mayya-sharipova commented on PR #12794: URL: https://github.com/apache/lucene/pull/12794#issuecomment-1806267939
### Experiments - [luceneutil](https://github.com/mikemccand/luceneutil) tool - Apple M1 Max (Apple M1 Max, 10 CPU cores) - **baseline**: Lucene main branch - **candidate**: this PR ### 1M vectors of 100 dims | | Avg visited nodes | QPS | Recall| | :--- | ---: | ---: | ---: | | Baseline | 7642 | 80| 0.607| | Candidate | 3319 | 179| 0.507| ### 10M vectors of 100 dims | | Avg visited nodes | QPS | Recall| | :--- | ---: | ---: | ---: | | Baseline | 21573 | 27| 0.570| | Candidate | 7354 | 60| 0.413| Conclusion: the global queue can increase QPS by 2x at the expense of drop in recall. -- 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
