Fix max sizes in DmaDimConfig and refactor #982
Merged
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
jtuyls
requested review from
makslevental,
MaheshRavishankar,
nirvedhmeshram,
yzhang93 and
Abhishek-Varma
as code owners
newling
reviewed
Dec 11, 2024
| return stepSizes; | ||
| } | ||
|
|
||
| SmallVector<int64_t> DmaDimConfig::getMaxStrides() const { |
There was a problem hiding this comment.
AFAICT the function getMaxStrides assumes nbInterStrides is 1, but getMaxSizes doesn't
There was a problem hiding this comment.
Ah, thanks for the catch! This wasn't where the issue was (and we have only one inter dimension in all current devices and inter and intra stride are always the same), so I forgot to update it.
jtuyls
force-pushed
the
fix-dma-dim-config
branch
from
838062a to
ef92dce
Compare
yzhang93
approved these changes
Dec 11, 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Outdated suggestions cannot be applied.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.
Some incorrect max size calculation in
DmaDimConfigwas blocking linear dimension folding and causing the following error when trying to increase the L1 matmul problem from 32x32x32 to 32x32x64 (MxNxK) for bf16:With this PR, that error should be resolved, but I am leaving the addition of that change to a separate PR. cc @yzhang93