jpountz commented on PR #13968: URL: https://github.com/apache/lucene/pull/13968#issuecomment-2454071806
Nightly benchmarks confirmed a speedup from the combination of #13958 (SIMD for advancing within a block) and this PR. ([CountAndHighHigh](https://benchmarks.mikemccandless.com/CountAndHighHigh.html), [CountAndHighMed](https://benchmarks.mikemccandless.com/CountAndHighMed.html)) Exhaustive evaluation of disjunctive queries looks stable or barely slower ([CountOrHighHigh](https://benchmarks.mikemccandless.com/CountOrHighHigh.html), [CountOrHighMed](https://benchmarks.mikemccandless.com/CountOrHighMed.html)) while we could have expected a slowdown from the loss of some optimizations in block decoding. -- 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
