iprithv commented on PR #16065: URL: https://github.com/apache/lucene/pull/16065#issuecomment-4454883323
Updated to use Faiss's fvec_renorm_L2 for normalization instead of doing it in Java. Had a discussion with @msfroh, thanks for looking at this and pointing this out. The C version normalizes the entire batch in-place with OpenMP, so we avoid the per-vector float[] clone() and the scalar Java loop. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
