[
https://issues.apache.org/jira/browse/DRILL-8088?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17467856#comment-17467856
]
ASF GitHub Bot commented on DRILL-8088:
---------------------------------------
Z0ltrix commented on pull request #2412:
URL: https://github.com/apache/drill/pull/2412#issuecomment-1003945110
> > Drill was designed to allow vector operations (hence Value Vectors), but
the code was never written. In part because there are no CPU vector
instructions that work with SQL nullable data. Arrow is supposed to have
figured out solutions (Gandiva, is it?) which, perhaps we could consider (but
probably only for non-nullable data.)
>
> Hi @paul-rogers, I think that what Arrow does for computations over
nullable data is store an external null mask and compute results for every
record, including the null ones where the value vector contains either rubbish
or some sentinel value. In a second pass, a null mask is computed for the
result. This results in wasted arithmetic operations for null values, but in
practice that's better than a branch for every value. Quite possibly even for
pretty sparse vectors.
i'm sure you have already discussed this, but i would like to know why we
are not migrating to arrow and cannot find any information about this decision.
As far as i know, arrow was inspired by drill and on the arrow homepage they
have still the picture with drill on it but drill does not use arrow.
https://arrow.apache.org/overview/
Is there any official statement from the project for the arrow
support/migration?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
> Improve expression evaluation performance
> -----------------------------------------
>
> Key: DRILL-8088
> URL: https://issues.apache.org/jira/browse/DRILL-8088
> Project: Apache Drill
> Issue Type: Improvement
> Components: Execution - Codegen
> Reporter: wtf
> Assignee: wtf
> Priority: Minor
>
> Found unnecessary map copy when doing expression evaluation, it will slow
> down the codegen when the query include many "case when" or avg/stddev(the
> reduced expressions include "case when"). In our case, the query include 314
> avg, it takes 3+ seconds to generate the projector expressions(Intel(R)
> Xeon(R) CPU E5-2682 v4 @ 2.50GHz 32cores).
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
