zhztheplayer opened a new issue, #13242: URL: https://github.com/apache/gluten/issues/13242
### Description Spark only creates runtime bloom filters for mall dimension tables because scanning the tables in subqueries is cheap. For heavy dimension tables that are slow to scan and behind shuffle exchanges, we'll consider combining the bloom filters that are generated by Velox hash build, and broadcast the combined bloom filter buffers to the scans. This will require Velox's pending feature https://github.com/facebookincubator/velox/issues/18084 ### Gluten version None -- 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]
