[GitHub] [lucene] benwtrent commented on pull request #12529: Introduce a random vector scorer in HNSW builder/searcher

["benwtrent (via GitHub)" <gi...@apache.org>]

benwtrent commented on PR #12529:
URL: https://github.com/apache/lucene/pull/12529#issuecomment-1701731417

   Ran a benchmark on Lucene util and here are the results, candidate (this PR) is consistently slightly slower.
   
   ```
   recall	latency	nDoc	fanout	maxConn	beamWidth  visited	index ms
   lucene_baseline
   0.980	 0.65	50000	100	32	100	   110	        16397
   lucene_candidate
   0.980	 0.67	50000	100	32	100	   110	        16481
   lucene_baseline
   0.991	 0.93	50000	100	32	250	   110	        51686
   lucene_candidate
   0.991	 0.96	50000	100	32	250	   110	        51721
   lucene_baseline
   0.979	 0.69	50000	100	96	100	   110	        16675
   lucene_candidate
   0.979	 0.71	50000	100	96	100	   110	        16713
   lucene_baseline 
   0.992	 0.99	50000	100	96	250	   110	        54563
   lucene_candidate
   0.992	 1.04	50000	100	96	250	   110	        54599
   ```
   
   Almost for sure it has to do with creating more objects. Not sure how to prevent that with a nice api


-- 
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-unsubscribe@lucene.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org