After merging your PR, Conbench analyzed the 5 benchmarking runs that have been run so far on merge-commit e1de9c5.

Benchmarks with performance regressions

There were 0 possible performance regressions, according to the lookback z-score method.

All benchmark runs analyzed:

• Commit Run on arm64-m6g-linux-compute at 2024-05-15 20:42:33Z
• Commit Run on ec2-t3-xlarge-us-east-2 at 2024-05-16 01:08:07Z
• Commit Run on test-mac-arm at 2024-05-15 22:31:22Z
• Commit Run on ec2-m5-4xlarge-us-east-2 at 2024-05-15 20:08:50Z
• Commit Run on arm64-t4g-linux-compute at 2024-05-15 21:49:10Z

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 test-mac-arm at 2024-05-15 22:31:22Z
  • ExecuteScalarExpressionOverhead (C++) with params=complex_integer_expression/rows_per_batch:100000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmark
  • DoubleColumnMajorTensorConversionFixture (C++) with params=/ConvertToSparseCOOTensorInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • BinaryBitBlockCounterSumWithOffset (C++) with params=64, source=cpp-micro, suite=arrow-bit-block-counter-benchmark
  • VisitBits (C++) with params=8192, source=cpp-micro, suite=arrow-bit-util-benchmark
  • DoubleRowMajorTensorConversionFixture (C++) with params=/ConvertToSparseCOOTensorInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • BinaryBitBlockCounterSumWithOffset (C++) with params=32768, source=cpp-micro, suite=arrow-bit-block-counter-benchmark
  • ExecuteScalarExpressionOverhead (C++) with params=complex_expression/rows_per_batch:100000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmark
  • BinaryBitBlockCounterSumWithOffset (C++) with params=8, source=cpp-micro, suite=arrow-bit-block-counter-benchmark