[PR] disable vectors (and don't warn to add incubator module) for jvmci/graal [lucene]

[via GitHub]

rmuir opened a new pull request, #12766:
URL: https://github.com/apache/lucene/pull/12766

   Another performance trap. I see use of this stuff a lot in the wild, lots of 
users/apps doing native image stuff, but we don't want to use vector api here, 
we should definitely not be encouraging the user to enable it either, as it 
makes things slow...
   
   ```
   java version "21.0.1" 2023-10-17
   Java(TM) SE Runtime Environment Oracle GraalVM 21.0.1+12.1 (build 
21.0.1+12-jvmci-23.1-b19)
   Java HotSpot(TM) 64-Bit Server VM Oracle GraalVM 21.0.1+12.1 (build 
21.0.1+12-jvmci-23.1-b19, mixed mode, sharing)
   ```
   
   Main:
   ```
   Benchmark                                   (size)   Mode  Cnt  Score   
Error   Units
   VectorUtilBenchmark.binaryCosineScalar        1024  thrpt   15  0.932 ± 
0.006  ops/us
   VectorUtilBenchmark.binaryCosineVector        1024  thrpt   15  0.411 ± 
0.011  ops/us
   VectorUtilBenchmark.binaryDotProductScalar    1024  thrpt   15  6.773 ± 
0.161  ops/us
   VectorUtilBenchmark.binaryDotProductVector    1024  thrpt   15  1.196 ± 
0.043  ops/us
   VectorUtilBenchmark.binarySquareScalar        1024  thrpt   15  6.318 ± 
0.040  ops/us
   VectorUtilBenchmark.binarySquareVector        1024  thrpt   15  1.172 ± 
0.016  ops/us
   VectorUtilBenchmark.floatCosineScalar         1024  thrpt   15  1.038 ± 
0.039  ops/us
   VectorUtilBenchmark.floatCosineVector         1024  thrpt   75  0.178 ± 
0.002  ops/us
   VectorUtilBenchmark.floatDotProductScalar     1024  thrpt   15  1.726 ± 
0.036  ops/us
   VectorUtilBenchmark.floatDotProductVector     1024  thrpt   75  0.512 ± 
0.011  ops/us
   VectorUtilBenchmark.floatSquareScalar         1024  thrpt   15  2.135 ± 
0.112  ops/us
   VectorUtilBenchmark.floatSquareVector         1024  thrpt   75  0.506 ± 
0.011  ops/us
   ```
   
   Patch:
   ```
   Benchmark                                   (size)   Mode  Cnt  Score   
Error   Units
   VectorUtilBenchmark.binaryCosineScalar        1024  thrpt   15  0.930 ± 
0.006  ops/us
   VectorUtilBenchmark.binaryCosineVector        1024  thrpt   15  0.930 ± 
0.005  ops/us
   VectorUtilBenchmark.binaryDotProductScalar    1024  thrpt   15  6.827 ± 
0.033  ops/us
   VectorUtilBenchmark.binaryDotProductVector    1024  thrpt   15  6.822 ± 
0.050  ops/us
   VectorUtilBenchmark.binarySquareScalar        1024  thrpt   15  6.286 ± 
0.096  ops/us
   VectorUtilBenchmark.binarySquareVector        1024  thrpt   15  6.305 ± 
0.029  ops/us
   VectorUtilBenchmark.floatCosineScalar         1024  thrpt   15  1.059 ± 
0.012  ops/us
   VectorUtilBenchmark.floatCosineVector         1024  thrpt   75  1.052 ± 
0.015  ops/us
   VectorUtilBenchmark.floatDotProductScalar     1024  thrpt   15  1.669 ± 
0.047  ops/us
   VectorUtilBenchmark.floatDotProductVector     1024  thrpt   75  1.661 ± 
0.049  ops/us
   VectorUtilBenchmark.floatSquareScalar         1024  thrpt   15  2.157 ± 
0.070  ops/us
   VectorUtilBenchmark.floatSquareVector         1024  thrpt   75  2.152 ± 
0.045  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