[
https://issues.apache.org/jira/browse/HIVE-13255?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15218897#comment-15218897
]
Prasanth Jayachandran commented on HIVE-13255:
----------------------------------------------
It definitely needs <0 check. But might not need the looping until requested
size satisfied logic. Since we are passing the InputStream instead of InStream
(does not need looping logic), I added that as well to the latest patch. Branch
prediction + inlining should mitigate the branch cost.
> FloatTreeReader.nextVector is expensive
> ----------------------------------------
>
> Key: HIVE-13255
> URL: https://issues.apache.org/jira/browse/HIVE-13255
> Project: Hive
> Issue Type: Bug
> Components: ORC
> Affects Versions: 2.1.0
> Reporter: Prasanth Jayachandran
> Assignee: Prasanth Jayachandran
> Attachments: HIVE-13255.1.patch, HIVE-13255.2.patch,
> bytecode-size-after.png, bytecode-size-before.png, float-reader-perf.png,
> q1-bottleneck.png, q1-warm-perf-map.png
>
>
> Some TPCDS queries on 1TB scale shows FloatTreeReader on profile samples. It
> is most likely because of multiple branching and polymorphic dispatch in
> FloatTreeReader.nextVector() implementation. See attached image for sampling
> profile output.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
