GeneralizePadTensorOpPattern might generate tensor.dim op so the
TensorDialect should be marked legal. This pattern should also
transform all linalg.pad_tensor ops so mark those as illegal. Those
changes are missed from a previous change in
https://reviews.llvm.org/D105293
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
yea, I think it's because the integration test added has static tensor shape so the tensor::Dim ops are not generated. Let me add another test for dynamic shape.
Comment Actions
+1: can we get a test?
Also please be more descriptive in the title and provide a contextual description: https://mlir.llvm.org/getting_started/Contributing/#commit-messages
Comment Actions
Add an integration test for dynamic shape case when testing padtensor
lowering. Add comments to be more descriptive.
Comment Actions
I don't think we need an integration test here. A regular IR test would be enough to exercise it? (just snapshot the IR from the itnegration test before linalg-bufferize)