[
https://issues.apache.org/jira/browse/SPARK-5773?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14318523#comment-14318523
]
Sean Owen commented on SPARK-5773:
----------------------------------
OK. It's a decent idea, but the impact of array access and cache miss may drown
out the savings in computation at any normal scale.
> Further optimize sparse syr
> ---------------------------
>
> Key: SPARK-5773
> URL: https://issues.apache.org/jira/browse/SPARK-5773
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Reporter: Liang-Chi Hsieh
> Priority: Minor
>
> The current sparse syr in BLAS can be further optimized.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
