spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Apache Spark (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (SPARK-16213) Reduce runtime overhead of a program that creates an primitive array in DataFrame
Date Sun, 26 Jun 2016 04:08:37 GMT

    [ https://issues.apache.org/jira/browse/SPARK-16213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15349940#comment-15349940
] 

Apache Spark commented on SPARK-16213:
--------------------------------------

User 'kiszk' has created a pull request for this issue:
https://github.com/apache/spark/pull/13909

> Reduce runtime overhead of a program that creates an primitive array in DataFrame
> ---------------------------------------------------------------------------------
>
>                 Key: SPARK-16213
>                 URL: https://issues.apache.org/jira/browse/SPARK-16213
>             Project: Spark
>          Issue Type: Improvement
>          Components: SQL
>            Reporter: Kazuaki Ishizaki
>
> Reduce runtime overhead of a program that creates an primitive array in DataFrame
> When a program creates an array in DataFrame, the code generator creates boxing operations.
If an array is for primitive type, there are some opportunities for optimizations in generated
code to reduce runtime overhead.
> Here is a simple example that has generated code with boxing operation
> {code}
> val df = sparkContext.parallelize(Seq(0.0d, 1.0d), 1).toDF
> df.selectExpr("Array(value + 1.1d, value + 2.2d)").show
> {code}



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

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


Mime
View raw message