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

[Jay Foad via llvm-commits]

================
@@ -2561,6 +2567,70 @@ bool SIMemoryLegalizer::expandAtomicCmpxchgOrRmw(const SIMemOpInfo &MOI,
   return Changed;
 }
 
+bool SIMemoryLegalizer::GFX9InsertWaitcntForPreciseMem(MachineFunction &MF) {
+  const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
+  const SIInstrInfo *TII = ST.getInstrInfo();
+  IsaVersion IV = getIsaVersion(ST.getCPU());
+
+  bool Changed = false;
+
+  for (auto &MBB : MF) {
+    for (auto MI = MBB.begin(); MI != MBB.end();) {
+      MachineInstr &Inst = *MI;
+      ++MI;
+      if (Inst.mayLoadOrStore() == false)
+        continue;
+
+      // Todo: if next insn is an s_waitcnt
+      AMDGPU::Waitcnt Wait;
+
+      if (!(Inst.getDesc().TSFlags & SIInstrFlags::maybeAtomic)) {
+        if (TII->isSMRD(Inst)) {          // scalar
----------------
jayfoad wrote:

This logic would need updating again for GFX12. It seems like it's duplicating a lot of knowledge which is already implemented in SIInsertWaitcnts.

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