[GitHub] rednaxelafx commented on issue #23731: [SPARK-26572][SQL] fix aggregate codegen result evaluation

[GitBox <gi...@apache.org>]

rednaxelafx commented on issue #23731: [SPARK-26572][SQL] fix aggregate codegen result evaluation
URL: https://github.com/apache/spark/pull/23731#issuecomment-462663491
 
 
   @maropu : my proposed change won't introduce any performance regressions because what used to be both (1) correct and (2) fast will stay the same, no changes whatsoever; whereas what used to be *incorrect* will be fixed.
   You won't see any statistically significant differences in TPC-DS perf numbers because that benchmark doesn't really use a lot of non-deterministic expressions. Such expressions are rare in the SQL world. There isn't even a `rand()` call in TPC-DS...
   We should expect the TPC-DS queries to generate identical whole-stage codegen code before and after my proposed fix.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org