Workaround for a misaligned access in read_csv on some CUDA versions
#17477
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
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
vuule
changed the title
read_csv on some CUDA versions
|
/ok to test |
|
/ok to test |
bdice
approved these changes
Dec 3, 2024
davidwendt
approved these changes
Dec 3, 2024
|
/merge |
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Outdated suggestions cannot be applied.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.
Description
Use a global array instead of a shared memory array in the
gather_row_offsets_gpukernel.Impact on the kernel performance is less than 5%, and this kernel takes very little portion of the total read_csv execution time - impact on the performance is negligible.
Also modified functions that take this array to take a
device_spaninstead on a plain pointer.Checklist