easyice commented on PR #12841:
URL: https://github.com/apache/lucene/pull/12841#issuecomment-1847102122

   It looks good on `byteBuffers` and `MMapDirectory`, the benchmark result is 
pretty close to previous commit,
   but a bit slowdon on `NIOFSDirectory`, i will dig it.
   
   * `*ReadGroupVInt` the current commit
   * `*_viaDupCode` the previous commit, using duplicated code.
   * `*Baseline` no change.
   
   java17
   ```
   Benchmark                                                   (size)   Mode  
Cnt  Score   Error   Units
   GroupVIntBenchmark.byteBuffersReadGroupVInt                     64  thrpt    
5  5.156 ± 0.378  ops/us
   GroupVIntBenchmark.byteBuffersReadGroupVIntBaseline             64  thrpt    
5  2.130 ± 0.039  ops/us
   GroupVIntBenchmark.byteBuffersReadGroupVInt_viaDupCode          64  thrpt    
5  5.455 ± 0.164  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVInt                 64  thrpt    
5  7.632 ± 0.377  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVIntBaseline         64  thrpt    
5  7.376 ± 0.485  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVInt_viaDupCode      64  thrpt    
5  7.408 ± 0.532  ops/us
   GroupVIntBenchmark.nioReadGroupVInt                             64  thrpt    
5  6.905 ± 0.589  ops/us
   GroupVIntBenchmark.nioReadGroupVIntBaseline                     64  thrpt    
5  5.574 ± 0.216  ops/us
   GroupVIntBenchmark.nioReadGroupVInt_viaDupCode                  64  thrpt    
5  9.014 ± 0.162  ops/us
   ```
   
   java21
   ```
   Benchmark                                                   (size)   Mode  
Cnt   Score   Error   Units
   GroupVIntBenchmark.byteBuffersReadGroupVInt                     64  thrpt    
5   5.539 ± 0.220  ops/us
   GroupVIntBenchmark.byteBuffersReadGroupVIntBaseline             64  thrpt    
5   1.825 ± 0.055  ops/us
   GroupVIntBenchmark.byteBuffersReadGroupVInt_viaDupCode          64  thrpt    
5   5.543 ± 0.097  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVInt                 64  thrpt    
5   9.428 ± 0.189  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVIntBaseline         64  thrpt    
5   5.565 ± 0.080  ops/us
   GroupVIntBenchmark.mmap_byteBufferReadGroupVInt_viaDupCode      64  thrpt    
5  10.476 ± 1.343  ops/us
   GroupVIntBenchmark.nioReadGroupVInt                             64  thrpt    
5   8.434 ± 1.887  ops/us
   GroupVIntBenchmark.nioReadGroupVIntBaseline                     64  thrpt    
5   5.431 ± 0.072  ops/us
   GroupVIntBenchmark.nioReadGroupVInt_viaDupCode                  64  thrpt    
5  10.723 ± 0.399  ops/us
   ```


-- 
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