[Mosaic GPU] Improve checks on the WG strided transfers #32247
Closed
+0
−0
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
![copybara-service[bot]](https://avatars.githubusercontent.com/in/44061?s=60&v=4){kind=small}
copybara-service
bot
force-pushed
the
test_813722484
branch
from
5375748 to
c0bff2f
Compare
copybara-service
bot
force-pushed
the
test_813722484
branch
from
c0bff2f to
33c7a7e
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Outdated suggestions cannot be applied.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.
[Mosaic GPU] Improve checks on the WG strided transfers
Our previous code didn't actually verify that the vector loads/stores are safe,
so you could pass in a non-contiguous reference with a weird shape, but the right
number of elements and get nonsensical results. The current check is a bit too conservative,
but it's better to lean this way.
This also factors the address calculation into a common
transfer_stridedclass method, followingthe same pattern we use for tiled layouts.