llvm/llvm-project
Voir sur GitHub[MLIR][affine] Proper handling of vector load / stores in Affine dialect and transformations
Open
#115 989 ouverte le 13 nov. 2024
good first issuemlir:affine
Métriques du dépôt
- Stars
- (26 378 stars)
- Métriques de merge PR
- (Merge moyen 1j 2h) (1 000 PRs mergées en 30 j)
Description
In the context of Issue-115849 , I see that affine transformation is producing invalid IR like below where vector is being stored to a memref of size 1x1xf32.
affine.vector_store %5, %alloc[0, 0] : memref<1x1xf32>, vector<64x64xf32>
%6 = affine.vector_load %alloc[0, 0] : memref<1x1xf32>, vector<64x512xf32>
I think validity of the affine transformations need to be enhanced by introducing good verifiers.