[Mlir-commits] [mlir] [mlir] [linalg] fix failure on specializing matmul with permuted loops (PR #184294)

[Renato Golin]

rengolin wrote:

> This patch fixes this problem by not forwarding the maps of the original generic and instead recreating them ensuring they always follow the canonical order.

But if the generic inputs were in a different order (transposed), then you'd have to un-transpose them first, to be able to use the canonical gemm map, no?

https://github.com/llvm/llvm-project/pull/184294