systemml-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Deron Eriksson (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (SYSTEMML-909) `determineDataFrameDimensionsIfNeeded(...)` is a bottleneck.
Date Wed, 14 Sep 2016 18:20:22 GMT

    [ https://issues.apache.org/jira/browse/SYSTEMML-909?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15491114#comment-15491114
] 

Deron Eriksson commented on SYSTEMML-909:
-----------------------------------------

[~mwdusenb@us.ibm.com] [~mboehm7]
I would be happy to see that conversion code removed from the API and moved deeper into the
project. That would help make the API more lightweight.


> `determineDataFrameDimensionsIfNeeded(...)` is a bottleneck.
> ------------------------------------------------------------
>
>                 Key: SYSTEMML-909
>                 URL: https://issues.apache.org/jira/browse/SYSTEMML-909
>             Project: SystemML
>          Issue Type: Improvement
>            Reporter: Mike Dusenberry
>
> The {{[determineDataFrameDimensionsIfNeeded(...) | https://github.com/apache/incubator-systemml/blob/master/src/main/java/org/apache/sysml/api/mlcontext/MLContextConversionUtil.java#L585]}}
function in {{MLContext}} is a major bottleneck, particularly due to the `javaRDD` call.
> The issue I'm seeing is that the javaRDD.count() function causes execution of the lazy
DataFrames I pass in, which are created from another DataFrame via df.randomSplit([0.8, 0.2]),
thus a shuffle occurs. I know that this is going to happen anyways in the internal conversion,
but it wastes a lot of time by having to also do it in this step too. Assume that I have more
data than I can efficiently cache (~7TB with the potential for much more), so I need to incur
the shuffle step only once on the way into the engine.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message