[clang] [llvm] [AMDGPU] Emit a waitcnt instruction after each memory instruction (PR #68932)

[Matt Arsenault via cfe-commits]

================
@@ -52,6 +52,11 @@ static cl::opt<bool> ForceEmitZeroFlag(
   cl::desc("Force all waitcnt instrs to be emitted as s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)"),
   cl::init(false), cl::Hidden);
 
+static cl::opt<bool>
+    PreciseMemOpFlag("amdgpu-precise-memory-op",
+                     cl::desc("Emit s_waitcnt 0 after each memory operation"),
+                     cl::init(false));
+
----------------
arsenm wrote:

I think this should be fused into an enum flag with the existing waitcnt flag.

https://github.com/llvm/llvm-project/pull/68932