[Mlir-commits] [mlir] [mlir][x86] Add extra patterns for AMX nano-kernel lowering (acc with zero constant) (PR #222513)

[Julian Oppermann]

https://github.com/jopperm commented:

Thanks for adding the logic to suppress the redundant loop, that looks good now. I've flagged a dominance issue inline.

https://github.com/llvm/llvm-project/pull/222513