[clang] [llvm] [AMDGPU][GFX12.5] Reimplement monitor load as an atomic operation (PR #177343)

[Pierre van Houtryve via cfe-commits]

================
@@ -131,42 +131,13 @@ class SPIRVTargetCodeGenInfo : public CommonSPIRTargetCodeGenInfo {
                                   const VarDecl *D) const override;
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
                            CodeGen::CodeGenModule &M) const override;
-  llvm::SyncScope::ID getLLVMSyncScopeID(const LangOptions &LangOpts,
-                                         SyncScope Scope,
-                                         llvm::AtomicOrdering Ordering,
-                                         llvm::LLVMContext &Ctx) const override;
+  std::string getLLVMSyncScopeStr(const LangOptions &LangOpts, SyncScope Scope,
----------------
Pierre-vh wrote:

Yeah one-as should eventually go in favor of a better system. It comes up every now and then in memory consistency discussions, but it's not a urgent thing to look at.

I went with returning a StringRef, it actually makes the AMDGPU impl cleaner than before (IMO).

https://github.com/llvm/llvm-project/pull/177343