compilation fails with -cl-opt-disable

[pszi1ard]

When compiling with -cl-opt-disable, I get the following errors (one for each kernel function):

: error: can't create dynamic relocation R_AMDGPU_REL32_LO against symbol: norm2 in readonly segment; recompile object files with -fPIC
>>> defined in /tmp/t_20283_71-5d7565.o
>>> referenced by /tmp/t_20283_71-5d7565.o:(nbnxn_kernel_prune_opencl)

: error: can't create dynamic relocation R_AMDGPU_REL32_HI against symbol: norm2 in readonly segment; recompile object files with -fPIC
>>> defined in /tmp/t_20283_71-5d7565.o
>>> referenced by /tmp/t_20283_71-5d7565.o:(nbnxn_kernel_prune_opencl)
[...]

[gstoner]

Need more info then this, we need to know which driver your using 1.7, is it the stock OpenCL runtime

run clinfo

G

[emankov]

Could you please provide the command line as well?

[pszi1ard]

Apologies for the missing details. I'm using GROMACS v2018, with default flags plus -cl-opt-disable (note this cab be repro-d by passing the GMX_OCL_NOOPT=1 env var to GROMACS). Admittedly, I was hoping this overrides all other command line options, including optimization options, though it may not; still, I'd hope for a more friendly error if that's the issue.

Here's the generated list of command line option (minus the -D's): -cl-opt-disable -cl-fast-relaxed-math

I'm using 1.7.1-rc5 (IIRC), here's the clinfo output:

Number of platforms:				 1
  Platform Profile:				 FULL_PROFILE
  Platform Version:				 OpenCL 2.1 AMD-APP.internal (2545.0)
  Platform Name:				 AMD Accelerated Parallel Processing
  Platform Vendor:				 Advanced Micro Devices, Inc.
  Platform Extensions:				 cl_khr_icd cl_amd_object_metadata cl_amd_event_callback 


  Platform Name:				 AMD Accelerated Parallel Processing
Number of devices:				 2
  Device Type:					 CL_DEVICE_TYPE_GPU
  Vendor ID:					 1002h
  Board name:					 Fiji [Radeon R9 FURY / NANO Series]
  Device Topology:				 PCI[ B#2, D#0, F#0 ]
  Max compute units:				 64
  Max work items dimensions:			 3
    Max work items[0]:				 1024
    Max work items[1]:				 1024
    Max work items[2]:				 1024
  Max work group size:				 256
  Preferred vector width char:			 4
  Preferred vector width short:			 2
  Preferred vector width int:			 1
  Preferred vector width long:			 1
  Preferred vector width float:			 1
  Preferred vector width double:		 1
  Native vector width char:			 4
  Native vector width short:			 2
  Native vector width int:			 1
  Native vector width long:			 1
  Native vector width float:			 1
  Native vector width double:			 1
  Max clock frequency:				 1000Mhz
  Address bits:					 64
  Max memory allocation:			 3650722201
  Image support:				 Yes
  Max number of images read arguments:		 128
  Max number of images write arguments:		 8
  Max image 2D width:				 16384
  Max image 2D height:				 16384
  Max image 3D width:				 2048
  Max image 3D height:				 2048
  Max image 3D depth:				 2048
  Max samplers within kernel:			 29440
  Max size of kernel argument:			 1024
  Alignment (bits) of base address:		 1024
  Minimum alignment (bytes) for any datatype:	 128
  Single precision floating point capability
    Denorms:					 No
    Quiet NaNs:					 Yes
    Round to nearest even:			 Yes
    Round to zero:				 Yes
    Round to +ve and infinity:			 Yes
    IEEE754-2008 fused multiply-add:		 Yes
  Cache type:					 Read/Write
  Cache line size:				 64
  Cache size:					 16384
  Global memory size:				 4294967296
  Constant buffer size:				 3650722201
  Max number of constant args:			 8
  Local memory type:				 Scratchpad
  Local memory size:				 65536
  Max pipe arguments:				 16
  Max pipe active reservations:			 16
  Max pipe packet size:				 3650722201
  Max global variable size:			 3650722201
  Max global variable preferred total size:	 4294967296
  Max read/write image args:			 64
  Max on device events:				 0
  Queue on device max size:			 0
  Max on device queues:				 0
  Queue on device preferred size:		 0
  SVM capabilities:				 
    Coarse grain buffer:			 Yes
    Fine grain buffer:				 Yes
    Fine grain system:				 No
    Atomics:					 No
  Preferred platform atomic alignment:		 0
  Preferred global atomic alignment:		 0
  Preferred local atomic alignment:		 0
  Kernel Preferred work group size multiple:	 64
  Error correction support:			 0
  Unified memory for Host and Device:		 0
  Profiling timer resolution:			 1
  Device endianess:				 Little
  Available:					 Yes
  Compiler available:				 Yes
  Execution capabilities:				 
    Execute OpenCL kernels:			 Yes
    Execute native function:			 No
  Queue on Host properties:				 
    Out-of-Order:				 No
    Profiling :					 Yes
  Queue on Device properties:				 
    Out-of-Order:				 No
    Profiling :					 No
  Platform ID:					 0x7fa0da4d3370
  Name:						 gfx803
  Vendor:					 Advanced Micro Devices, Inc.
  Device OpenCL C version:			 OpenCL C 2.0 
  Driver version:				 2545.0 (HSA1.1,LC)
  Profile:					 FULL_PROFILE
  Version:					 OpenCL 1.2 
  Extensions:					 cl_khr_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p 


  Device Type:					 CL_DEVICE_TYPE_GPU
  Vendor ID:					 1002h
  Board name:					 Device 6863
  Device Topology:				 PCI[ B#5, D#0, F#0 ]
  Max compute units:				 64
  Max work items dimensions:			 3
    Max work items[0]:				 1024
    Max work items[1]:				 1024
    Max work items[2]:				 1024
  Max work group size:				 256
  Preferred vector width char:			 4
  Preferred vector width short:			 2
  Preferred vector width int:			 1
  Preferred vector width long:			 1
  Preferred vector width float:			 1
  Preferred vector width double:		 1
  Native vector width char:			 4
  Native vector width short:			 2
  Native vector width int:			 1
  Native vector width long:			 1
  Native vector width float:			 1
  Native vector width double:			 1
  Max clock frequency:				 1600Mhz
  Address bits:					 64
  Max memory allocation:			 14588628172
  Image support:				 Yes
  Max number of images read arguments:		 128
  Max number of images write arguments:		 8
  Max image 2D width:				 16384
  Max image 2D height:				 16384
  Max image 3D width:				 2048
  Max image 3D height:				 2048
  Max image 3D depth:				 2048
  Max samplers within kernel:			 26723
  Max size of kernel argument:			 1024
  Alignment (bits) of base address:		 1024
  Minimum alignment (bytes) for any datatype:	 128
  Single precision floating point capability
    Denorms:					 Yes
    Quiet NaNs:					 Yes
    Round to nearest even:			 Yes
    Round to zero:				 Yes
    Round to +ve and infinity:			 Yes
    IEEE754-2008 fused multiply-add:		 Yes
  Cache type:					 Read/Write
  Cache line size:				 64
  Cache size:					 16384
  Global memory size:				 17163091968
  Constant buffer size:				 14588628172
  Max number of constant args:			 8
  Local memory type:				 Scratchpad
  Local memory size:				 65536
  Max pipe arguments:				 16
  Max pipe active reservations:			 16
  Max pipe packet size:				 1703726284
  Max global variable size:			 14588628172
  Max global variable preferred total size:	 17163091968
  Max read/write image args:			 64
  Max on device events:				 0
  Queue on device max size:			 0
  Max on device queues:				 0
  Queue on device preferred size:		 0
  SVM capabilities:				 
    Coarse grain buffer:			 Yes
    Fine grain buffer:				 Yes
    Fine grain system:				 No
    Atomics:					 No
  Preferred platform atomic alignment:		 0
  Preferred global atomic alignment:		 0
  Preferred local atomic alignment:		 0
  Kernel Preferred work group size multiple:	 64
  Error correction support:			 0
  Unified memory for Host and Device:		 0
  Profiling timer resolution:			 1
  Device endianess:				 Little
  Available:					 Yes
  Compiler available:				 Yes
  Execution capabilities:				 
    Execute OpenCL kernels:			 Yes
    Execute native function:			 No
  Queue on Host properties:				 
    Out-of-Order:				 No
    Profiling :					 Yes
  Queue on Device properties:				 
    Out-of-Order:				 No
    Profiling :					 No
  Platform ID:					 0x7fa0da4d3370
  Name:						 gfx900
  Vendor:					 Advanced Micro Devices, Inc.
  Device OpenCL C version:			 OpenCL C 2.0 
  Driver version:				 2545.0 (HSA1.1,LC)
  Profile:					 FULL_PROFILE
  Version:					 OpenCL 1.2 
  Extensions:					 cl_khr_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_media_ops cl_amd_media_ops2 cl_khr_subgroups cl_khr_depth_images cl_amd_copy_buffer_p2p 

[pszi1ard]

PS: Removing the -cl-fast-relaxed-math does not fix the original issue.

[kzhuravl]

Hi @pszi1ard,

I fixed similar issue earlier. Can you try with the newer version of compiler, which includes this commit: ROCm/clang@217f7ef#diff-6e55490bc6f998368636d91d111084a2 ?

[pszi1ard]

@kzhuravl will this be in 1.7.1 (asking because I'm short on time so I'd rather wait for the release and test it).

[gstoner]

@pszi1ard currently it is not, I am looking to see it is possible