Put the GPU data back on host before processing cache on CPU #2970
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Raza Jafri <[email protected]>
|
build |
jlowe
reviewed
Jul 20, 2021
There was a problem hiding this comment.
If DataType isn't supported on the GPU and the data is already on the GPU
This sentence is confusing. If the data type isn't supported by the GPU, how did it get on the GPU? I assume this is a case where the cache serializer doesn't support the type on the GPU but other operators do.
Adding a test would help explain what's going on and also help avoid regressions.
...311/src/main/scala/com/nvidia/spark/rapids/shims/spark311/ParquetCachedBatchSerializer.scala
Outdated
Show resolved
Hide resolved
...311/src/main/scala/com/nvidia/spark/rapids/shims/spark311/ParquetCachedBatchSerializer.scala
Outdated
Show resolved
Hide resolved
Signed-off-by: Raza Jafri <[email protected]>
…rash Signed-off-by: Raza Jafri <[email protected]>
jlowe
changed the title
jlowe
approved these changes
Jul 21, 2021
|
build |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
If DataType isn't supported by
ParquetCachedBatchSerializeron the GPU but the data is already on the GPU, we should copy it back to the host before writing it to cache otherwise the plugin will throw an exception.Fixes #2942
Signed-off-by: Raza Jafri [email protected]