[Mlir-commits] [mlir] [mlir] Handle arith.const expr in dispatchIndexOpFoldResult func (PR #122432)

Matthias Springer llvmlistbot at llvm.org
Tue Jan 14 06:15:39 PST 2025


matthias-springer wrote:

What I am wondering: Where is this example op coming from?
```
  %expand = tensor.expand_shape %collapse [[0], [1], [2, 3]]
              output_shape [%s0, %s1, %c2, %c3] : tensor<?x4x6xf32> into tensor<?x4x2x3xf32>
```

I'd like to understand why the `output_shape` is not static.


https://github.com/llvm/llvm-project/pull/122432


More information about the Mlir-commits mailing list