EmmyMiao87 commented on issue #7901: URL: https://github.com/apache/incubator-doris/issues/7901#issuecomment-1077323522
> shuffling profit most from column pruning so we only do projection (including column pruning, some computing operations) in each datastreamsender instead of each node (join, agg, etc.). When be is implemented, it is possible to put the project logic in the sender uniformly. However, in the case of vectorization, if the project logic is pushed down to the hash join node, the time-consuming of **memory copying can also be reduced during node calculation**. Therefore, the project implementation of hash join is not uniformly placed in the sender. -- 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: commits-unsubscr...@doris.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org
