[
https://issues.apache.org/jira/browse/IMPALA-14882?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Work on IMPALA-14882 started by Balazs Hevele.
----------------------------------------------
> Add efficient conversion between RowBatch and arrow
> ---------------------------------------------------
>
> Key: IMPALA-14882
> URL: https://issues.apache.org/jira/browse/IMPALA-14882
> Project: IMPALA
> Issue Type: New Feature
> Components: Backend
> Reporter: Csaba Ringhofer
> Assignee: Balazs Hevele
> Priority: Major
> Labels: arrow, performance
>
> There is already arrow -> RowBatch conversion in PaimonScanner, but it is
> done per row and is unlikely to be efficient.
> Fast "transposing" in both direction would allow experimenting with arrow in
> more places, for example in aggregates without group by.
> At first I would focus on RowBatches with a single tuple per row.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
