[PATCH] D74638: [mlir][Linalg] Allow specifiying zero-rank shaped type operands to linalg.generic ops.

[Han-Chung Wang via Phabricator via llvm-commits]

hanchung added inline comments.


================
Comment at: mlir/lib/Dialect/Linalg/Transforms/LinalgToLoops.cpp:346-351
     for (unsigned i = 0; i < nInputs; ++i) {
       ValueHandleArray indexing(makeCanonicalAffineApplies(
           b, loc, indexedGenericOp.getInputIndexingMap(i), allIvs));
       indexedValues[nLoops + i] =
           std_load(indexedGenericOp.getInput(i), indexing);
     }
----------------
This part should also be updated with

```
      Value input = indexedGenericOp.getInput(i);
      if (!input.getType().cast<ShapedType>().getRank()) {
        indexedValues[nLoops + i] = std_load(input);
      } else {
        ValueHandleArray indexing(makeCanonicalAffineApplies(
            b, loc, indexedGenericOp.getInputIndexingMap(i), allIvs));
        indexedValues[nLoops + i] = std_load(input, indexing);
      }
    }
```


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74638/new/

https://reviews.llvm.org/D74638