After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit da5a295.

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-linux at 2024-10-16 01:44:40Z
• Commit Run on arm64-t4g-2xlarge-linux at 2024-10-16 02:00:58Z
• Commit Run on amd64-m5-4xlarge-linux at 2024-10-16 01:56:41Z
• Commit Run on test-mac-arm at 2024-10-16 02:03:16Z

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 2024-10-16 01:44:40Z

  • MemoryBandwidth (C++) with params=/33554432/real_time/threads:1, source=cpp-micro, suite=arrow-io-memory-benchmark

• Commit Run on test-mac-arm at 2024-10-16 02:03:16Z

  • BM_DeltaBitPackingEncode_Int64_Narrow (C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmark
  • BM_DeltaBitPackingEncode_Int64_Narrow (C++) with params=4096, source=cpp-micro, suite=parquet-encoding-benchmark
  • BM_ExecSpanIterator (C++) with params=4096, source=cpp-micro, suite=arrow-compute-function-benchmark
  • BM_ExecSpanIterator (C++) with params=65536, source=cpp-micro, suite=arrow-compute-function-benchmark
  • BM_DeltaBitPackingEncode_Int64_Narrow (C++) with params=32768, source=cpp-micro, suite=parquet-encoding-benchmark
  • BM_DeltaBitPackingEncode_Int64_Narrow (C++) with params=1024, source=cpp-micro, suite=parquet-encoding-benchmark