[clang] [llvm] [AMDGPU] Emit a waitcnt instruction after each memory instruction (PR #79236)

[Matt Arsenault via llvm-commits]

================
@@ -2561,6 +2567,70 @@ bool SIMemoryLegalizer::expandAtomicCmpxchgOrRmw(const SIMemOpInfo &MOI,
   return Changed;
 }
 
+bool SIMemoryLegalizer::GFX9InsertWaitcntForPreciseMem(MachineFunction &MF) {
----------------
arsenm wrote:

can you just make this happen as a consequence of the existing flow rather than using an entirely separate pass over the function?

https://github.com/llvm/llvm-project/pull/79236