Thanks for your patience. Conbench analyzed the 6 benchmarking runs that have been run so far on PR commit c7c3059.

Benchmarks with performance regressions

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

All benchmark runs analyzed:

• Pull Request Run on ursa-i9-9960x at 2023-08-08 11:45:20Z
• Pull Request Run on ec2-t3-xlarge-us-east-2 at 2023-08-08 08:55:16Z
• Pull Request Run on ec2-m5-4xlarge-us-east-2 at 2023-08-08 08:57:35Z
• Pull Request Run on arm64-m6g-linux-compute at 2023-08-08 09:49:57Z
• Pull Request Run on arm64-t4g-linux-compute at 2023-08-08 10:37:19Z
• Pull Request Run on ursa-thinkcentre-m75q at 2023-08-08 10:42:41Z

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.

• Pull Request Run on ursa-thinkcentre-m75q at 2023-08-08 10:42:41Z
  • MoveEmptyVector (C++) with params=<STATIC_VECTOR(std::string)>, source=cpp-micro, suite=arrow-small-vector-benchmark
  • UniqueInt64 (C++) with params=6, source=cpp-micro, suite=arrow-compute-vector-hash-benchmark