[vectorIntrinsics] Withdrawn: 8263149: Adding some algorithms optimized by Vector API into JMH benc…
Wang Zhuo
wzhuo at openjdk.java.net
Wed Mar 17 09:56:54 UTC 2021
On Mon, 8 Mar 2021 03:06:40 GMT, Wang Zhuo <wzhuo at openjdk.org> wrote:
> 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>
This pull request has been closed without being integrated.
-------------
PR: https://git.openjdk.java.net/panama-vector/pull/44
More information about the panama-dev
mailing list