[
https://issues.apache.org/jira/browse/SPARK-10599?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Joseph K. Bradley updated SPARK-10599:
--------------------------------------
Shepherd: Joseph K. Bradley
Assignee: Burak Yavuz
Target Version/s: 1.6.0
> Decrease communication in BlockMatrix multiply and increase performance
> -----------------------------------------------------------------------
>
> Key: SPARK-10599
> URL: https://issues.apache.org/jira/browse/SPARK-10599
> Project: Spark
> Issue Type: Improvement
> Components: MLlib
> Reporter: Burak Yavuz
> Assignee: Burak Yavuz
>
> The BlockMatrix multiply sends each block to all the corresponding columns of
> the right BlockMatrix, even though there might not be any corresponding block
> to multiply with.
> Some optimizations we can perform are:
> - Simulate the multiplication on the driver, and figure out which blocks
> actually need to be shuffled
> - Send the block once to a partition, and join inside the partition rather
> than sending multiple copies to the same partition
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
