msokolov commented on PR #14874: URL: https://github.com/apache/lucene/pull/14874#issuecomment-3079963146
> Looks like the JVM is producing optimized branches of code based on the underlying input type(s) of int dotProduct(MemorySegment, MemorySegment) -- and the non-optimized branches suffer a latency regression.. Yes this gibes with my understanding. It made me wonder if we could introduce a different signature for the two cases. But it seems crazy, if the Java code is identical for them, that the underlying machine code would be so completely different. And wouldn't it be nice if HotSpot could understand that context may change and generate multiple versions for multiple contexts. -- 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
