[
https://issues.apache.org/jira/browse/SPARK-15985?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Wenchen Fan resolved SPARK-15985.
---------------------------------
Resolution: Fixed
Fix Version/s: 2.1.0
Issue resolved by pull request 13704
[https://github.com/apache/spark/pull/13704]
> Reduce runtime overhead of a program that reads an primitive array in Dataset
> -----------------------------------------------------------------------------
>
> Key: SPARK-15985
> URL: https://issues.apache.org/jira/browse/SPARK-15985
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Reporter: Kazuaki Ishizaki
> Assignee: Kazuaki Ishizaki
> Fix For: 2.1.0
>
>
> When a program read an array in Dataset, the code generator create some copy
> operations. If an array is for primitive type, there are some opportunities
> for optimizations in generated code to reduce runtime overhead.
> {code}
> val ds = Seq(Array(1.0, 2.0, 3.0), Array(4.0, 5.0, 6.0)).toDS()
> ds.map(p => {
> var s = 0.0
> for (i <- 0 to 2) { s += p(i) }
> s
> }).show
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
