mbutrovich commented on PR #7358: URL: https://github.com/apache/arrow-rs/pull/7358#issuecomment-2770715329
> Thanks @psvri - I think we should run some benchmarks to ensure we aren't introducing some performance regressions by accident I dumped the disassembly of `MutableBuffer::shrink_to_fit` which uses `round_upto_multiple_of_64` from a release build for main and this PR: [pr.txt](https://github.com/user-attachments/files/19557873/pr.txt) [main.txt](https://github.com/user-attachments/files/19557874/main.txt) [Here's an online diff.](https://www.diffchecker.com/TbQj0WrK/) The generated instructions are slightly different, but general instruction count and most importantly branches look about the same. I would be stunned if there was any difference in release mode. I'll take a look at `ceil` next. -- 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]
