From 8608e552baf7254ba3e435c76f87c41db24302e0 Mon Sep 17 00:00:00 2001 From: glutenperfbot Date: Fri, 26 Jun 2026 13:04:17 +0000 Subject: [PATCH] [GLUTEN-6887][VL] Daily Update Velox Version (dft-2026_06_26) Upstream Velox's New Commits: 4741b5227 by Chandrashekhar Kumar Singh, feat(cursor): Add a non-blocking future to TaskCursor::moveNext (#17930) afecd6753 by Wei He, fix(fuzzer): Handle zero selected rows in ExpressionVerifier (#17934) 69519c68d by inf, fix(iceberg): Min max statistics for decimal type when encoded as int32 (#17894) 3069f55ca by Bikramjeet Vig, test: Fix failing table scan and table writer tests (#17929) ae44d34da by Bradley Dice, test: Make DirectBufferedInputTest.duplicateRegionsShareCoalescedRead deterministic (#17912) ea74295fc by Reema Alzaid, feat: Add Spark cast mode special form registration (#17687) b00bd14ab by Hongze Zhang, build: Fix missing fbthrift generated headers when Velox is imported as CMake submodule (#17797) e9ff792c0 by sungwoo-XCENA, build(cxl): Install libnuma in the setup scripts (#17909) 39db1a2c5 by Natasha Sehgal, refactor: Consolidate coercion into a recursive coerce() (#17921) 1a4d1241a by Bikramjeet Vig, feat: Fuzz non-contiguous array and map elements in VectorFuzzer (#17882) 2150b78c0 by Natasha Sehgal, fix(tdigest): Name destructure_tdigest output row fields (#17907) e37eabc47 by generatedunixname1395027625275998, Reserve hash set capacity in ArrayUnionFunction to avoid rehashing (#17773) 8bd7be543 by Ke Wang, refactor(velox): Rename timer classes to clarify clock source (#17919) 903de0446 by Avanish Mishra, perf: Report SST encode CPU as backgroundTiming in VeloxPlan stats (#17832) 91c5264b3 by Zhichen Xu, fix: Add missing FBThrift::thriftcpp2 link dep to velox_rpc_error_classification (#17922) 19662761c by Zhichen Xu, feat: Unify RPC PER_ROW/BATCH flow control with a latency-gradient congestion window (#17886) 2287151d5 by Bikramjeet Vig, misc: Add bounds DCHECK to ArrayView element access (#17880) 1c0f6f381 by Bikramjeet Vig, test: Verify VectorFuzzer naturally generates empty arrays/maps (#17879) 6cbb52cc8 by Bikramjeet Vig, feat: Generate garbage data behind nulls in VectorFuzzer (#17878) 41ab906b2 by Masha Basmanova, refactor(exec): Move AssignUniqueId task id to PlanFragment (#17915) 454c98d61 by Masha Basmanova, fix(exec): Share AssignUniqueId row id pool across a task (#17914) 235d3df9d by Bikramjeet Vig, fix: Prevent crash when copying FlatMapVector with view inMaps buffers (#17910) ac91ac9a3 by Zac Wen, refactor: Extract HiveIndexSourceUtils from anonymous namespace (#17903) 2c782deba by dependabot[bot], build(deps): Bump webpack-dev-server from 5.2.4 to 5.2.5 in /website (#17877) 43a3fc7cb by Natasha Sehgal, fix: Resolve UNKNOWN coercion to parameterized signatures (#17290) dba9f1cad by Bikramjeet Vig, perf: Lazily evaluate RowVector's containsLazyNotLoaded_ state (#17642) 5ca9a9532 by Sebastiano Peluso, fix(rpc): Fix batch response row-alignment (#17904) cce374a36 by Ke Wang, refactor(velox): Rename ColumnMetrics to DecodingStats (#17913) 3458f9357 by Sebastiano Peluso, fix(rpc): Fix deadlock in RPCState::addPendingBatch (#17902) 45975e8d6 by Sebastiano Peluso, test(rpc): Add DemoBatchRPCFunction for batch-mode operator testing (#17854) e603dc1ed by dependabot[bot], build(ci): Bump docker/setup-buildx-action from 3.11.1 to 4.1.0 (#17889) 55aac34e5 by Kostas Xirogiannopoulos, refactor(hive): Pass maxNumBuckets to FileNameGenerator gen() (#17892) d439b4ecf by Ke Wang, fix: Use verbose cache state in makeSpace failure message (#17896) b414e22d7 by Ping Liu, refactor: Breaking - Make common writer options format-agnostic (#17858) 14dd26f08 by Matt Gara, fix(cudf): Preserve zero-column hash join row counts (#17367) 072b4afea by Mariam-Almesfer, feat: Add Spark CAST(timestamp_utc as varchar) (#17514) 9c8db07d2 by wecharyu, fix: Core dump when import UnknownType arrow array (#17732) 5a397b22b by n0r0shi, feat: Make Spark remainder function ANSI-compliant (#17885) 7096ab48d by Ke Wang, fix: Fix misleading "0B" in AsyncDataCache contiguous allocation failure message (#17876) 888128106 by Ke Jia, feat: Add add() and exist() API in HashTableCache for Gluten (#17662) 1d05891bc by Deepak Majeti, fix(parquet): Check rowgroup in range before filterRowGroups (#17836) 280903fc4 by Xiaoxuan Meng, docs: Add Ping Liu as Iceberg and Parquet maintainer (#17859) aac6209b6 by Natasha Sehgal, fix: Don't emit duplicate default global grouping-set rows with multiple drivers (#17785) 5ded8d7c0 by Simon Eves, feat(cudf): GPU Decimal (Part 3) (#16751) eecbc6057 by Apurva Kumar, feat: Collect per-column statistics for DWRF/ORC Iceberg writes (#17881) bdd93b5fa by Prashant Golash, feat: Make nimble_lazy_column_io a session-overridable config (#17871) 3f4001615 by Lipeng Zhu, perf(function): Allow `LIKE` substrings fast path when escape is inert (#17789) 219359c19 by dependabot[bot], build(deps): Bump launch-editor from 2.13.2 to 2.14.1 in /website (#17847) 4e21d8480 by dependabot[bot], build(deps): Bump form-data from 4.0.5 to 4.0.6 in /website (#17845) e67357e4b by dependabot[bot], build(deps): Bump ws from 7.5.10 to 7.5.11 in /website (#17846) f959d5e88 by Ke Wang, feat: Gate `cacheMetadata` and `cacheIndex` on split `cacheable` (#17869) 5a07a844b by Wei He, fix(build): Fix build failure of TraceHistoryTest (#17867) 6adba8702 by Wei He, fix(build): Fix race conditions in AsyncSourceTest concurrent tests causing flaky SIGABRT (#17868) 7c14743e9 by Orri Erling, Fix CompositeKernel::warmup() compile hang in heavyweight hosts (#17863) f6bf8ec4d by Orri Erling, feat: Fast path for views, more fused ops (#17862) c407e4fe6 by Xiaoxuan Meng, fix: Stabilize adaptive prefetch timing tests (#17865) 86fdca603 by Shaojie Li, docs: Add blog post on Parquet DELTA decoding with SIMD (#17857) fbcddd6e0 by Huameng (Michael) Jiang, feat(selective): Enable dictionary path for filtered string reads (#17810) 4ac26e2be by Ping Liu, refactor(iceberg): Reuse IcebergTestBase across tests and split positional-delete tests (#17764) f0d94f82c by Apurva Kumar, feat: Iceberg V3 field-id support for DWRF (proto, writer, reader, connector) [velox][dwrf] (#17843) e48e3cd6c by Prashant Golash, fix(geo): Gate GooglePolyline on VELOX_ENABLE_GEO (#17850) 8fe696e9c by Karthikeyan Natarajan, fix(test): Build the libraries DynamicLinkTest dlopens (#17848) fd0e7d5ae by Christian Zentgraf, refactor(ABFS): Allow registration of default providers (#17114) 029541115 by dependabot[bot], build(deps): Bump shell-quote from 1.8.3 to 1.8.4 in /website (#17781) 2e1026b98 by Avinash, fix(cudf): Order hash join probes after async build (#17758) 2ee2f0f96 by Kyle Hubert, fix(cudf): Support count(*) through batch concat (#17749) 831f308af by Ping Liu, docs: Add missing hive config (#17838) 232ab605b by Pratik Pugalia, build(ci): Include CONTRIBUTOR in force-full approval allowlist (#17825) 6b5247478 by Christian Zentgraf, fix(build): Additional Apple toolchain fixes (#17802) 94c605332 by dependabot[bot], build(ci): Bump actions/cache from 4.3.0 to 5.0.5 (#17835) 7bf146596 by Jimmy Lu, feat: Run the ads-preproc (CMF 830857007) graph on GPU (#17819) 819b14690 by Prashant Golash, perf: Preload small Nimble files to reduce WarmStorage round trips (#17821) e34f436ee by Masha Basmanova, feat: Add TpchQueryBuilder::getAltPlan (#17829) 0d3d37be7 by Guilherme Kunigami, feat: Support json type when parsing Hive types (#17573) 919943145 by Masha Basmanova, docs: Rework commit-message Test Plan guidance (#17824) 1ac8d90e4 by Masha Basmanova, feat(expr): Support the varargs IN form in subfield filter conversion (#17823) 1cfd2dbc8 by Masha Basmanova, fix(test): Handle typed NULL in IN lists in DuckParser (#17822) 71af07fb4 by Pratik Pugalia, fix(sparksql): Make make_timestamp ANSI-aware (#17745) 34b50951a by Zoltan Arnold Nagy, build(cudf): Bring in ucxx when ucx is present and update all RAPIDS dependencies to latest (#17572) 16d2e3bcd by Xiaoxuan Meng, fix: Link ORC reader into Hive connector tests (#17817) 235cf20b7 by Orri Erling, feat: Scalar support and numeric parity for IG roo pipeline (#17809) 3d6cbc2a9 by generatedunixname89002005307016, Enable Pyrefly in fbcode/velox (#17808) 5d63faec2 by Ping Liu, refactor: Format-specific DWIO reader options (#17663) a83a6caeb by malinjawi, refactor(spark): Extract XxHash64 helper (#17681) 1e4c3a0ea by Ping Liu, refactor: Replace anonymous {ParquetReader, RowReader} pair with named ParquetReaderBundle (#17746) 913684d2f by Pratik Pugalia, build: Add selective-build CI gating for unapproved PRs (#17260) (#17260) 3a9cb8f91 by Mariam-Almesfer, feat(spark): Add support for minute/second(timestamp_utc) (#17759) abfc6b2d3 by Pratik Pugalia, fix(cmake): Fix gersemi formatting in common/io CMakeLists (#17796) Signed-off-by: glutenperfbot --- ep/build-velox/src/get-velox.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ep/build-velox/src/get-velox.sh b/ep/build-velox/src/get-velox.sh index 637860db37d..32e86cbeedb 100755 --- a/ep/build-velox/src/get-velox.sh +++ b/ep/build-velox/src/get-velox.sh @@ -18,8 +18,8 @@ set -exu CURRENT_DIR=$(cd "$(dirname "$BASH_SOURCE")"; pwd) VELOX_REPO=https://github.com/IBM/velox.git -VELOX_BRANCH=dft-2026_06_12 -VELOX_ENHANCED_BRANCH=ibm-2026_06_12 +VELOX_BRANCH=dft-2026_06_26 +VELOX_ENHANCED_BRANCH=ibm-2026_06_26 VELOX_HOME="" RUN_SETUP_SCRIPT=ON ENABLE_ENHANCED_FEATURES=OFF