After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit f45594d.

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 2025-05-20 01:07:51Z
• Commit Run on amd64-m5-4xlarge-linux at 2025-05-20 04:38:49Z
• Commit Run on arm64-t4g-2xlarge-linux at 2025-05-20 01:17:28Z
• Commit Run on test-mac-arm at 2025-05-20 01:11:20Z

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 2025-05-20 01:07:51Z
  • UniqueInt64 (C++) with params=6, source=cpp-micro, suite=arrow-compute-vector-hash-benchmark
  • BenchmarkTemporalRounding (C++) with params=<RoundTemporal, non_zoned, round_10_week>/524288/0, source=cpp-micro, suite=arrow-compute-scalar-temporal-benchmark
  • BenchmarkTemporal (C++) with params=<Month, non_zoned>/524288/100, source=cpp-micro, suite=arrow-compute-scalar-temporal-benchmark
  • ResolveManyUInt64Sorted (C++) with params=chunked_array_length:65535/num_chunks:10000/num_indices:508, source=cpp-micro, suite=arrow-chunk-resolver-benchmark
  • ExecuteScalarExpressionOverhead (C++) with params=simple_expression/rows_per_batch:1000000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmark
  • UniqueInt64 (C++) with params=13, source=cpp-micro, suite=arrow-compute-vector-hash-benchmark
  • ArrayArrayKernel (C++) with params=<Add, Int8Type>/size:524288/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
  • CastInt64ToDoubleUnsafe (C++) with params=524288/1000, source=cpp-micro, suite=arrow-compute-scalar-cast-benchmark
  • ExecuteScalarExpressionOverhead (C++) with params=simple_expression/rows_per_batch:10000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmark
  • ArrayScalarKernel (C++) with params=<Subtract, Int8Type>/size:524288/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
  • ArrayArrayKernel (C++) with params=<Add, Int8Type>/size:524288/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
  • ArrayScalarKernel (C++) with params=<Subtract, Int8Type>/size:524288/inverse_null_proportion:100, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
  • ExecuteScalarExpressionOverhead (C++) with params=simple_expression/rows_per_batch:100000/real_time/threads:1, source=cpp-micro, suite=arrow-acero-expression-benchmark
  • BenchmarkTemporalBinary (C++) with params=<MonthDayNanoBetween, non_zoned>/524288/0, source=cpp-micro, suite=arrow-compute-scalar-temporal-benchmark
  • RoundArrayBenchmark (C++) with params=<Round, UInt32Type, RoundMode::DOWN>/size:524288/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-round-benchmark