[Mlir-commits] [mlir] [mlir][vector] Implement speculation for vector.transferx ops (PR #111533)

[Jakub Kuderski]

kuhar wrote:

> A lot (most?) things in that doc only really matter when dealing with MemRefs. And the implementation here also implies that:
> when operating on tensors, everything is safe,
> when operating on memrefs, exercise caution.

This is not true in the general case outside of these ops. For example, dividing a tensor by tensor (elementwise) is not always safe. I think what we have with these 'element access ops' here might be a special case.

https://github.com/llvm/llvm-project/pull/111533