jpountz commented on PR #14906:
URL: https://github.com/apache/lucene/pull/14906#issuecomment-3044560305

   The new impl is slightly slower on my ARM Mac, but it's still a similar 
order of magnitude and much faster than the baseline, and the code looks more 
idiomatic, so I think we're good to merge.
   
   ```
   Benchmark                                     (minScoreInclusive)  (size)   
Mode  Cnt      Score      Error   Units
   CompetitiveBenchmark.baseline                                   0     128  
thrpt    5  40218,516 ± 5935,656  ops/ms
   CompetitiveBenchmark.baseline                                 0.2     128  
thrpt    5   4247,052 ±  216,541  ops/ms
   CompetitiveBenchmark.baseline                                 0.4     128  
thrpt    5   2401,350 ±   32,013  ops/ms
   CompetitiveBenchmark.baseline                                 0.5     128  
thrpt    5   2117,681 ±   14,486  ops/ms
   CompetitiveBenchmark.baseline                                 0.8     128  
thrpt    5   4630,407 ±  235,055  ops/ms
   CompetitiveBenchmark.branchlessCandidate                        0     128  
thrpt    5  39799,572 ± 8695,960  ops/ms
   CompetitiveBenchmark.branchlessCandidate                      0.2     128  
thrpt    5  11255,718 ±  579,988  ops/ms
   CompetitiveBenchmark.branchlessCandidate                      0.4     128  
thrpt    5  11181,453 ±  418,377  ops/ms
   CompetitiveBenchmark.branchlessCandidate                      0.5     128  
thrpt    5  11238,359 ±  367,859  ops/ms
   CompetitiveBenchmark.branchlessCandidate                      0.8     128  
thrpt    5  11120,788 ±  263,541  ops/ms
   CompetitiveBenchmark.branchlessCandidateCmov                    0     128  
thrpt    5  43470,171 ± 4588,605  ops/ms
   CompetitiveBenchmark.branchlessCandidateCmov                  0.2     128  
thrpt    5  10343,082 ±  324,145  ops/ms
   CompetitiveBenchmark.branchlessCandidateCmov                  0.4     128  
thrpt    5  10286,804 ±   77,779  ops/ms
   CompetitiveBenchmark.branchlessCandidateCmov                  0.5     128  
thrpt    5  10256,737 ±  123,636  ops/ms
   CompetitiveBenchmark.branchlessCandidateCmov                  0.8     128  
thrpt    5  10306,218 ±  169,973  ops/ms
   ```


-- 
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

Reply via email to