[Mlir-commits] [mlir] [MLIR][Vector] Relax shape_cast unrolling to per-reassociation-group contiguity (PR #205684)

[Jianhui Li]

Jianhui-Li wrote:

> Your reply addresses my concerns. It would be good to add comments in code to re-enforce these assumptions/guidelines, i.e. this unrolling should not be used by targets for which `tensor.extract_strided_slice` is a concern and `vector.shape_cast` should be treated as NOP.
> 
> Otherwise LGTM

Added comments and two negative tests. Please take a look. Thanks! @banach-space

https://github.com/llvm/llvm-project/pull/205684