cyb70289 commented on pull request #7542: URL: https://github.com/apache/arrow/pull/7542#issuecomment-649457378
> I see no significant performance difference here on an AMD Ryzen CPU. > The weird thing with these performance numbers is that the `null_percent=0` case should probably be faster, no? Per @wesm [comment ](https://github.com/apache/arrow/pull/7525#issuecomment-648279829), he also didn't see significant performance difference after replacing bitmapreader with bitblockcount. But I see big differences on AMD EYPC 7251, Intel Gold 5218, and Arm server. Both gcc and clang. No idea what's happening. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
