[Mlir-commits] [mlir] [mlir][vector] Disable transpose -> shuffle lowering for scalable vectors (PR #79979)

[Diego Caballero]

dcaballe wrote:

There are multiple transpose lowering strategies, one using scalar elementwise ops, which should be somewhat equivalent to what you describe above. We may want to choose the right lowering strategy accordingly instead of defaulting to the shuffle one for all the cases.

https://github.com/llvm/llvm-project/pull/79979