lidavidm commented on pull request #10412: URL: https://github.com/apache/arrow/pull/10412#issuecomment-876453122
Performance here looks highly variable - the benchmark seems to be one of the bimodal ones; we either run at ~1.3 G/s or ~1.7 G/s when repeatedly running the benchmark. As written, this makes use of rather generic code like CopyBitmap, which hurts us quite a bit in terms of performance. Specializing the cases for array and scalar replacements and using direct methods like SetBitTo looks to help performance quite a bit, so I'll give that a swing. -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
