[AMD] Remove tritonamdgpu-stream-pipeline #4845
Open
+3
−983
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
antiagainst
requested changes
Oct 3, 2024
third_party/amd/backend/compiler.py
Outdated
| else: | ||
| if options.num_stages == 0: | ||
| amd.passes.ttgpuir.add_stream_pipeline(pm) | ||
| num_stages = options.num_stages if options.num_stages != 0 else 2 |
There was a problem hiding this comment.
We should also drop this too--it was meant to smooth transition. After v1 gone we need to respect what the user set--if it's 0 then we don't pipeline anymore.
There was a problem hiding this comment.
This will have a big influence on almost everyone. For now, all gemm-like kernels on AMD backend uses num_stages=0. Removing it will cause a significant perf regression.
There was a problem hiding this comment.
Yeah num_stages=0 just need to be fixed in all downstream users--we cannot be beholden to that.
antiagainst
approved these changes
Oct 3, 2024
antiagainst
requested changes
Oct 3, 2024
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Outdated suggestions cannot be applied.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.
No description provided.