[jira] [Resolved] (SPARK-35150) Accelerate fallback BLAS with dev.ludovic.netlib

["Sean R. Owen (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/SPARK-35150?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Sean R. Owen resolved SPARK-35150.
----------------------------------
    Fix Version/s: 3.2.0
       Resolution: Fixed

Issue resolved by pull request 32253
[https://github.com/apache/spark/pull/32253]

> Accelerate fallback BLAS with dev.ludovic.netlib
> ------------------------------------------------
>
>                 Key: SPARK-35150
>                 URL: https://issues.apache.org/jira/browse/SPARK-35150
>             Project: Spark
>          Issue Type: Improvement
>          Components: GraphX, ML, MLlib
>    Affects Versions: 3.2.0
>            Reporter: Ludovic Henry
>            Assignee: Ludovic Henry
>            Priority: Major
>             Fix For: 3.2.0
>
>
> Following https://github.com/apache/spark/pull/30810, I've continued looking for ways to accelerate the usage of BLAS in Spark. With this PR, I integrate work done in the [{{dev.ludovic.netlib}}|https://github.com/luhenry/netlib/] Maven package.
> The {{dev.ludovic.netlib}} library wraps the original {{com.github.fommil.netlib}} library and focus on accelerating the linear algebra routines in use in Spark. When running the {{org.apache.spark.ml.linalg.BLASBenchmark}}benchmarking suite, I get the results at [1] on an Intel machine. Moreover, this library is thoroughly tested to return the exact same results as the reference implementation.
> Under the hood, it reimplements the necessary algorithms in pure autovectorization-friendly Java 8, as well as takes advantage of the Vector API and Foreign Linker API introduced in JDK 16 when available.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org