GH-47012: [C++][Parquet] Reserve values correctly when reading BYTE_A…
conbench-apache-arrow / Conbench performance report
succeeded
Jul 9, 2025 in 0s
Found 0 regressions
After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit d2a1718.
Benchmarks with performance regressions
There were 0 possible performance regressions, according to the lookback z-score method.
All benchmark runs analyzed:
- Commit Run on
amd64-c6a-4xlarge-linuxat 2025-07-09 09:08:15Z - Commit Run on
amd64-m5-4xlarge-linuxat 2025-07-09 09:23:45Z - Commit Run on
test-mac-armat 2025-07-09 09:35:21Z - Commit Run on
arm64-t4g-2xlarge-linuxat 2025-07-09 09:23:55Z
Unstable benchmarks with performance regressions
The following benchmark results indicate a possible performance regression, but are known to sometimes produce false positives when applying the lookback z-score analysis.
-
Commit Run on
amd64-c6a-4xlarge-linuxat 2025-07-09 09:08:15ZBM_PlainEncodingSpacedBoolean(C++) with params=32768/100, source=cpp-micro, suite=parquet-encoding-benchmarkBM_BatchComputeHash(C++) with params=, source=cpp-micro, suite=parquet-bloom-filter-benchmarkBuildIntArrayNoNulls(C++) with source=cpp-micro, suite=arrow-builder-benchmarkArrayArrayKernel(C++) with params=<MultiplyChecked, Int64Type>/size:524288/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmarkBufferOutputStreamTinyWrites(C++) with params=real_time, source=cpp-micro, suite=arrow-io-memory-benchmarkBM_PlainEncodingSpacedBoolean(C++) with params=32768/1, source=cpp-micro, suite=parquet-encoding-benchmarkBM_RleDecoding(C++) with params=65536/16, source=cpp-micro, suite=parquet-column-io-benchmarkBM_PlainEncodingSpacedBoolean(C++) with params=32768/10000, source=cpp-micro, suite=parquet-encoding-benchmarkBM_ByteStreamSplitEncode_Int16_Scalar(C++) with params=1024, source=cpp-micro, suite=parquet-encoding-benchmarkBM_PlainEncodingSpacedDouble(C++) with params=32768/10000, source=cpp-micro, suite=parquet-encoding-benchmarkBM_PlainEncodingSpacedFloat(C++) with params=32768/10000, source=cpp-micro, suite=parquet-encoding-benchmarkBM_RleEncodingSpacedBoolean(C++) with params=32768/10000, source=cpp-micro, suite=parquet-encoding-benchmarkBM_ComputeHash(C++) with params=, source=cpp-micro, suite=parquet-bloom-filter-benchmarkBM_ByteStreamSplitDecode_Int16_Scalar(C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmarkBenchmarkTemporalRounding(C++) with params=<CeilTemporal, non_zoned, round_1_minute>/524288/100, source=cpp-micro, suite=arrow-compute-scalar-temporal-benchmarkBatchToTensorSimple(C++) with params=/size:32768/num_columns:3, source=cpp-micro, suite=arrow-tensor-benchmarkBM_ByteStreamSplitEncode_Int16_Scalar(C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmarkArrayArrayKernel(C++) with params=<AddChecked, UInt8Type>/size:524288/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmarkBenchmarkTemporalRounding(C++) with params=<FloorTemporal, non_zoned, round_1_minute>/524288/0, source=cpp-micro, suite=arrow-compute-scalar-temporal-benchmarkBM_BatchComputeHash(C++) with params=, source=cpp-micro, suite=parquet-bloom-filter-benchmark
-
Commit Run on
amd64-m5-4xlarge-linuxat 2025-07-09 09:23:45ZBM_DecodeArrowBooleanPlain(C++) with params=DecodeArrowWithNull/num_values:65536/null_in_ten_thousand:1000, source=cpp-micro, suite=parquet-encoding-benchmarkAllocateTouchDeallocate(C++) with params=/size:1048576/real_time/threads:8, source=cpp-micro, suite=arrow-memory-pool-benchmarkBM_DecodeArrowBooleanPlain(C++) with params=DecodeArrowWithNull/num_values:1024/null_in_ten_thousand:100, source=cpp-micro, suite=parquet-encoding-benchmarkBM_DecodeArrowBooleanPlain(C++) with params=DecodeArrowWithNull/num_values:1024/null_in_ten_thousand:1000, source=cpp-micro, suite=parquet-encoding-benchmarkExecuteScalarExpressionOverhead(C++) with params=ref_only_expression/rows_per_batch:1000000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmarkCopyShortVector(C++) with params=<STATIC_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmark
-
Commit Run on
test-mac-armat 2025-07-09 09:35:21ZValidateLargeAlmostAscii(C++) with source=cpp-micro, suite=arrow-utf8-util-benchmarkThreadPoolSpawn(C++) with params=threads:2/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkValidateTinyAscii(C++) with source=cpp-micro, suite=arrow-utf8-util-benchmarkBM_RowArray_DecodeOneOfColumns(C++) with params="fixed_length_row:{boolean,int32,fixed_size_binary(64)}"/column:0, source=cpp-micro, suite=arrow-acero-hash-join-benchmarkReferenceWorkloadCost(C++) with params=task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkBM_ByteStreamSplitDecode_Int16_Scalar(C++) with params=1024, source=cpp-micro, suite=parquet-encoding-benchmarkIntegerParsing(C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmarkIntegerParsing(C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmarkInt8ColumnMajorMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkValidateSmallAscii(C++) with source=cpp-micro, suite=arrow-utf8-util-benchmarkFloatStridedMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkBM_RleDecoding(C++) with params=32768/1, source=cpp-micro, suite=parquet-column-io-benchmarkBM_DeltaBitPackingEncode_Int64_Fixed(C++) with params=32768, source=cpp-micro, suite=parquet-encoding-benchmarkDoubleStridedMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkFloatStridedMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkBM_ByteStreamSplitEncode_FLBA_Generic(C++) with params=<16>/65536, source=cpp-micro, suite=parquet-encoding-benchmarkThreadedTaskGroup(C++) with params=threads:4/task_cost:10000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkResolveManyUInt16Sorted(C++) with params=chunked_array_length:65535/num_chunks:100/num_indices:508, source=cpp-micro, suite=arrow-chunk-resolver-benchmarkBM_ByteStreamSplitDecode_FLBA_Generic(C++) with params=<7>/65536, source=cpp-micro, suite=parquet-encoding-benchmarkBM_RowArray_Decode(C++) with params="boolean", source=cpp-micro, suite=arrow-acero-hash-join-benchmarkGreaterArrayArrayString(C++) with params=65536/1, source=cpp-micro, suite=arrow-compute-scalar-compare-benchmarkReferenceStreamingDecompression(C++) with params=Compression::GZIP, source=cpp-micro, suite=arrow-compression-benchmarkBM_RowArray_DecodeOneOfColumns(C++) with params="var_length_row:{boolean,int32,utf8,utf8}"/column:0, source=cpp-micro, suite=arrow-acero-hash-join-benchmarkThreadedTaskGroup(C++) with params=threads:1/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkFloatRowMajorMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkDoubleRowMajorMatrixConversionFixture(C++) with params=/ConvertToSparseCSCMatrixInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkThreadedTaskGroup(C++) with params=threads:2/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkBM_ByteStreamSplitDecode_FLBA_Generic(C++) with params=<16>/1024, source=cpp-micro, suite=parquet-encoding-benchmarkHexParsing(C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmarkThreadPoolSpawn(C++) with params=threads:1/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkThreadPoolSpawn(C++) with params=threads:4/task_cost:10000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkBM_DeltaBitPackingEncode_Int64_Fixed(C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmarkBM_DeltaBitPackingEncode_Int32_Narrow(C++) with params=32768, source=cpp-micro, suite=parquet-encoding-benchmarkDoubleRowMajorMatrixConversionFixture(C++) with params=/ConvertToSparseCSRMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkBM_ByteStreamSplitDecode_Int16_Scalar(C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmarkBM_ByteStreamSplitEncode_FLBA_Generic(C++) with params=<7>/1024, source=cpp-micro, suite=parquet-encoding-benchmarkHexParsing(C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmarkSerialTaskGroup(C++) with params=task_cost:10000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkThreadPoolSpawn(C++) with params=threads:4/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkSerialTaskGroup(C++) with params=task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkHexParsing(C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmarkBM_HashJoinBasic_ProbeParallelism(C++) with params=Threads:4/HashTable krows:512/process_time, source=cpp-micro, suite=arrow-acero-hash-join-benchmarkDoubleStridedMatrixConversionFixture(C++) with params=/ConvertToSparseCSRMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkMaxElementWiseArrayArrayInt64(C++) with params=65536/1, source=cpp-micro, suite=arrow-compute-scalar-compare-benchmarkDoubleColumnMajorMatrixConversionFixture(C++) with params=/ConvertToSparseCSRMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmarkBM_ByteStreamSplitEncode_FLBA_Generic(C++) with params=<7>/65536, source=cpp-micro, suite=parquet-encoding-benchmarkBM_ByteStreamSplitEncode_FLBA_Generic(C++) with params=<16>/1024, source=cpp-micro, suite=parquet-encoding-benchmarkThreadedTaskGroup(C++) with params=threads:4/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmark
-
Commit Run on
arm64-t4g-2xlarge-linuxat 2025-07-09 09:23:55ZGrouperWithMultiTypes(C++) with params="{int64, int32}"/4096/10000, source=cpp-micro, suite=arrow-compute-grouper-benchmarkArrayScalarKernel(C++) with params=<Divide, DoubleType>/size:1048576/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmarkGrouperWithMultiTypes(C++) with params="{utf8}"/4096/0, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{int32}"/1024/10000, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{int32}"/1024/10, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{boolean, utf8}"/4096/1, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{int64}"/4096/10000, source=cpp-micro, suite=arrow-compute-grouper-benchmarkUniqueString10bytes(C++) with params=3, source=cpp-micro, suite=arrow-compute-vector-hash-benchmarkUniqueString10bytes(C++) with params=2, source=cpp-micro, suite=arrow-compute-vector-hash-benchmarkGrouperWithMultiTypes(C++) with params="{int32, int64, boolean, utf8}"/4096/100, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{int32, boolean, utf8}"/4096/100, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{int32}"/1024/2, source=cpp-micro, suite=arrow-compute-grouper-benchmarkUniqueUInt8(C++) with params=3, source=cpp-micro, suite=arrow-compute-vector-hash-benchmarkGrouperWithMultiTypes(C++) with params="{int64}"/1024/100, source=cpp-micro, suite=arrow-compute-grouper-benchmarkGrouperWithMultiTypes(C++) with params="{utf8, int32, int64, fixed_size_binary(32), boolean}"/1024/100, source=cpp-micro, suite=arrow-compute-grouper-benchmarkArrayScalarKernel(C++) with params=<Divide, FloatType>/size:1048576/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmarkArrayScalarKernel(C++) with params=<Divide, DoubleType>/size:1048576/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
Details
This report was generated using the lookback z-score method with a z-score threshold of 30.0.
Loading