andygrove opened a new issue, #2894: URL: https://github.com/apache/datafusion-comet/issues/2894
### What is the problem the feature request solves? Comet currently tries to avoid mixing "Spark partial / Comet final" and "Comet partial / Spark final" aggregates. This is necessary in some cases due to incompatibilities between Spark and Comet for the intermediate aggregate buffer format, but in other cases this fallback is not necessary. ### Describe the potential solution Add logic to determine which aggregates are safe to have both Spark and Comet operators and do not fall back for those. ### Additional context _No response_ -- 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]
