3DCube,N32,62,GradOperator,SerialExecutor,2323700.0,NeoN,No allocation,0.16672763265481774 +3DCube,N32,63,GradOperator,GPUExecutor,1273110.0,NeoN,with Allocation,0.3043138456221379 +3DCube,N32,64,GradOperator,GPUExecutor,701555.0,NeoN,No allocation,0.5522375294880658 +3DCube,N64,135,GradOperator,OpenFOAM,3699860.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,136,GradOperator,SerialExecutor,19735400.0,NeoN,with Allocation,0.18747327138036218 +3DCube,N64,137,GradOperator,SerialExecutor,19129700.0,NeoN,No allocation,0.1934092013988719 +3DCube,N64,138,GradOperator,GPUExecutor,1933780.0,NeoN,with Allocation,1.9132786563104387 +3DCube,N64,139,GradOperator,GPUExecutor,1091410.0,NeoN,No allocation,3.3899817667054544 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv new file mode 100644 index 0000000..2acc120 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/LaplacianOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,5,LaplacianOperator,OpenFOAM,3640.37,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,40121.6,NeoN,with Allocation,0.09073342040197799 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,20296.3,NeoN,No allocation,0.17936126289028048 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1260540.0,NeoN,with Allocation,0.002887944849032954 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,673379.0,NeoN,No allocation,0.005406123446083112 +2DSquare,N256,80,LaplacianOperator,OpenFOAM,472868.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,81,LaplacianOperator,SerialExecutor,1672910.0,NeoN,with Allocation,0.2826619483415127 +2DSquare,N256,82,LaplacianOperator,SerialExecutor,1603140.0,NeoN,No allocation,0.294963633868533 +2DSquare,N256,83,LaplacianOperator,GPUExecutor,1253820.0,NeoN,with Allocation,0.3771418544926704 +2DSquare,N256,84,LaplacianOperator,GPUExecutor,652481.0,NeoN,No allocation,0.7247230187545691 +2DSquare,N64,105,LaplacianOperator,OpenFOAM,21734.7,OpenFOAM,with Allocation,1.0 +2DSquare,N64,106,LaplacianOperator,SerialExecutor,123056.0,NeoN,with Allocation,0.176624463658822 +2DSquare,N64,107,LaplacianOperator,SerialExecutor,107815.0,NeoN,No allocation,0.20159254278161667 +2DSquare,N64,108,LaplacianOperator,GPUExecutor,1213350.0,NeoN,with Allocation,0.0179129682284584 +2DSquare,N64,109,LaplacianOperator,GPUExecutor,629155.0,NeoN,No allocation,0.03454585912851364 +3DCube,N16,30,LaplacianOperator,OpenFOAM,33100.6,OpenFOAM,with Allocation,1.0 +3DCube,N16,31,LaplacianOperator,SerialExecutor,172494.0,NeoN,with Allocation,0.1918942108131297 +3DCube,N16,32,LaplacianOperator,SerialExecutor,157188.0,NeoN,No allocation,0.21057968801689694 +3DCube,N16,33,LaplacianOperator,GPUExecutor,1360580.0,NeoN,with Allocation,0.024328301165679342 +3DCube,N16,34,LaplacianOperator,GPUExecutor,713522.0,NeoN,No allocation,0.046390440659152765 +3DCube,N32,55,LaplacianOperator,OpenFOAM,297917.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,1328370.0,NeoN,with Allocation,0.224272604771261 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1282170.0,NeoN,No allocation,0.23235374404330159 +3DCube,N32,58,LaplacianOperator,GPUExecutor,1254460.0,NeoN,with Allocation,0.237486249063342 +3DCube,N32,59,LaplacianOperator,GPUExecutor,655589.0,NeoN,No allocation,0.4544264775644497 +3DCube,N64,130,LaplacianOperator,OpenFOAM,2608900.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,131,LaplacianOperator,SerialExecutor,10874500.0,NeoN,with Allocation,0.239909880914065 +3DCube,N64,132,LaplacianOperator,SerialExecutor,10437100.0,NeoN,No allocation,0.2499640704793477 +3DCube,N64,133,LaplacianOperator,GPUExecutor,1789970.0,NeoN,with Allocation,1.45751046106918 +3DCube,N64,134,LaplacianOperator,GPUExecutor,963846.0,NeoN,No allocation,2.7067602085810387 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/Poisson.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/Poisson.csv new file mode 100644 index 0000000..beca4fe --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/Poisson.csv @@ -0,0 +1,19 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,Poisson,OpenFOAM,6101.04,OpenFOAM,Poisson,1.0 +2DSquare,N16,1,Poisson,SerialExecutor,37941.8,NeoN,Poisson,0.16079996204713534 +2DSquare,N16,2,Poisson,GPUExecutor,1476160.0,NeoN,Poisson,0.004133047908085844 +2DSquare,N256,9,Poisson,OpenFOAM,813617.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,10,Poisson,SerialExecutor,849261.0,NeoN,Poisson,0.9580293926131072 +2DSquare,N256,11,Poisson,GPUExecutor,1660730.0,NeoN,Poisson,0.48991527822102326 +2DSquare,N64,12,Poisson,OpenFOAM,34267.9,OpenFOAM,Poisson,1.0 +2DSquare,N64,13,Poisson,SerialExecutor,52539.8,NeoN,Poisson,0.6522274542346944 +2DSquare,N64,14,Poisson,GPUExecutor,1524610.0,NeoN,Poisson,0.02247650218744466 +3DCube,N16,3,Poisson,OpenFOAM,49528.5,OpenFOAM,Poisson,1.0 +3DCube,N16,4,Poisson,SerialExecutor,62405.8,NeoN,Poisson,0.7936521925846636 +3DCube,N16,5,Poisson,GPUExecutor,1511080.0,NeoN,Poisson,0.03277688805357758 +3DCube,N32,6,Poisson,OpenFOAM,603014.0,OpenFOAM,Poisson,1.0 +3DCube,N32,7,Poisson,SerialExecutor,566234.0,NeoN,Poisson,1.0649554777706742 +3DCube,N32,8,Poisson,GPUExecutor,1526870.0,NeoN,Poisson,0.3949347357666337 +3DCube,N64,15,Poisson,OpenFOAM,5178840.0,OpenFOAM,Poisson,1.0 +3DCube,N64,16,Poisson,SerialExecutor,4359960.0,NeoN,Poisson,1.1878182368645585 +3DCube,N64,17,Poisson,GPUExecutor,1854230.0,NeoN,Poisson,2.792986846291992 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv new file mode 100644 index 0000000..cfa43b4 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/DivOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,DivOperator,OpenFOAM,2618.88,OpenFOAM,with Allocation,1.0 +2DSquare,N16,1,DivOperator,SerialExecutor,27344.0,NeoN,with Allocation,0.09577530719719135 +2DSquare,N16,2,DivOperator,SerialExecutor,14331.3,NeoN,No allocation,0.18273848150551592 +2DSquare,N16,3,DivOperator,GPUExecutor,1179300.0,NeoN,with Allocation,0.002220707199185958 +2DSquare,N16,4,DivOperator,GPUExecutor,607042.0,NeoN,No allocation,0.004314166070881422 +2DSquare,N256,75,DivOperator,OpenFOAM,327119.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,76,DivOperator,SerialExecutor,402396.0,NeoN,with Allocation,0.8129280609151185 +2DSquare,N256,77,DivOperator,SerialExecutor,369558.0,NeoN,No allocation,0.8851628161208795 +2DSquare,N256,78,DivOperator,GPUExecutor,1240970.0,NeoN,with Allocation,0.26359944237169314 +2DSquare,N256,79,DivOperator,GPUExecutor,653107.0,NeoN,No allocation,0.5008658611835427 +2DSquare,N64,100,DivOperator,OpenFOAM,18101.9,OpenFOAM,with Allocation,1.0 +2DSquare,N64,101,DivOperator,SerialExecutor,76760.2,NeoN,with Allocation,0.2358240338091876 +2DSquare,N64,102,DivOperator,SerialExecutor,32550.9,NeoN,No allocation,0.5561105837319399 +2DSquare,N64,103,DivOperator,GPUExecutor,1210650.0,NeoN,with Allocation,0.014952215751868832 +2DSquare,N64,104,DivOperator,GPUExecutor,629449.0,NeoN,No allocation,0.02875832672702634 +3DCube,N16,25,DivOperator,OpenFOAM,27502.7,OpenFOAM,with Allocation,1.0 +3DCube,N16,26,DivOperator,SerialExecutor,57097.6,NeoN,with Allocation,0.4816787395617329 +3DCube,N16,27,DivOperator,SerialExecutor,41067.1,NeoN,No allocation,0.6697015372402727 +3DCube,N16,28,DivOperator,GPUExecutor,1228300.0,NeoN,with Allocation,0.02239086542375641 +3DCube,N16,29,DivOperator,GPUExecutor,643609.0,NeoN,No allocation,0.04273200032939253 +3DCube,N32,50,DivOperator,OpenFOAM,252017.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,51,DivOperator,SerialExecutor,329593.0,NeoN,with Allocation,0.7646309235936443 +3DCube,N32,52,DivOperator,SerialExecutor,306827.0,NeoN,No allocation,0.8213651340983681 +3DCube,N32,53,DivOperator,GPUExecutor,1239780.0,NeoN,with Allocation,0.20327558115149463 +3DCube,N32,54,DivOperator,GPUExecutor,647526.0,NeoN,No allocation,0.38919981591472774 +3DCube,N64,125,DivOperator,OpenFOAM,2111550.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,126,DivOperator,SerialExecutor,2625800.0,NeoN,with Allocation,0.804154924213573 +3DCube,N64,127,DivOperator,SerialExecutor,2346460.0,NeoN,No allocation,0.899887490091457 +3DCube,N64,128,DivOperator,GPUExecutor,1488870.0,NeoN,with Allocation,1.418223216264684 +3DCube,N64,129,DivOperator,GPUExecutor,809052.0,NeoN,No allocation,2.6099064089823645 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv new file mode 100644 index 0000000..869cd59 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceInterpolation.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,15,FaceInterpolation,OpenFOAM,839.071,OpenFOAM,with Allocation,1.0 +2DSquare,N16,16,FaceInterpolation,SerialExecutor,13458.5,NeoN,with Allocation,0.062345060742281834 +2DSquare,N16,17,FaceInterpolation,SerialExecutor,537.976,NeoN,No allocation,1.5596811010156588 +2DSquare,N16,18,FaceInterpolation,GPUExecutor,582977.0,NeoN,with Allocation,0.0014392866270882042 +2DSquare,N16,19,FaceInterpolation,GPUExecutor,16637.3,NeoN,No allocation,0.05043312316301323 +2DSquare,N256,90,FaceInterpolation,OpenFOAM,102512.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,91,FaceInterpolation,SerialExecutor,174198.0,NeoN,with Allocation,0.5884797758872088 +2DSquare,N256,92,FaceInterpolation,SerialExecutor,100582.0,NeoN,No allocation,1.0191883239545843 +2DSquare,N256,93,FaceInterpolation,GPUExecutor,609750.0,NeoN,with Allocation,0.16812136121361212 +2DSquare,N256,94,FaceInterpolation,GPUExecutor,22745.6,NeoN,No allocation,4.506893640967924 +2DSquare,N64,115,FaceInterpolation,OpenFOAM,4890.58,OpenFOAM,with Allocation,1.0 +2DSquare,N64,116,FaceInterpolation,SerialExecutor,20739.4,NeoN,with Allocation,0.23581106492955436 +2DSquare,N64,117,FaceInterpolation,SerialExecutor,6325.09,NeoN,No allocation,0.773203227147756 +2DSquare,N64,118,FaceInterpolation,GPUExecutor,591108.0,NeoN,with Allocation,0.008273581139148853 +2DSquare,N64,119,FaceInterpolation,GPUExecutor,22540.7,NeoN,No allocation,0.21696664256212095 +3DCube,N16,40,FaceInterpolation,OpenFOAM,7121.42,OpenFOAM,with Allocation,1.0 +3DCube,N16,41,FaceInterpolation,SerialExecutor,25819.7,NeoN,with Allocation,0.275813429280743 +3DCube,N16,42,FaceInterpolation,SerialExecutor,9700.05,NeoN,No allocation,0.7341632259627529 +3DCube,N16,43,FaceInterpolation,GPUExecutor,599645.0,NeoN,with Allocation,0.011876060002167949 +3DCube,N16,44,FaceInterpolation,GPUExecutor,17942.6,NeoN,No allocation,0.3969001148105626 +3DCube,N32,65,FaceInterpolation,OpenFOAM,78205.3,OpenFOAM,with Allocation,1.0 +3DCube,N32,66,FaceInterpolation,SerialExecutor,154395.0,NeoN,with Allocation,0.5065274134525082 +3DCube,N32,67,FaceInterpolation,SerialExecutor,77583.8,NeoN,No allocation,1.0080106929539414 +3DCube,N32,68,FaceInterpolation,GPUExecutor,603152.0,NeoN,with Allocation,0.12966101413905617 +3DCube,N32,69,FaceInterpolation,GPUExecutor,20442.3,NeoN,No allocation,3.8256605176521234 +3DCube,N64,140,FaceInterpolation,OpenFOAM,670886.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,141,FaceInterpolation,SerialExecutor,1124570.0,NeoN,with Allocation,0.596571133855607 +3DCube,N64,142,FaceInterpolation,SerialExecutor,665561.0,NeoN,No allocation,1.008000769275844 +3DCube,N64,143,FaceInterpolation,GPUExecutor,718319.0,NeoN,with Allocation,0.9339666638359837 +3DCube,N64,144,FaceInterpolation,GPUExecutor,35724.3,NeoN,No allocation,18.77954221636253 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv new file mode 100644 index 0000000..8f1c858 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/FaceNormalGradient.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,20,FaceNormalGradient,OpenFOAM,912.9,OpenFOAM,with Allocation,1.0 +2DSquare,N16,21,FaceNormalGradient,SerialExecutor,13452.9,NeoN,with Allocation,0.0678589746448721 +2DSquare,N16,22,FaceNormalGradient,SerialExecutor,446.516,NeoN,No allocation,2.044495605980525 +2DSquare,N16,23,FaceNormalGradient,GPUExecutor,580142.0,NeoN,with Allocation,0.0015735802613842818 +2DSquare,N16,24,FaceNormalGradient,GPUExecutor,19816.2,NeoN,No allocation,0.04606836830472038 +2DSquare,N256,95,FaceNormalGradient,OpenFOAM,102246.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,96,FaceNormalGradient,SerialExecutor,175409.0,NeoN,with Allocation,0.5829005353203085 +2DSquare,N256,97,FaceNormalGradient,SerialExecutor,100366.0,NeoN,No allocation,1.0187314429189167 +2DSquare,N256,98,FaceNormalGradient,GPUExecutor,615182.0,NeoN,with Allocation,0.16620447282267686 +2DSquare,N256,99,FaceNormalGradient,GPUExecutor,32538.5,NeoN,No allocation,3.1423083424251272 +2DSquare,N64,120,FaceNormalGradient,OpenFOAM,5213.82,OpenFOAM,with Allocation,1.0 +2DSquare,N64,121,FaceNormalGradient,SerialExecutor,19875.4,NeoN,with Allocation,0.2623252865351137 +2DSquare,N64,122,FaceNormalGradient,SerialExecutor,4645.76,NeoN,No allocation,1.1222749345639895 +2DSquare,N64,123,FaceNormalGradient,GPUExecutor,595478.0,NeoN,with Allocation,0.00875568870722344 +2DSquare,N64,124,FaceNormalGradient,GPUExecutor,29701.8,NeoN,No allocation,0.17553885623093549 +3DCube,N16,45,FaceNormalGradient,OpenFOAM,7654.33,OpenFOAM,with Allocation,1.0 +3DCube,N16,46,FaceNormalGradient,SerialExecutor,24038.9,NeoN,with Allocation,0.31841432012280096 +3DCube,N16,47,FaceNormalGradient,SerialExecutor,7206.99,NeoN,No allocation,1.062070295643535 +3DCube,N16,48,FaceNormalGradient,GPUExecutor,617438.0,NeoN,with Allocation,0.012396920824439052 +3DCube,N16,49,FaceNormalGradient,GPUExecutor,22587.0,NeoN,No allocation,0.33888210032319477 +3DCube,N32,70,FaceNormalGradient,OpenFOAM,87505.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,71,FaceNormalGradient,SerialExecutor,186354.0,NeoN,with Allocation,0.46956330424890264 +3DCube,N32,72,FaceNormalGradient,SerialExecutor,76062.2,NeoN,No allocation,1.150440034603259 +3DCube,N32,73,FaceNormalGradient,GPUExecutor,613112.0,NeoN,with Allocation,0.1427226999308446 +3DCube,N32,74,FaceNormalGradient,GPUExecutor,29601.7,NeoN,No allocation,2.956080225122206 +3DCube,N64,145,FaceNormalGradient,OpenFOAM,679166.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,146,FaceNormalGradient,SerialExecutor,1175300.0,NeoN,with Allocation,0.5778660767463626 +3DCube,N64,147,FaceNormalGradient,SerialExecutor,722096.0,NeoN,No allocation,0.9405480711705922 +3DCube,N64,148,FaceNormalGradient,GPUExecutor,753776.0,NeoN,with Allocation,0.9010183396658954 +3DCube,N64,149,FaceNormalGradient,GPUExecutor,44069.8,NeoN,No allocation,15.411143231873073 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv new file mode 100644 index 0000000..6a904c4 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/GradOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,10,GradOperator,OpenFOAM,3522.07,OpenFOAM,with Allocation,1.0 +2DSquare,N16,11,GradOperator,SerialExecutor,38878.9,NeoN,with Allocation,0.09059078317544993 +2DSquare,N16,12,GradOperator,SerialExecutor,24814.6,NeoN,No allocation,0.14193539287355025 +2DSquare,N16,13,GradOperator,GPUExecutor,1179570.0,NeoN,with Allocation,0.002985893164458235 +2DSquare,N16,14,GradOperator,GPUExecutor,614531.0,NeoN,No allocation,0.005731313798652957 +2DSquare,N256,85,GradOperator,OpenFOAM,498745.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,86,GradOperator,SerialExecutor,3197000.0,NeoN,with Allocation,0.15600406631216765 +2DSquare,N256,87,GradOperator,SerialExecutor,3076600.0,NeoN,No allocation,0.16210914646037833 +2DSquare,N256,88,GradOperator,GPUExecutor,1273930.0,NeoN,with Allocation,0.3915011028863438 +2DSquare,N256,89,GradOperator,GPUExecutor,680460.0,NeoN,No allocation,0.7329527084619228 +2DSquare,N64,110,GradOperator,OpenFOAM,29008.7,OpenFOAM,with Allocation,1.0 +2DSquare,N64,111,GradOperator,SerialExecutor,216682.0,NeoN,with Allocation,0.13387683333179498 +2DSquare,N64,112,GradOperator,SerialExecutor,200239.0,NeoN,No allocation,0.14487037989602425 +2DSquare,N64,113,GradOperator,GPUExecutor,1212010.0,NeoN,with Allocation,0.023934373478766677 +2DSquare,N64,114,GradOperator,GPUExecutor,632678.0,NeoN,No allocation,0.04585065388712742 +3DCube,N16,35,GradOperator,OpenFOAM,45446.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,36,GradOperator,SerialExecutor,309470.0,NeoN,with Allocation,0.14685171422108767 +3DCube,N16,37,GradOperator,SerialExecutor,291830.0,NeoN,No allocation,0.1557283349895487 +3DCube,N16,38,GradOperator,GPUExecutor,1227350.0,NeoN,with Allocation,0.037027905650384975 +3DCube,N16,39,GradOperator,GPUExecutor,653319.0,NeoN,No allocation,0.06956203630998027 +3DCube,N32,60,GradOperator,OpenFOAM,499608.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,61,GradOperator,SerialExecutor,2420890.0,NeoN,with Allocation,0.2063736890151969 +3DCube,N32,62,GradOperator,SerialExecutor,2369140.0,NeoN,No allocation,0.2108815857230894 +3DCube,N32,63,GradOperator,GPUExecutor,1258780.0,NeoN,with Allocation,0.3968985843435708 +3DCube,N32,64,GradOperator,GPUExecutor,699080.0,NeoN,No allocation,0.7146649882702981 +3DCube,N64,135,GradOperator,OpenFOAM,3633100.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,136,GradOperator,SerialExecutor,19741700.0,NeoN,with Allocation,0.18403177031360016 +3DCube,N64,137,GradOperator,SerialExecutor,19220200.0,NeoN,No allocation,0.1890250881884684 +3DCube,N64,138,GradOperator,GPUExecutor,1621030.0,NeoN,with Allocation,2.241229341838214 +3DCube,N64,139,GradOperator,GPUExecutor,948079.0,NeoN,No allocation,3.832064627525765 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv new file mode 100644 index 0000000..e5b2387 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/LaplacianOperator.csv @@ -0,0 +1,31 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,5,LaplacianOperator,OpenFOAM,3450.31,OpenFOAM,with Allocation,1.0 +2DSquare,N16,6,LaplacianOperator,SerialExecutor,33381.2,NeoN,with Allocation,0.1033608737852444 +2DSquare,N16,7,LaplacianOperator,SerialExecutor,19326.4,NeoN,No allocation,0.17852833429919693 +2DSquare,N16,8,LaplacianOperator,GPUExecutor,1174220.0,NeoN,with Allocation,0.002938384629796801 +2DSquare,N16,9,LaplacianOperator,GPUExecutor,609512.0,NeoN,No allocation,0.005660774521256349 +2DSquare,N256,80,LaplacianOperator,OpenFOAM,378098.0,OpenFOAM,with Allocation,1.0 +2DSquare,N256,81,LaplacianOperator,SerialExecutor,1622100.0,NeoN,with Allocation,0.2330916712903027 +2DSquare,N256,82,LaplacianOperator,SerialExecutor,1580580.0,NeoN,No allocation,0.23921471864758506 +2DSquare,N256,83,LaplacianOperator,GPUExecutor,1277080.0,NeoN,with Allocation,0.29606445954834465 +2DSquare,N256,84,LaplacianOperator,GPUExecutor,673829.0,NeoN,No allocation,0.5611186220836444 +2DSquare,N64,105,LaplacianOperator,OpenFOAM,20283.8,OpenFOAM,with Allocation,1.0 +2DSquare,N64,106,LaplacianOperator,SerialExecutor,123395.0,NeoN,with Allocation,0.1643810527168848 +2DSquare,N64,107,LaplacianOperator,SerialExecutor,107848.0,NeoN,No allocation,0.18807766486165714 +2DSquare,N64,108,LaplacianOperator,GPUExecutor,1210210.0,NeoN,with Allocation,0.016760562216474827 +2DSquare,N64,109,LaplacianOperator,GPUExecutor,627046.0,NeoN,No allocation,0.03234818498164409 +3DCube,N16,30,LaplacianOperator,OpenFOAM,31218.2,OpenFOAM,with Allocation,1.0 +3DCube,N16,31,LaplacianOperator,SerialExecutor,170611.0,NeoN,with Allocation,0.18297882317083894 +3DCube,N16,32,LaplacianOperator,SerialExecutor,154288.0,NeoN,No allocation,0.20233718759722077 +3DCube,N16,33,LaplacianOperator,GPUExecutor,1247650.0,NeoN,with Allocation,0.025021600609145194 +3DCube,N16,34,LaplacianOperator,GPUExecutor,639537.0,NeoN,No allocation,0.0488137511981324 +3DCube,N32,55,LaplacianOperator,OpenFOAM,368155.0,OpenFOAM,with Allocation,1.0 +3DCube,N32,56,LaplacianOperator,SerialExecutor,1348780.0,NeoN,with Allocation,0.2729540770177494 +3DCube,N32,57,LaplacianOperator,SerialExecutor,1309510.0,NeoN,No allocation,0.28113951019847117 +3DCube,N32,58,LaplacianOperator,GPUExecutor,1274140.0,NeoN,with Allocation,0.28894391511136924 +3DCube,N32,59,LaplacianOperator,GPUExecutor,650675.0,NeoN,No allocation,0.5658047412302609 +3DCube,N64,130,LaplacianOperator,OpenFOAM,2724060.0,OpenFOAM,with Allocation,1.0 +3DCube,N64,131,LaplacianOperator,SerialExecutor,10834700.0,NeoN,with Allocation,0.2514199747108826 +3DCube,N64,132,LaplacianOperator,SerialExecutor,10627700.0,NeoN,No allocation,0.25631698297844313 +3DCube,N64,133,LaplacianOperator,GPUExecutor,1487920.0,NeoN,with Allocation,1.8307839131136083 +3DCube,N64,134,LaplacianOperator,GPUExecutor,809438.0,NeoN,No allocation,3.3653720235521436 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv new file mode 100644 index 0000000..4f9c3bd --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/Poisson.csv @@ -0,0 +1,19 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,Poisson,OpenFOAM,5297.0,OpenFOAM,Poisson,1.0 +2DSquare,N16,1,Poisson,SerialExecutor,37495.2,NeoN,Poisson,0.1412714160745909 +2DSquare,N16,2,Poisson,GPUExecutor,1464260.0,NeoN,Poisson,0.003617526941936541 +2DSquare,N256,9,Poisson,OpenFOAM,870095.0,OpenFOAM,Poisson,1.0 +2DSquare,N256,10,Poisson,SerialExecutor,866365.0,NeoN,Poisson,1.0043053447449979 +2DSquare,N256,11,Poisson,GPUExecutor,1632710.0,NeoN,Poisson,0.5329146021032517 +2DSquare,N64,12,Poisson,OpenFOAM,34006.4,OpenFOAM,Poisson,1.0 +2DSquare,N64,13,Poisson,SerialExecutor,52085.3,NeoN,Poisson,0.6528982265629649 +2DSquare,N64,14,Poisson,GPUExecutor,1534590.0,NeoN,Poisson,0.022159925452400968 +3DCube,N16,3,Poisson,OpenFOAM,50100.4,OpenFOAM,Poisson,1.0 +3DCube,N16,4,Poisson,SerialExecutor,61100.5,NeoN,Poisson,0.8199671033788595 +3DCube,N16,5,Poisson,GPUExecutor,1519260.0,NeoN,Poisson,0.032976843989837155 +3DCube,N32,6,Poisson,OpenFOAM,643012.0,OpenFOAM,Poisson,1.0 +3DCube,N32,7,Poisson,SerialExecutor,626682.0,NeoN,Poisson,1.0260578730520424 +3DCube,N32,8,Poisson,GPUExecutor,1799400.0,NeoN,Poisson,0.35734800489051904 +3DCube,N64,15,Poisson,OpenFOAM,4930450.0,OpenFOAM,Poisson,1.0 +3DCube,N64,16,Poisson,SerialExecutor,4146160.0,NeoN,Poisson,1.1891605726744747 +3DCube,N64,17,Poisson,GPUExecutor,1886180.0,NeoN,Poisson,2.6139870001802583 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv new file mode 100644 index 0000000..e2eebac --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/momentum.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,momentum,OpenFOAM,11097.9,OpenFOAM,without RHS,1.0 +2DSquare,N16,1,momentum,OpenFOAM,16790.1,OpenFOAM,with RHS,0.6609787910733111 +2DSquare,N16,2,momentum,SerialExecutor,88502.3,NeoN,without RHS,0.12539674110164367 +2DSquare,N16,3,momentum,SerialExecutor,140425.0,NeoN,with RHS,0.07903079935908848 +2DSquare,N16,4,momentum,GPUExecutor,2197590.0,NeoN,without RHS,0.0050500320805973815 +2DSquare,N16,5,momentum,GPUExecutor,3405040.0,NeoN,with RHS,0.0032592568662923194 +2DSquare,N256,18,momentum,OpenFOAM,2327260.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,19,momentum,OpenFOAM,3274020.0,OpenFOAM,with RHS,0.7108264457761406 +2DSquare,N256,20,momentum,SerialExecutor,8443040.0,NeoN,without RHS,0.27564242263450134 +2DSquare,N256,21,momentum,SerialExecutor,15813900.0,NeoN,with RHS,0.14716546835379002 +2DSquare,N256,22,momentum,GPUExecutor,2721950.0,NeoN,without RHS,0.8549973364683408 +2DSquare,N256,23,momentum,GPUExecutor,4270320.0,NeoN,with RHS,0.5449849191629668 +2DSquare,N64,24,momentum,OpenFOAM,78196.7,OpenFOAM,without RHS,1.0 +2DSquare,N64,25,momentum,OpenFOAM,127813.0,OpenFOAM,with RHS,0.6118055283891309 +2DSquare,N64,26,momentum,SerialExecutor,563342.0,NeoN,without RHS,0.13880857454264017 +2DSquare,N64,27,momentum,SerialExecutor,1018400.0,NeoN,with RHS,0.07678387666928516 +2DSquare,N64,28,momentum,GPUExecutor,2156060.0,NeoN,without RHS,0.03626833205012847 +2DSquare,N64,29,momentum,GPUExecutor,3341940.0,NeoN,with RHS,0.023398594828153707 +3DCube,N16,6,momentum,OpenFOAM,125748.0,OpenFOAM,without RHS,1.0 +3DCube,N16,7,momentum,OpenFOAM,207218.0,OpenFOAM,with RHS,0.6068391742030133 +3DCube,N16,8,momentum,SerialExecutor,853179.0,NeoN,without RHS,0.1473875939281206 +3DCube,N16,9,momentum,SerialExecutor,1553370.0,NeoN,with RHS,0.080951737190753 +3DCube,N16,10,momentum,GPUExecutor,2351050.0,NeoN,without RHS,0.053485889283511626 +3DCube,N16,11,momentum,GPUExecutor,3640820.0,NeoN,with RHS,0.03453837322361446 +3DCube,N32,12,momentum,OpenFOAM,1363740.0,OpenFOAM,without RHS,1.0 +3DCube,N32,13,momentum,OpenFOAM,1980950.0,OpenFOAM,with RHS,0.6884272697443146 +3DCube,N32,14,momentum,SerialExecutor,6332160.0,NeoN,without RHS,0.21536726804123713 +3DCube,N32,15,momentum,SerialExecutor,11888800.0,NeoN,with RHS,0.11470796043334903 +3DCube,N32,16,momentum,GPUExecutor,2658020.0,NeoN,without RHS,0.5130661168839964 +3DCube,N32,17,momentum,GPUExecutor,4091410.0,NeoN,with RHS,0.33331785374724116 +3DCube,N64,30,momentum,OpenFOAM,14533400.0,OpenFOAM,without RHS,1.0 +3DCube,N64,31,momentum,OpenFOAM,21873100.0,OpenFOAM,with RHS,0.6644417115086567 +3DCube,N64,32,momentum,SerialExecutor,65682800.0,NeoN,without RHS,0.22126645027313085 +3DCube,N64,33,momentum,SerialExecutor,118378000.0,NeoN,with RHS,0.12277112301272196 +3DCube,N64,34,momentum,GPUExecutor,4883740.0,NeoN,without RHS,2.9758750465831514 +3DCube,N64,35,momentum,GPUExecutor,8461970.0,NeoN,with RHS,1.717496044065389 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv new file mode 100644 index 0000000..0d6af2f --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/pressureVelocityCoupling.csv @@ -0,0 +1,55 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,pressureVelocityCoupling,CPU,1392.35,OpenFOAM,Compute rAU, +2DSquare,N16,1,pressureVelocityCoupling,CPU,4826.98,OpenFOAM,Compute HbyA, +2DSquare,N16,2,pressureVelocityCoupling,CPU,4383.84,OpenFOAM,constrainHbyA, +2DSquare,N16,3,pressureVelocityCoupling,SerialExecutor,12901.0,NeoN,Compute rAU, +2DSquare,N16,4,pressureVelocityCoupling,SerialExecutor,55529.0,NeoN,Compute HbyA, +2DSquare,N16,5,pressureVelocityCoupling,SerialExecutor,58.51,NeoN,constrainHbyA, +2DSquare,N16,6,pressureVelocityCoupling,GPUExecutor,647242.0,NeoN,Compute rAU, +2DSquare,N16,7,pressureVelocityCoupling,GPUExecutor,1999260.0,NeoN,Compute HbyA, +2DSquare,N16,8,pressureVelocityCoupling,GPUExecutor,367.12,NeoN,constrainHbyA, +2DSquare,N256,27,pressureVelocityCoupling,CPU,108592.0,OpenFOAM,Compute rAU, +2DSquare,N256,28,pressureVelocityCoupling,CPU,1321430.0,OpenFOAM,Compute HbyA, +2DSquare,N256,29,pressureVelocityCoupling,CPU,1322790.0,OpenFOAM,constrainHbyA, +2DSquare,N256,30,pressureVelocityCoupling,SerialExecutor,342499.0,NeoN,Compute rAU, +2DSquare,N256,31,pressureVelocityCoupling,SerialExecutor,3605080.0,NeoN,Compute HbyA, +2DSquare,N256,32,pressureVelocityCoupling,SerialExecutor,58.574,NeoN,constrainHbyA, +2DSquare,N256,33,pressureVelocityCoupling,GPUExecutor,799768.0,NeoN,Compute rAU, +2DSquare,N256,34,pressureVelocityCoupling,GPUExecutor,2482850.0,NeoN,Compute HbyA, +2DSquare,N256,35,pressureVelocityCoupling,GPUExecutor,369.144,NeoN,constrainHbyA, +2DSquare,N64,36,pressureVelocityCoupling,CPU,7044.01,OpenFOAM,Compute rAU, +2DSquare,N64,37,pressureVelocityCoupling,CPU,48755.3,OpenFOAM,Compute HbyA, +2DSquare,N64,38,pressureVelocityCoupling,CPU,52833.0,OpenFOAM,constrainHbyA, +2DSquare,N64,39,pressureVelocityCoupling,SerialExecutor,18084.9,NeoN,Compute rAU, +2DSquare,N64,40,pressureVelocityCoupling,SerialExecutor,238962.0,NeoN,Compute HbyA, +2DSquare,N64,41,pressureVelocityCoupling,SerialExecutor,58.2221,NeoN,constrainHbyA, +2DSquare,N64,42,pressureVelocityCoupling,GPUExecutor,668574.0,NeoN,Compute rAU, +2DSquare,N64,43,pressureVelocityCoupling,GPUExecutor,2077010.0,NeoN,Compute HbyA, +2DSquare,N64,44,pressureVelocityCoupling,GPUExecutor,367.739,NeoN,constrainHbyA, +3DCube,N16,9,pressureVelocityCoupling,CPU,10155.3,OpenFOAM,Compute rAU, +3DCube,N16,10,pressureVelocityCoupling,CPU,64750.5,OpenFOAM,Compute HbyA, +3DCube,N16,11,pressureVelocityCoupling,CPU,64076.8,OpenFOAM,constrainHbyA, +3DCube,N16,12,pressureVelocityCoupling,SerialExecutor,19740.2,NeoN,Compute rAU, +3DCube,N16,13,pressureVelocityCoupling,SerialExecutor,331935.0,NeoN,Compute HbyA, +3DCube,N16,14,pressureVelocityCoupling,SerialExecutor,254.38,NeoN,constrainHbyA, +3DCube,N16,15,pressureVelocityCoupling,GPUExecutor,684826.0,NeoN,Compute rAU, +3DCube,N16,16,pressureVelocityCoupling,GPUExecutor,2135420.0,NeoN,Compute HbyA, +3DCube,N16,17,pressureVelocityCoupling,GPUExecutor,22896.6,NeoN,constrainHbyA, +3DCube,N32,18,pressureVelocityCoupling,CPU,64004.8,OpenFOAM,Compute rAU, +3DCube,N32,19,pressureVelocityCoupling,CPU,763520.0,OpenFOAM,Compute HbyA, +3DCube,N32,20,pressureVelocityCoupling,CPU,762910.0,OpenFOAM,constrainHbyA, +3DCube,N32,21,pressureVelocityCoupling,SerialExecutor,203986.0,NeoN,Compute rAU, +3DCube,N32,22,pressureVelocityCoupling,SerialExecutor,2622560.0,NeoN,Compute HbyA, +3DCube,N32,23,pressureVelocityCoupling,SerialExecutor,1844.3,NeoN,constrainHbyA, +3DCube,N32,24,pressureVelocityCoupling,GPUExecutor,685166.0,NeoN,Compute rAU, +3DCube,N32,25,pressureVelocityCoupling,GPUExecutor,2514440.0,NeoN,Compute HbyA, +3DCube,N32,26,pressureVelocityCoupling,GPUExecutor,28710.2,NeoN,constrainHbyA, +3DCube,N64,45,pressureVelocityCoupling,CPU,796110.0,OpenFOAM,Compute rAU, +3DCube,N64,46,pressureVelocityCoupling,CPU,6351390.0,OpenFOAM,Compute HbyA, +3DCube,N64,47,pressureVelocityCoupling,CPU,7353860.0,OpenFOAM,constrainHbyA, +3DCube,N64,48,pressureVelocityCoupling,SerialExecutor,1192710.0,NeoN,Compute rAU, +3DCube,N64,49,pressureVelocityCoupling,SerialExecutor,21803800.0,NeoN,Compute HbyA, +3DCube,N64,50,pressureVelocityCoupling,SerialExecutor,6909.62,NeoN,constrainHbyA, +3DCube,N64,51,pressureVelocityCoupling,GPUExecutor,809767.0,NeoN,Compute rAU, +3DCube,N64,52,pressureVelocityCoupling,GPUExecutor,2709910.0,NeoN,Compute HbyA, +3DCube,N64,53,pressureVelocityCoupling,GPUExecutor,25185.9,NeoN,constrainHbyA, diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv new file mode 100644 index 0000000..56eb0e8 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/develop/scalarAdvection.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,scalarAdvection,OpenFOAM,9070.97,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,scalarAdvection,OpenFOAM,7960.05,OpenFOAM,implicit-time-integration,1.139561937425016 +2DSquare,N16,2,scalarAdvection,SerialExecutor,36931.6,NeoN,explicit-time-integration,0.2456154079433331 +2DSquare,N16,3,scalarAdvection,SerialExecutor,64472.4,NeoN,implicit-time-integration,0.1406953983409955 +2DSquare,N16,4,scalarAdvection,GPUExecutor,1744310.0,NeoN,explicit-time-integration,0.005200319897265967 +2DSquare,N16,5,scalarAdvection,GPUExecutor,2086350.0,NeoN,implicit-time-integration,0.0043477700289980105 +2DSquare,N256,18,scalarAdvection,OpenFOAM,1271200.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,19,scalarAdvection,OpenFOAM,1439170.0,OpenFOAM,implicit-time-integration,0.8832868945294857 +2DSquare,N256,20,scalarAdvection,SerialExecutor,868682.0,NeoN,explicit-time-integration,1.4633663411927496 +2DSquare,N256,21,scalarAdvection,SerialExecutor,4190710.0,NeoN,implicit-time-integration,0.30333762059412367 +2DSquare,N256,22,scalarAdvection,GPUExecutor,1593660.0,NeoN,explicit-time-integration,0.7976607306451815 +2DSquare,N256,23,scalarAdvection,GPUExecutor,2266920.0,NeoN,implicit-time-integration,0.5607608561396079 +2DSquare,N64,24,scalarAdvection,OpenFOAM,48983.2,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,25,scalarAdvection,OpenFOAM,55326.4,OpenFOAM,implicit-time-integration,0.8853494895745972 +2DSquare,N64,26,scalarAdvection,SerialExecutor,56100.2,NeoN,explicit-time-integration,0.8731377071739495 +2DSquare,N64,27,scalarAdvection,SerialExecutor,281126.0,NeoN,implicit-time-integration,0.174239309064263 +2DSquare,N64,28,scalarAdvection,GPUExecutor,1428650.0,NeoN,explicit-time-integration,0.03428635425051622 +2DSquare,N64,29,scalarAdvection,GPUExecutor,2009880.0,NeoN,implicit-time-integration,0.024371206241168626 +3DCube,N16,6,scalarAdvection,OpenFOAM,66817.9,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,7,scalarAdvection,OpenFOAM,77080.2,OpenFOAM,implicit-time-integration,0.8668620475816098 +3DCube,N16,8,scalarAdvection,SerialExecutor,64257.7,NeoN,explicit-time-integration,1.039842695894811 +3DCube,N16,9,scalarAdvection,SerialExecutor,417763.0,NeoN,implicit-time-integration,0.15994212029308483 +3DCube,N16,10,scalarAdvection,GPUExecutor,1542890.0,NeoN,explicit-time-integration,0.04330697586995832 +3DCube,N16,11,scalarAdvection,GPUExecutor,2321730.0,NeoN,implicit-time-integration,0.02877935849560457 +3DCube,N32,12,scalarAdvection,OpenFOAM,740530.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,13,scalarAdvection,OpenFOAM,1000840.0,OpenFOAM,implicit-time-integration,0.7399084768794213 +3DCube,N32,14,scalarAdvection,SerialExecutor,636714.0,NeoN,explicit-time-integration,1.1630496580882468 +3DCube,N32,15,scalarAdvection,SerialExecutor,3169190.0,NeoN,implicit-time-integration,0.23366538453043206 +3DCube,N32,16,scalarAdvection,GPUExecutor,1469180.0,NeoN,explicit-time-integration,0.5040430716454076 +3DCube,N32,17,scalarAdvection,GPUExecutor,2208210.0,NeoN,implicit-time-integration,0.3353530687751618 +3DCube,N64,30,scalarAdvection,OpenFOAM,6719030.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,31,scalarAdvection,OpenFOAM,10664100.0,OpenFOAM,implicit-time-integration,0.630060670848923 +3DCube,N64,32,scalarAdvection,SerialExecutor,5412200.0,NeoN,explicit-time-integration,1.2414600347363365 +3DCube,N64,33,scalarAdvection,SerialExecutor,26955900.0,NeoN,implicit-time-integration,0.2492600877729922 +3DCube,N64,34,scalarAdvection,GPUExecutor,1955110.0,NeoN,explicit-time-integration,3.4366506232385903 +3DCube,N64,35,scalarAdvection,GPUExecutor,3143370.0,NeoN,implicit-time-integration,2.137524376703983 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/momentum.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/momentum.csv new file mode 100644 index 0000000..1b0de3a --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/momentum.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,momentum,OpenFOAM,10470.9,OpenFOAM,without RHS,1.0 +2DSquare,N16,1,momentum,OpenFOAM,15770.1,OpenFOAM,with RHS,0.6639716932676394 +2DSquare,N16,2,momentum,SerialExecutor,88363.9,NeoN,without RHS,0.11849748596429086 +2DSquare,N16,3,momentum,SerialExecutor,139664.0,NeoN,with RHS,0.07497207583915683 +2DSquare,N16,4,momentum,GPUExecutor,2394720.0,NeoN,without RHS,0.004372494487873321 +2DSquare,N16,5,momentum,GPUExecutor,3461430.0,NeoN,with RHS,0.003025021450672121 +2DSquare,N256,18,momentum,OpenFOAM,2141880.0,OpenFOAM,without RHS,1.0 +2DSquare,N256,19,momentum,OpenFOAM,3059360.0,OpenFOAM,with RHS,0.7001072119659013 +2DSquare,N256,20,momentum,SerialExecutor,8348810.0,NeoN,without RHS,0.2565491369428697 +2DSquare,N256,21,momentum,SerialExecutor,15752900.0,NeoN,with RHS,0.13596734569507837 +2DSquare,N256,22,momentum,GPUExecutor,2734740.0,NeoN,without RHS,0.7832115667302925 +2DSquare,N256,23,momentum,GPUExecutor,4222320.0,NeoN,with RHS,0.5072756209856193 +2DSquare,N64,24,momentum,OpenFOAM,78541.2,OpenFOAM,without RHS,1.0 +2DSquare,N64,25,momentum,OpenFOAM,126909.0,OpenFOAM,with RHS,0.6188780937522161 +2DSquare,N64,26,momentum,SerialExecutor,546538.0,NeoN,without RHS,0.14370675049127415 +2DSquare,N64,27,momentum,SerialExecutor,1005070.0,NeoN,with RHS,0.07814500482553453 +2DSquare,N64,28,momentum,GPUExecutor,2343190.0,NeoN,without RHS,0.03351892078747348 +2DSquare,N64,29,momentum,GPUExecutor,3434970.0,NeoN,with RHS,0.022865177861815387 +3DCube,N16,6,momentum,OpenFOAM,118322.0,OpenFOAM,without RHS,1.0 +3DCube,N16,7,momentum,OpenFOAM,187809.0,OpenFOAM,with RHS,0.6300124062212141 +3DCube,N16,8,momentum,SerialExecutor,828402.0,NeoN,without RHS,0.14283162039686045 +3DCube,N16,9,momentum,SerialExecutor,1530780.0,NeoN,with RHS,0.07729523510889873 +3DCube,N16,10,momentum,GPUExecutor,2177710.0,NeoN,without RHS,0.05433322159516189 +3DCube,N16,11,momentum,GPUExecutor,3396400.0,NeoN,with RHS,0.034837474973501356 +3DCube,N32,12,momentum,OpenFOAM,1355940.0,OpenFOAM,without RHS,1.0 +3DCube,N32,13,momentum,OpenFOAM,1988520.0,OpenFOAM,with RHS,0.6818840142417476 +3DCube,N32,14,momentum,SerialExecutor,6336310.0,NeoN,without RHS,0.21399521172417385 +3DCube,N32,15,momentum,SerialExecutor,11889300.0,NeoN,with RHS,0.11404708435315788 +3DCube,N32,16,momentum,GPUExecutor,2655520.0,NeoN,without RHS,0.5106118575646201 +3DCube,N32,17,momentum,GPUExecutor,4163560.0,NeoN,with RHS,0.3256684183727387 +3DCube,N64,30,momentum,OpenFOAM,15302000.0,OpenFOAM,without RHS,1.0 +3DCube,N64,31,momentum,OpenFOAM,23191300.0,OpenFOAM,with RHS,0.6598163966659911 +3DCube,N64,32,momentum,SerialExecutor,66691300.0,NeoN,without RHS,0.22944521999121326 +3DCube,N64,33,momentum,SerialExecutor,119578000.0,NeoN,with RHS,0.12796668283463514 +3DCube,N64,34,momentum,GPUExecutor,4901850.0,NeoN,without RHS,3.1216785499352286 +3DCube,N64,35,momentum,GPUExecutor,8445220.0,NeoN,with RHS,1.8119125375064238 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv new file mode 100644 index 0000000..0fd321a --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/pressureVelocityCoupling.csv @@ -0,0 +1,55 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,pressureVelocityCoupling,CPU,1376.13,OpenFOAM,Compute rAU, +2DSquare,N16,1,pressureVelocityCoupling,CPU,4650.77,OpenFOAM,Compute HbyA, +2DSquare,N16,2,pressureVelocityCoupling,CPU,4257.34,OpenFOAM,constrainHbyA, +2DSquare,N16,3,pressureVelocityCoupling,SerialExecutor,13209.3,NeoN,Compute rAU, +2DSquare,N16,4,pressureVelocityCoupling,SerialExecutor,56463.6,NeoN,Compute HbyA, +2DSquare,N16,5,pressureVelocityCoupling,SerialExecutor,58.5674,NeoN,constrainHbyA, +2DSquare,N16,6,pressureVelocityCoupling,GPUExecutor,719398.0,NeoN,Compute rAU, +2DSquare,N16,7,pressureVelocityCoupling,GPUExecutor,2338740.0,NeoN,Compute HbyA, +2DSquare,N16,8,pressureVelocityCoupling,GPUExecutor,364.619,NeoN,constrainHbyA, +2DSquare,N256,27,pressureVelocityCoupling,CPU,100619.0,OpenFOAM,Compute rAU, +2DSquare,N256,28,pressureVelocityCoupling,CPU,1169470.0,OpenFOAM,Compute HbyA, +2DSquare,N256,29,pressureVelocityCoupling,CPU,1150750.0,OpenFOAM,constrainHbyA, +2DSquare,N256,30,pressureVelocityCoupling,SerialExecutor,258650.0,NeoN,Compute rAU, +2DSquare,N256,31,pressureVelocityCoupling,SerialExecutor,3529830.0,NeoN,Compute HbyA, +2DSquare,N256,32,pressureVelocityCoupling,SerialExecutor,57.9398,NeoN,constrainHbyA, +2DSquare,N256,33,pressureVelocityCoupling,GPUExecutor,647843.0,NeoN,Compute rAU, +2DSquare,N256,34,pressureVelocityCoupling,GPUExecutor,2084030.0,NeoN,Compute HbyA, +2DSquare,N256,35,pressureVelocityCoupling,GPUExecutor,374.821,NeoN,constrainHbyA, +2DSquare,N64,36,pressureVelocityCoupling,CPU,7034.81,OpenFOAM,Compute rAU, +2DSquare,N64,37,pressureVelocityCoupling,CPU,49309.0,OpenFOAM,Compute HbyA, +2DSquare,N64,38,pressureVelocityCoupling,CPU,49535.9,OpenFOAM,constrainHbyA, +2DSquare,N64,39,pressureVelocityCoupling,SerialExecutor,18470.3,NeoN,Compute rAU, +2DSquare,N64,40,pressureVelocityCoupling,SerialExecutor,240016.0,NeoN,Compute HbyA, +2DSquare,N64,41,pressureVelocityCoupling,SerialExecutor,56.6659,NeoN,constrainHbyA, +2DSquare,N64,42,pressureVelocityCoupling,GPUExecutor,667515.0,NeoN,Compute rAU, +2DSquare,N64,43,pressureVelocityCoupling,GPUExecutor,2083930.0,NeoN,Compute HbyA, +2DSquare,N64,44,pressureVelocityCoupling,GPUExecutor,364.071,NeoN,constrainHbyA, +3DCube,N16,9,pressureVelocityCoupling,CPU,10103.7,OpenFOAM,Compute rAU, +3DCube,N16,10,pressureVelocityCoupling,CPU,66568.2,OpenFOAM,Compute HbyA, +3DCube,N16,11,pressureVelocityCoupling,CPU,64581.0,OpenFOAM,constrainHbyA, +3DCube,N16,12,pressureVelocityCoupling,SerialExecutor,19516.1,NeoN,Compute rAU, +3DCube,N16,13,pressureVelocityCoupling,SerialExecutor,331042.0,NeoN,Compute HbyA, +3DCube,N16,14,pressureVelocityCoupling,SerialExecutor,256.28,NeoN,constrainHbyA, +3DCube,N16,15,pressureVelocityCoupling,GPUExecutor,740570.0,NeoN,Compute rAU, +3DCube,N16,16,pressureVelocityCoupling,GPUExecutor,2407670.0,NeoN,Compute HbyA, +3DCube,N16,17,pressureVelocityCoupling,GPUExecutor,23296.6,NeoN,constrainHbyA, +3DCube,N32,18,pressureVelocityCoupling,CPU,64782.9,OpenFOAM,Compute rAU, +3DCube,N32,19,pressureVelocityCoupling,CPU,674181.0,OpenFOAM,Compute HbyA, +3DCube,N32,20,pressureVelocityCoupling,CPU,674314.0,OpenFOAM,constrainHbyA, +3DCube,N32,21,pressureVelocityCoupling,SerialExecutor,140198.0,NeoN,Compute rAU, +3DCube,N32,22,pressureVelocityCoupling,SerialExecutor,2592020.0,NeoN,Compute HbyA, +3DCube,N32,23,pressureVelocityCoupling,SerialExecutor,1790.16,NeoN,constrainHbyA, +3DCube,N32,24,pressureVelocityCoupling,GPUExecutor,718472.0,NeoN,Compute rAU, +3DCube,N32,25,pressureVelocityCoupling,GPUExecutor,2376000.0,NeoN,Compute HbyA, +3DCube,N32,26,pressureVelocityCoupling,GPUExecutor,24130.2,NeoN,constrainHbyA, +3DCube,N64,45,pressureVelocityCoupling,CPU,788823.0,OpenFOAM,Compute rAU, +3DCube,N64,46,pressureVelocityCoupling,CPU,6312460.0,OpenFOAM,Compute HbyA, +3DCube,N64,47,pressureVelocityCoupling,CPU,6819460.0,OpenFOAM,constrainHbyA, +3DCube,N64,48,pressureVelocityCoupling,SerialExecutor,1193120.0,NeoN,Compute rAU, +3DCube,N64,49,pressureVelocityCoupling,SerialExecutor,21722000.0,NeoN,Compute HbyA, +3DCube,N64,50,pressureVelocityCoupling,SerialExecutor,7037.81,NeoN,constrainHbyA, +3DCube,N64,51,pressureVelocityCoupling,GPUExecutor,817261.0,NeoN,Compute rAU, +3DCube,N64,52,pressureVelocityCoupling,GPUExecutor,2692570.0,NeoN,Compute HbyA, +3DCube,N64,53,pressureVelocityCoupling,GPUExecutor,24477.9,NeoN,constrainHbyA, diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv new file mode 100644 index 0000000..bc75462 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/scalarAdvection.csv @@ -0,0 +1,37 @@ +MeshType,Resolution,level_2,test_case,benchmark_name,avg_runtime,section1,section2,normalized_speedup +2DSquare,N16,0,scalarAdvection,OpenFOAM,8630.76,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N16,1,scalarAdvection,OpenFOAM,7940.15,OpenFOAM,implicit-time-integration,1.0869769462793524 +2DSquare,N16,2,scalarAdvection,SerialExecutor,37186.5,NeoN,explicit-time-integration,0.23209390504618613 +2DSquare,N16,3,scalarAdvection,SerialExecutor,63529.0,NeoN,implicit-time-integration,0.1358554361000488 +2DSquare,N16,4,scalarAdvection,GPUExecutor,1371380.0,NeoN,explicit-time-integration,0.006293485394274381 +2DSquare,N16,5,scalarAdvection,GPUExecutor,1992550.0,NeoN,implicit-time-integration,0.004331514892976337 +2DSquare,N256,18,scalarAdvection,OpenFOAM,1172980.0,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N256,19,scalarAdvection,OpenFOAM,1467380.0,OpenFOAM,implicit-time-integration,0.7993703062601372 +2DSquare,N256,20,scalarAdvection,SerialExecutor,816399.0,NeoN,explicit-time-integration,1.436772950481321 +2DSquare,N256,21,scalarAdvection,SerialExecutor,4230680.0,NeoN,implicit-time-integration,0.2772556657558596 +2DSquare,N256,22,scalarAdvection,GPUExecutor,1626860.0,NeoN,explicit-time-integration,0.7210085686537255 +2DSquare,N256,23,scalarAdvection,GPUExecutor,2415300.0,NeoN,implicit-time-integration,0.48564567548544696 +2DSquare,N64,24,scalarAdvection,OpenFOAM,51569.8,OpenFOAM,explicit-time-integration,1.0 +2DSquare,N64,25,scalarAdvection,OpenFOAM,56188.2,OpenFOAM,implicit-time-integration,0.9178048059912937 +2DSquare,N64,26,scalarAdvection,SerialExecutor,56738.8,NeoN,explicit-time-integration,0.9088983200208676 +2DSquare,N64,27,scalarAdvection,SerialExecutor,280614.0,NeoN,implicit-time-integration,0.18377486511720728 +2DSquare,N64,28,scalarAdvection,GPUExecutor,1715500.0,NeoN,explicit-time-integration,0.030061090061206646 +2DSquare,N64,29,scalarAdvection,GPUExecutor,2524840.0,NeoN,implicit-time-integration,0.020424977424312037 +3DCube,N16,6,scalarAdvection,OpenFOAM,67830.5,OpenFOAM,explicit-time-integration,1.0 +3DCube,N16,7,scalarAdvection,OpenFOAM,78801.3,OpenFOAM,implicit-time-integration,0.860778946540222 +3DCube,N16,8,scalarAdvection,SerialExecutor,64455.7,NeoN,explicit-time-integration,1.052358441534263 +3DCube,N16,9,scalarAdvection,SerialExecutor,411102.0,NeoN,implicit-time-integration,0.1649967647931657 +3DCube,N16,10,scalarAdvection,GPUExecutor,1425240.0,NeoN,explicit-time-integration,0.04759233532598019 +3DCube,N16,11,scalarAdvection,GPUExecutor,2113120.0,NeoN,implicit-time-integration,0.03209969145150299 +3DCube,N32,12,scalarAdvection,OpenFOAM,670895.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N32,13,scalarAdvection,OpenFOAM,934346.0,OpenFOAM,implicit-time-integration,0.7180370012821803 +3DCube,N32,14,scalarAdvection,SerialExecutor,559755.0,NeoN,explicit-time-integration,1.198551151843217 +3DCube,N32,15,scalarAdvection,SerialExecutor,3169760.0,NeoN,implicit-time-integration,0.21165482560193832 +3DCube,N32,16,scalarAdvection,GPUExecutor,1598160.0,NeoN,explicit-time-integration,0.4197921359563498 +3DCube,N32,17,scalarAdvection,GPUExecutor,2285950.0,NeoN,implicit-time-integration,0.2934862967256502 +3DCube,N64,30,scalarAdvection,OpenFOAM,8865640.0,OpenFOAM,explicit-time-integration,1.0 +3DCube,N64,31,scalarAdvection,OpenFOAM,11077900.0,OpenFOAM,implicit-time-integration,0.8002996957907185 +3DCube,N64,32,scalarAdvection,SerialExecutor,5270460.0,NeoN,explicit-time-integration,1.6821378020134865 +3DCube,N64,33,scalarAdvection,SerialExecutor,27926900.0,NeoN,implicit-time-integration,0.3174587942091675 +3DCube,N64,34,scalarAdvection,GPUExecutor,2158240.0,NeoN,explicit-time-integration,4.107810067462377 +3DCube,N64,35,scalarAdvection,GPUExecutor,3595910.0,NeoN,implicit-time-integration,2.4654788356772 diff --git a/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/system-info.log b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/system-info.log new file mode 100644 index 0000000..53c3ad5 --- /dev/null +++ b/NeoFOAM/222/neon-cluster-meta-runner-adapter-amd/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: Intel(R) Xeon(R) Gold 6438Y+ +CPU family: 6 +Model: 143 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 8 +BogoMIPS: 4000.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Indirect target selection: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== + + +============================ ROCm System Management Interface ============================ +========================================= VBIOS ========================================== +GPU[0] : VBIOS version: 113-D67301V-073 +========================================================================================== +====================================== Product Info ====================================== +GPU[0] : Card Series: AMD Instinct MI210 +GPU[0] : Card Model: 0x740f +GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] +GPU[0] : Card SKU: D67301V +GPU[0] : Subsystem ID: 0x0c34 +GPU[0] : Device Rev: 0x02 +GPU[0] : Node ID: 2 +GPU[0] : GUID: 1997 +GPU[0] : GFX Version: gfx90a +========================================================================================== +================================== End of ROCm SMI Log =================================== + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +HIP version: 6.4.43483-a187df25c +AMD clang version 19.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.4.1 25184 c87081df219c42dc27c5b6d86c0525bc7d01f727) +Target: x86_64-unknown-linux-gnu +Thread model: posix +InstalledDir: /opt/rocm-6.4.1/lib/llvm/bin +Configuration file: /opt/rocm-6.4.1/lib/llvm/bin/clang++.cfg diff --git a/benchmark-results/system-info.log b/benchmark-results/system-info.log new file mode 100644 index 0000000..86a4767 --- /dev/null +++ b/benchmark-results/system-info.log @@ -0,0 +1,81 @@ +===== CPU INFO ===== +Architecture: x86_64 +CPU op-mode(s): 32-bit, 64-bit +Address sizes: 46 bits physical, 57 bits virtual +Byte Order: Little Endian +CPU(s): 128 +On-line CPU(s) list: 0-127 +Vendor ID: GenuineIntel +Model name: INTEL(R) XEON(R) GOLD 6548N +CPU family: 6 +Model: 207 +Thread(s) per core: 2 +Core(s) per socket: 32 +Socket(s): 2 +Stepping: 2 +BogoMIPS: 5600.00 +Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities +Virtualization: VT-x +L1d cache: 3 MiB (64 instances) +L1i cache: 2 MiB (64 instances) +L2 cache: 128 MiB (64 instances) +L3 cache: 120 MiB (2 instances) +NUMA node(s): 2 +NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126 +NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127 +Vulnerability Gather data sampling: Not affected +Vulnerability Itlb multihit: Not affected +Vulnerability L1tf: Not affected +Vulnerability Mds: Not affected +Vulnerability Meltdown: Not affected +Vulnerability Mmio stale data: Not affected +Vulnerability Reg file data sampling: Not affected +Vulnerability Retbleed: Not affected +Vulnerability Spec rstack overflow: Not affected +Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl +Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization +Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S +Vulnerability Srbds: Not affected +Vulnerability Tsx async abort: Not affected + +===== GPU INFO ===== +Tue Oct 14 15:50:45 2025 ++-----------------------------------------------------------------------------------------+ +| NVIDIA-SMI 575.51.03 Driver Version: 575.51.03 CUDA Version: 12.9 | +|-----------------------------------------+------------------------+----------------------+ +| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | +| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | +| | | MIG M. | +|=========================================+========================+======================| +| 0 NVIDIA H100 NVL On | 00000000:4A:00.0 Off | 0 | +| N/A 29C P0 60W / 400W | 0MiB / 95830MiB | 0% Default | +| | | Disabled | ++-----------------------------------------+------------------------+----------------------+ + ++-----------------------------------------------------------------------------------------+ +| Processes: | +| GPU GI CI PID Type Process name GPU Memory | +| ID ID Usage | +|=========================================================================================| +| No running processes found | ++-----------------------------------------------------------------------------------------+ + +===== COMPILER INFO ===== +CMake: +cmake version 3.28.3 + +CMake suite maintained and supported by Kitware (kitware.com/cmake). + +C++ compiler: +g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 +Copyright (C) 2023 Free Software Foundation, Inc. +This is free software; see the source for copying conditions. There is NO +warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + + +CUDA/ROCm compiler: +nvcc: NVIDIA (R) Cuda compiler driver +Copyright (c) 2005-2025 NVIDIA Corporation +Built on Fri_Feb_21_20:23:50_PST_2025 +Cuda compilation tools, release 12.8, V12.8.93 +Build cuda_12.8.r12.8/compiler.35583870_0