HippoBaro commented on PR #9848: URL: https://github.com/apache/arrow-rs/pull/9848#issuecomment-4512399848
Sorry @alamb, `arrow_reader_peak_memory` is also a benchmark target we should run on this one, since most of the gains are concentrated around lower RSS when decoding. For CPU benchmarks, the results are roughly as expected, except for `arrow_array_reader/BinaryViewArray/plain encoded, mandatory, no NULLs, short string`, which shows a worrying 20% regression. I’ll see if I can measure that locally as well. -- 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]
