uschindler commented on PR #13076: URL: https://github.com/apache/lucene/pull/13076#issuecomment-1929503472
> My question is why add this function when it's not that much faster than integer dot product? I see less than 20 percent improvement, which won't even translate to 20 percent indexing/search. I think the idea is to have shorter vectors and so it is faster. With hamilton you see multiple dimensions per byte (a byte component is a vector of 8 dimensions). So when you want 512 dimensions, you need a byte vector dimension of 64 to encode that. -- 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
