vulkan: support larger argsort #17313
Merged
+257
−48
Conversation
This file contains hidden or 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
github-actions
bot
added
testing
jeffbolznv
force-pushed
the
argsort_large
branch
from
a6f38e1 to
b7f5a07
Compare
This is an extension of the original bitonic sorting shader that puts the temporary values in global memory and when more than 1024 threads are needed it runs multiple workgroups and synchronizes through a pipelinebarrier. To improve the memory access pattern, a copy of the float value is kept with the index value. I've applied this same change to the original shared memory version of the shader, which is still used when ncols <= 1024.
jeffbolznv
force-pushed
the
argsort_large
branch
from
b7f5a07 to
69a5306
Compare
…ng a single pass, for a modest perf boost
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This is an extension of the original bitonic sorting shader that puts the temporary values in global memory and when more than 1024 threads are needed it runs multiple workgroups and synchronizes through a pipelinebarrier.
To improve the memory access pattern, a copy of the float value is kept with the index value. I've applied this same change to the original shared memory version of the shader, which is still used when ncols <= 1024.
Performance seems pretty good relative to the cuda backend, but somewhat worse than CUB for the largest sizes with multiple rows.