[llvm] [AMDGPU] Register allocation anti-hints to reduce MFMA hazard NOPs (PR #156943)

[Syadus Sefat via llvm-commits]

================
@@ -248,6 +254,95 @@ bool GCNPreRAOptimizationsImpl::run(MachineFunction &MF) {
 
   bool Changed = false;
 
+  // Single pass implementation
----------------
mssefat wrote:

Fixed it. Please check.

https://github.com/llvm/llvm-project/pull/156943