Sameer Raheja
Sameer Raheja
Closing until we can retarget to the latest branch
Would need to add dictionary support.
@thirtiseven has this issue been verified to be closed by https://github.com/NVIDIA/spark-rapids/pull/10466 ? cc: @revans2
Is this similar to #9033 ?
Hi @liurenjie1024 , can you be more specific about current performance and what we are going to do to improve performance?
Removing P1 and removing from 22.08 since the issue only occurs in WSL2 (which we do not support).
Hi @asddfl ( @asdsql ? ), cudf and Spark handle quotes in CSV files differently, which is what you identified. We are working to ensure the RAPIDS Spark plugin matches...
We could leverage https://github.com/rapidsai/cudf/pull/9215 , but could also implement the sha-2 algorithm in spark-rapids-jni.
@arturzangiev let us know if using the newer release with a newer GPU addresses the issue. Closing for now, please reopen if you have further questions.
This has not appeared again, even with the same datagen seed. Usually we run where shuffle is done on a single node. The results are based on shuffle and therefore...