[llvm] [AMDGPU] Add scheduling stage to rewrite MFMA from VGPR to AGPR (PR #149367)

[Lucas Ramirez via llvm-commits]

================
@@ -1036,6 +1041,114 @@ bool GCNSchedStage::initGCNSchedStage() {
   return true;
 }
 
+SlotIndex
----------------
lucas-rami wrote:

Return value not used anywhere.

https://github.com/llvm/llvm-project/pull/149367