Add support for dynamic parallel dims in GEMMs #274
+157
−14
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
harsh-nod
force-pushed
the
gemm_dyn_dims
branch
3 times, most recently
from
e1efc6f
to
322edaa
Compare
harsh-nod
requested review from
Hardcode84,
martin-luecke,
raikonenfnu and
erman-gurses
harsh-nod
force-pushed
the
gemm_dyn_dims
branch
2 times, most recently
from
eaac07b
to
bd7f717
Compare
This PR adds tests for dynamic M, N and K dims in GEMMs. This works out of the box for the most part and just requires moving the align index pass after scheduling and handling the max value of the induction variable for the reduction loop. Signed-off-by: Harsh Menon <[email protected]>
harsh-nod
force-pushed
the
gemm_dyn_dims
branch
from
bd7f717
to
71b0d5d
Compare
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Outdated suggestions cannot be applied.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.
This PR adds tests for dynamic M and N dims in
GEMMs. This works out of the box for the most part
and just requires moving the align index pass
after scheduling.