You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@arrow.apache.org by "Yibo Cai (Jira)" <ji...@apache.org> on 2020/09/01 05:11:00 UTC
[jira] [Commented] (ARROW-9873) [C++][Compute] Improve mode kernel
for intergers within limited value range
[ https://issues.apache.org/jira/browse/ARROW-9873?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17188142#comment-17188142 ]
Yibo Cai commented on ARROW-9873:
---------------------------------
Array size in bytes looks a more reasonable crossover point than array size in items. Tested with int32/int64, int32 needs more items than int64 to benefit from this optimization.
So the threshold is:
- array size in bytes >= 8192
- array value range <= 16384
> [C++][Compute] Improve mode kernel for intergers within limited value range
> ---------------------------------------------------------------------------
>
> Key: ARROW-9873
> URL: https://issues.apache.org/jira/browse/ARROW-9873
> Project: Apache Arrow
> Issue Type: Improvement
> Components: C++
> Reporter: Yibo Cai
> Assignee: Yibo Cai
> Priority: Major
> Attachments: mode-range-skylake.png
>
>
> It's possible to improve mode kernel performance for integers within limited value range by using a value indexed array instead of general hash table.
> Similar trick is used in sorting kernel ARROW-1571.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)