You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by GitBox <gi...@apache.org> on 2022/06/28 18:23:37 UTC
[GitHub] [arrow-datafusion] tustvold commented on pull request #2808: Use specialized dictionary kernels (#1178)
tustvold commented on PR #2808:
URL: https://github.com/apache/arrow-datafusion/pull/2808#issuecomment-1169072866
Unsurprisingly the performance benefits of this are quite pronounced
```
scheduled: select count(*) from t where dict_10_required = 'prefix#0'
time: [4.0683 ms 4.0732 ms 4.0783 ms]
change: [-40.646% -40.476% -40.299%] (p = 0.00 < 0.05)
Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
3 (3.00%) high mild
tokio: select count(*) from t where dict_100_required = 'prefix#0'
time: [4.4917 ms 4.5479 ms 4.6022 ms]
change: [-39.027% -38.266% -37.502%] (p = 0.00 < 0.05)
Performance has improved.
scheduled: select count(*) from t where dict_100_required = 'prefix#0'
time: [3.8694 ms 3.8755 ms 3.8815 ms]
change: [-33.176% -32.985% -32.795%] (p = 0.00 < 0.05)
Performance has improved.
tokio: select count(*) from t where dict_1000_required = 'prefix#0'
time: [4.7944 ms 4.8326 ms 4.8687 ms]
change: [-31.344% -30.719% -30.083%] (p = 0.00 < 0.05)
Performance has improved.
```
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org