After merging your PR, Conbench analyzed the 3 benchmarking runs that have been run so far on merge-commit 37eb3b5.

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-m5-4xlarge-linux at 2025-01-11 00:13:00Z
• Commit Run on test-mac-arm at 2025-01-10 04:54:39Z
• Commit Run on arm64-t4g-2xlarge-linux at 2025-01-11 06:16:52Z

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 2025-01-10 04:54:39Z
  • FloatStridedMatrixConversionFixture (C++) with params=/ConvertToSparseCSRMatrixInt32, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • DoubleColumnMajorMatrixConversionFixture (C++) with params=/ConvertToSparseCSCMatrixInt64, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • Int8ColumnMajorMatrixConversionFixture (C++) with params=/ConvertToSparseCSRMatrixInt8, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • Int8RowMajorMatrixConversionFixture (C++) with params=/ConvertToSparseCSRMatrixInt8, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • Int8RowMajorMatrixConversionFixture (C++) with params=/ConvertToSparseCSRMatrixInt16, source=cpp-micro, suite=arrow-tensor-conversion-benchmark
  • ArrayArrayKernel (C++) with params=<SubtractChecked, UInt16Type>/size:4194304/inverse_null_proportion:0, source=cpp-micro, suite=arrow-compute-scalar-arithmetic-benchmark
  • Int8StridedMatrixConversionFixture (C++) with params=/ConvertToSparseCSRMatrixInt8, source=cpp-micro, suite=arrow-tensor-conversion-benchmark