You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Hyukjin Kwon (Jira)" <ji...@apache.org> on 2022/10/28 00:36:00 UTC
[jira] [Commented] (SPARK-40931) Need to Speed up unpacking when reading the next group in VectorizedRleValuesReader
[ https://issues.apache.org/jira/browse/SPARK-40931?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17625361#comment-17625361 ]
Hyukjin Kwon commented on SPARK-40931:
--------------------------------------
[~GGZ] it'd be great if you provide the benchmark codes and results.
> Need to Speed up unpacking when reading the next group in VectorizedRleValuesReader
> --------------------------------------------------------------------------------------
>
> Key: SPARK-40931
> URL: https://issues.apache.org/jira/browse/SPARK-40931
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.4.0
> Reporter: Gu, Guangze
> Priority: Major
>
> In VectorizedRleValuesReader, BytePacker#unpack8Values() with ByteBuffer input API will bring performance degradation, compared to this function with Array input API.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org