[
https://issues.apache.org/jira/browse/SPARK-16412?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15366167#comment-15366167
]
Apache Spark commented on SPARK-16412:
--------------------------------------
User 'kiszk' has created a pull request for this issue:
https://github.com/apache/spark/pull/14091
> Generate Java code that gets an array in each column of CachedBatch when
> DataFrame.cache() is called
> ----------------------------------------------------------------------------------------------------
>
> Key: SPARK-16412
> URL: https://issues.apache.org/jira/browse/SPARK-16412
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Reporter: Kazuaki Ishizaki
>
> Once SPARK-14098 is merged, we will migrate a feature in this JIRA entry.
> When DataFrame.cache() is called, data is stored as column-oriented storage
> in CachedBatch. The current Catalyst generates Java program to get an array
> in a column from an InternalRow that is copied from CachedBatch. This JIRA
> entry generates Java code to directly get the array in a column from
> CachedBatch without copy. This JIRA entry supports an array (ArrayType in
> Spark).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
