xuechendi commented on pull request #34396: URL: https://github.com/apache/spark/pull/34396#issuecomment-963903913
> @xuechendi thanks for the PR, I'd like to hear a little more about your use case especially how you will with batches serialized to byte arrays, and I'm also curious how much this has in common with RAPIDS use of columnar batches. my use case is that we intend to use Arrow ColumnarBatch as our ColumnarBatch, and we have some operators implemented based on Arrow ColumnarBatch. if this PR is acceptable, then spark will support Arrow as a third candidate for ColumnarBatch Solution(since it can convert Row To Arrow Based Columnar). I think our use case will be very similar with how RAPIDS use of columnar, so this PR should work for both side? -- 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]
