After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit 52d258b.

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-t4g-2xlarge-linux at 2025-11-25 10:21:23Z
• Commit Run on amd64-c6a-4xlarge-linux at 2025-11-25 09:52:34Z
• Commit Run on amd64-m5-4xlarge-linux at 2025-11-25 12:30:29Z
• Commit Run on test-mac-arm at 2025-11-25 10:15:02Z

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-linux at 2025-11-25 09:52:34Z

  • ArrayArrayKernel (C++) with params=<Divide, UInt8Type>/size:524288/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark

• Commit Run on amd64-m5-4xlarge-linux at 2025-11-25 12:30:29Z

  • FloatColumnMajorTensorConversionFixture (C++) with params=/ConvertToSparseCOOTensorInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmark