Neuw84 commented on issue #6264: URL: https://github.com/apache/datafusion-comet/issues/6264#issuecomment-5913466722
Confirming that #6270, applied together with #6268 on main `b58b2f3a` (HEAD `0f22d064`), fixes this at SF1000. **q64 now returns 12,185 rows, the same as vanilla Spark, with the same checksum.** Test setup: - Parquet on S3; - Spark 4.1 on EKS, 8 x 13 cores on m5.4xlarge, in one availability zone; - AQE on, with 300 shuffle partitions; - native scan, exec and shuffle enabled. All 103 TPC-DS queries match Spark on row counts. -- 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]
