rmuir commented on PR #12632: URL: https://github.com/apache/lucene/pull/12632#issuecomment-1753003897
> Oh! I didn't look back as far as the original commit on this PR, sorry. I see now that @rmuir tried exactly the same thing. > > @gf2121 Strange that we see different results. Could you please try with JDK 21 ? Yes and I looked at the assembler, it looked good, maybe the difference is CPU? So I am concerned about CPU differences and causing slowdowns for some AVX-512 machines, and I just reverted the change. I see similar performance boost as you on skylake (no AVX-512) by "going directly to int". This is the explanation where I got the idea: https://stackoverflow.com/a/69848057 -- 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: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
