andygrove commented on PR #4591: URL: https://github.com/apache/datafusion-comet/pull/4591#issuecomment-4793520364
> thank you @andygrove for your very detailed review and comparison of the PRs. > > So, what should I take up as my next course of action exactly now? Should I now include Batch-level pruning, stats-based `buildFilter`, and respect-user-serializer install logic in my current PR as you've indicated above? or do you have something else in mind? I'm happy to keep reviewing if you want to keep iterating on this. My review was just using AI, so we need to decide what makes sense for the first PR. I would say the pruning/filter work is quite important. I'd also like to see microbenchmarks so that we can measure the Comet 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
