FelixYBW commented on issue #10075: URL: https://github.com/apache/incubator-gluten/issues/10075#issuecomment-3017356556
Hash based shuffle data can be compressed column by column or batch by batch. In theory compressing by column has best compression ratio since each column has its own characteristics. Batch compression introduced extra memcpy. -- 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]
