[vectorIntrinsics] RFR: 8263149: Adding some algorithms optimized by Vector API into JMH benc…

Wang Zhuo wzhuo at openjdk.java.net
Mon Mar 8 03:11:27 UTC 2021


Here are some tests for Vector API JMH benchmarks.
These code came our work on optimizing Alibaba applications with Vector API.
VectorDistance contains Cosine distance and Euclidean Distance. The two distance algorithms are widely used in ElasticSearch, you can find opensource code here: github.com/opendistro-for-elasticsearch/k-NN/blob/aa5d1d40b136e2b3d33a14e80a2a374b2be015f9/src/main/java/com/amazon/opendistroforelasticsearch/knn/plugin/script/KNNScoringUtil.java#L61

BooleanArrayCheck and ValueRangeCheckAndCastL2I were developed during our optimization on OLAP systems.

Please help review this change.

Co-authored-by: Joshua Zhu <jzhu at openjdk.org>

-------------

Commit messages:
 - 8263149: Adding some algorithms optimized by Vector API into JMH benchmarks

Changes: https://git.openjdk.java.net/panama-vector/pull/44/files
 Webrev: https://webrevs.openjdk.java.net/?repo=panama-vector&pr=44&range=00
  Issue: https://bugs.openjdk.java.net/browse/JDK-8263149
  Stats: 736 lines in 3 files changed: 736 ins; 0 del; 0 mod
  Patch: https://git.openjdk.java.net/panama-vector/pull/44.diff
  Fetch: git fetch https://git.openjdk.java.net/panama-vector pull/44/head:pull/44

PR: https://git.openjdk.java.net/panama-vector/pull/44


More information about the panama-dev mailing list