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

[Pierre van Houtryve via cfe-commits]

================
@@ -603,14 +626,69 @@ class SIGfx12CacheControl : public SIGfx11CacheControl {
                                       SIAtomicAddrSpace AddrSpace, SIMemOp Op,
                                       bool IsVolatile,
                                       bool IsNonTemporal) const override;
+
+  bool
+  handleNonAtomicForPreciseMemory(MachineBasicBlock::iterator &MI) override;
+  bool handleAtomicForPreciseMemory(MachineBasicBlock::iterator &MI,
+                                    bool ret) override;
+};
+
+#if 0
+class SIPreciseMemorySupport {
+protected:
+  const GCNSubtarget &ST;
+  const SIInstrInfo *TII = nullptr;
+
+  IsaVersion IV;
+
+  SIPreciseMemorySupport(const GCNSubtarget &ST) : ST(ST) {
+    TII = ST.getInstrInfo();
+    IV = getIsaVersion(ST.getCPU());
+  }
+
+public:
+  static std::unique_ptr<SIPreciseMemorySupport> create(const GCNSubtarget &ST);
+
+  virtual bool handleNonAtomic(MachineBasicBlock::iterator &MI) = 0;
+  /// Handles atomic instruction \p MI with \p ret indicating whether \p MI
+  /// returns a result.
+  virtual bool handleAtomic(MachineBasicBlock::iterator &MI, bool ret) = 0;
+};
+
+class SIGfx9PreciseMemorySupport : public SIPreciseMemorySupport {
+public:
+  SIGfx9PreciseMemorySupport(const GCNSubtarget &ST)
+      : SIPreciseMemorySupport(ST) {}
+  bool handleNonAtomic(MachineBasicBlock::iterator &MI) override;
+  bool handleAtomic(MachineBasicBlock::iterator &MI, bool ret) override;
 };
 
+class SIGfx10And11PreciseMemorySupport : public SIPreciseMemorySupport {
+public:
+  SIGfx10And11PreciseMemorySupport(const GCNSubtarget &ST)
+      : SIPreciseMemorySupport(ST) {}
+  bool handleNonAtomic(MachineBasicBlock::iterator &MI) override;
+  bool handleAtomic(MachineBasicBlock::iterator &MI, bool ret) override;
+};
+
+std::unique_ptr<SIPreciseMemorySupport>
+SIPreciseMemorySupport::create(const GCNSubtarget &ST) {
+  GCNSubtarget::Generation Generation = ST.getGeneration();
+  if (Generation < AMDGPUSubtarget::GFX10)
+    return std::make_unique<SIGfx9PreciseMemorySupport>(ST);
+  return std::make_unique<SIGfx10And11PreciseMemorySupport>(ST);
+}
+#endif
+
 class SIMemoryLegalizer final : public MachineFunctionPass {
 private:
 
   /// Cache Control.
   std::unique_ptr<SICacheControl> CC = nullptr;
 
+  /// Precise Memory support.
+  bool PM = false;
----------------
Pierre-vh wrote:

PM is commonly used for PassManager so I'd just use `PrecMem` or something similar. Of course PassManager makes no sense here but I personally thought of that first before thinking PreciseMemory

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