lidavidm commented on pull request #10813: URL: https://github.com/apache/arrow/pull/10813#issuecomment-887576231
Ah indeed. Testing it with std::fmax in both kernels, the hash aggregate kernel is slower in all cases: ``` ---------------------------------------------------------------------------------------------------- Benchmark Time CPU Iterations UserCounters... ---------------------------------------------------------------------------------------------------- MinMaxKernelDouble/1048576/10000 495 us 495 us 2897 bytes_per_second=1.97278G/s null_percent=0.01 size=1048.58k MinMaxKernelDoubleAggregate/1048576/10000 645 us 645 us 2160 bytes_per_second=1.5149G/s null_percent=0.01 size=1048.58k MinMaxKernelInt64/1048576/10000 80.1 us 80.1 us 16304 bytes_per_second=12.1949G/s null_percent=0.01 size=1048.58k MinMaxKernelInt64Aggregate/1048576/10000 718 us 718 us 1897 bytes_per_second=1.35927G/s null_percent=0.01 size=1048.58k ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
