GlutenPerfBot opened a new pull request, #11349: URL: https://github.com/apache/incubator-gluten/pull/11349
Upstream Velox's New Commits: ``` 2fdcd253e by Xiaoxuan Meng, misc: Added index bound type unit test (15879) 74af4ef1b by Xiao Du, feat: Add string compaction for approx_most_frequent global aggregation (15852) 48e853131 by Pedro Eugenio Rocha Pedreira, refactor(simple-function): Make materialization of string-types explicit (15869) 80638a89e by Artem Selishchev, fix: [velox] Reuse context in ZSTD_decompress (15854) b959f0d89 by Ge Gao, fix: Disable SSD cache write when SSD is full (15860) a5bd8cd5a by Xiaoxuan Meng, refactor: Change key encoder namespace from exec to serializer (15868) 4da242827 by Xiaoxuan Meng, refactor: Move KeyEncoder from velox/exec to velox/serializers (15867) 64b217c63 by Xiaoxuan Meng, refactor: trival ApproxMostFrequentAggregate related code cleanup (15866) 9377c95c0 by duanmeng, docs: Add sort analyze blog (15856) d9a87e74f by Xiaoxuan Meng, feat: Support normalized key encoder in Velox for sort optimizations (15864) 6c5e02008 by Shrinidhi Joshi, Make Exchange client eager fetching behavior configurable (15768) 37583860d by Pedro Eugenio Rocha Pedreira, perf(function): Avoid unnecessary string copies (15863) ba59291b1 by Shrinidhi Joshi, feat: Enable caching and re-use of HashTable in HashBuild operator (15754) 5a46bce60 by Shrinidhi Joshi, feat: Add release callbacks to QueryCtx (15858) f7f995849 by Zac Wen, feat: Add maxEntries limit to SSD cache (14879) acee28e00 by Pedro Eugenio Rocha Pedreira, refactor: Make std::string conversions explicit (15861) ec451a1d4 by Pedro Eugenio Rocha Pedreira, refactor(query-ctx): Add builder pattern and documentation 7c409cc9c by Chang chen, feat: Enhance floating point value retrieval with type-specific handling in parquet reader (15657) e98e45e52 by beliefer, refactor: Remove unnecessary sizeof(char) (15779) 4bd07a726 by Pedro Eugenio Rocha Pedreira, fix(variant): Variant string conversion logic on creation (15855) 3d614a161 by Pedro Eugenio Rocha Pedreira, refactor: Move TableWriteTraits to velox/core (15835) d3132b27f by Pedro Eugenio Rocha Pedreira, perf(function): Avoid string copy in normalize() Presto function (15850) 17e600352 by Wei He, misc: Rename QueryConfig::kParallelJoinBuildRowsEnabled to kParallelOutputJoinBuildRowsEnabled to avoid confusion (15851) fd021d025 by Pedro Eugenio Rocha Pedreira, refactor: Add is_string_kind/is_nested_kind() metaprogramming helpers (15849) 97fdb67a2 by NEUpanning, perf: Avoid redundant sorting of map entries in ValueList and ValueSet (15717) 45093a706 by Chengcheng Jin, fix: Expand operator with constants specified using ConstantVector (15684) 39378d7c9 by Xiaoxuan Meng, fix: Fix TopNRowNumber crash by handling add new groups failure properly (15845) 659b52aba by Shakyan Kushwaha, feat: Add now() and current_timestamp function (14139) fcb794960 by Rui Mo, fix: Access null value in makeInFilter (14082) 7855828e9 by Rong Ma, perf: Optimize extractFiltersFromRemainingFilter for a mix of OR and NOT (15732) ba0f4f228 by Wei He, perf: Parallelize output of build-side rows for right and full joins (15808) 325111557 by Masha Basmanova, feat: Add support for resolving aggregate functions with coercions (15846) cd4596875 by Pedro Eugenio Rocha Pedreira, refactor(variant): Improve code organization and more tests (15842) 161401dec by Heidi Han, fix: Use aggregate initialization to fix cmake error (15841) b54cda6a2 by Andrii Rosa, feat: Limit maximum number of distinct values when merging VectorHasher's (15840) 6b549bb00 by Andrii Rosa, feat: Measure cpu time taken by VectorHasher merge in HashBuild (15807) bc00dac1e by Xiao Du, fix: Fix incorrect comments (15839) 25a88106a by Ping Liu, fix: Incorrect min max stats when the column value are infinity or -infinity (14603) 109a59bc8 by zml1206, fix: Support legacy date formatter for Spark date_format function (15535) 3ab1039be by beliefer, refactor: Replace VELOX_ARRAY_SIZE with std::size (15730) b325a22ad by Yedidya Feldblum, misc: Fix ReaderTest.projectColumnsMutation (15830) d6b6de2d3 by Christian Zentgraf, fix(ci): Clang-tidy does not find compile-commands.json (15572) 832bcee13 by Masha Basmanova, fix: TypeCoercer::leastCommonSuperType(MAP, ROW) should be null (15838) bbe1d1d9f by Natasha Sehgal, feat: Update SfmSketch scalar functions to use query memory pool (15834) a886644e9 by Jimmy Lu, feat: Dynamic Bloom filter pushdown from hash probe (15752) f993598ad by Patrick Sullivan, fix: remove zero-area polygon checks (15833) b21fcbe67 by Pedro Eugenio Rocha Pedreira, perf(functions): Remove unecessary string copies in parse_presto_data_size() (15832) d43494402 by Pedro Eugenio Rocha Pedreira, perf(utf8): Remove unnecessary string allocations (15827) 208636a0f by Pratik Pugalia, feat: Add biased NULL pattern generation to VectorFuzzer (15798) 84b2f34ab by Masha Basmanova, feat: Add coercion for generic types (15823) 5664493e1 by Masha Basmanova, fix: Check type constraints when binding homogeneous row (15822) a5bcef4ea by Peter Enescu, build: Enable GEO by default (15815) 59178cd28 by Pramod Satya, docs: Fix CompareFlags documentation (15706) 4f7ea08b3 by Masha Basmanova, feat: Add coercion for complex types (15818) db0319005 by Masha Basmanova, feat: Add coercions for variable arity arguments (15816) e3e83289f by Pedro Eugenio Rocha Pedreira, refactor(text-reader): String usage cleanup (15812) 385cb03cd by Masha Basmanova, perf: Avoid double lookup in maps in SignatureBinder (15804) 77852de81 by Masha Basmanova, fix: Do not bind UNKNOWN type to another type (15802) c019fbd0b by Pratik Pugalia, fix: Nanos validation in Timestamp::tmToStringView (15786) e3bd98d38 by Masha Basmanova, feat: Add sanity checks for function signatures with variable arity argument (15800) 77eaed4e2 by Masha Basmanova, perf: Use boost::algorithm::iequals to compare type names (15801) 12e5c7b34 by Masha Basmanova, fix(cudf): Replace tryBindWithCoercions call with tryBind (15799) 097349754 by MJ Deng, feat(function): Support 10 key-value pairs in Spark map function (15794) 6ced2785a by Rui Mo, misc: Allow registration of custom buffered input (15781) 394104570 by Avinaash Gupta, misc: Revert usage of rowVectorToIOBufBatch (batch serialization) in Remote function udf (15796) 92779b3e0 by Xiao Du, misc: Add null checks for trace node lookups (15795) 40285f427 by Carl Shapiro, misc: Respect Linux cgroups restrictions when sizing thread pools (15719) dbfe5e4a1 by Zhen Li, fix: Prevent integer overflow in PrefixSort memory estimation (15789) 1a6cbf69a by Abhinav Mukherjee, Fix map_except to handle null elements in complex keys gracefully (15775) eec00ebc0 by Muhammad Haseeb, feat(cudf): Integrate the new cudf parquet reader (15482) cb994015d by Matt Gara, fix: CMake CMP0002 issue due to velox_aggregates defined in add_library twice (15787) ef67c2437 by Bikramjeet Vig, Fix string buffer ownership transfer in side table reader (15792) bd0c7741a by Ping Liu, feat(parquet): Support write field_id to metadata SchemaElement (14741) 14a692166 by James Gill, fix(geo): Fix correctness issue with spatial joins on GeometryCollections (15778) ``` velox_branch: https://github.com/IBM/velox/commits/dft-2026_01_02 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
