fix[next][dace]: Fix memlet for array slicing #1399
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
The memlet used for array slicing was configured in the wrong direction, which caused an error in memlet propagation.
|
While the fix proposed by @edopao helps, I now get an error regarding some missed symbols in an nested SDFG. |
|
@philip-paul-mueller I have pushed a different implementation, based on a mapped tasklet. This implementation works on GPU (tested on |
philip-paul-mueller
approved these changes
Dec 19, 2023
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Outdated suggestions cannot be applied.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.
The memlet used for array slicing was configured in the wrong direction, which caused an error in memlet propagation when targeting a GPU node.
This problem was analyzed in DaCe issue #1481, and resolved by @philip-paul-mueller and @edopao. However, DaCe is still not able of generating CUDA code for such representation.
As a workaround, this PR proposes an implementation of array slicing based on a mapped tasklet.