rmuir commented on PR #12311: URL: https://github.com/apache/lucene/pull/12311#issuecomment-1561030863
at the end of the day, there's definitely a bigger design issue, unrelated to vector length, in that there are landmines everywhere with regards to the various functions. If you use the wrong one on the wrong cpu, performance can get like 50x slower (terrible trap). It would be better to just use your own scalar function. We try to only use simple operations here to avoid problems, but the general issue remains. And there's no way for you to cleanly check "is this supported" (e.g. like checking CPUID or similar). So I don't understand how libraries are supposed to use this thing :) -- 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
