HUSTERGS commented on PR #14896: URL: https://github.com/apache/lucene/pull/14896#issuecomment-3091463045
> In general, the slowdowns are tiny, so I don't think we need to revert, this would likely still help when AVX512 is available? Sorry about that, I just found that the nightly benchmark runs on an AVX2 env. > Maybe we can do something about it? Either by detecting the case when the leading clause produces 0 scores since there's nothing to filter, or/and by looking optimizing vectorized filtering in this case? I'll try to look into this issue these days, maybe we should first change the default behavior to only enable the vectorized filter only when AVX512 is available ? > We need to make sure that it is avx512. Can we dete t this with Default Vectorsize 512? Yeah, VectorSize can certainly help with this -- 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
