Rachelint commented on PR #11943: URL: https://github.com/apache/datafusion/pull/11943#issuecomment-2287994535
> THank you @Rachelint -- I took a look at this PR and here is some feedback: > > 1. I think it is important to spend time actually showing this approach makes some queries faster (e.g. we should try and update one accumulator and one implementation of groups to show it makes a difference) > > 2. I think it is important to actually chunk saving the intermediate state (e.g. in a `Vec<...>` rather than `...` to realize the benefit of this chunked approach > > 3. Thank you for working on this. Very cool Thanks, I have finished a blocked style `GroupValuesRows` impl, will do the benchmark soon (As I expect, maybe `blocked GroupValues` + `single GroupAccumulator` also has benefit). -- 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-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
