[clang] [llvm] [AMDGPU] Add amdgpu-as MMRA for fences (PR #78572)

[Sameer Sahasrabuddhe via llvm-commits]

================
@@ -18365,6 +18366,28 @@ Value *CodeGenFunction::EmitHLSLBuiltinExpr(unsigned BuiltinID,
   return nullptr;
 }
 
+void CodeGenFunction::AddAMDGCNFenceAddressSpaceMMRA(llvm::Instruction *Inst,
+                                                     const CallExpr *E) {
+  constexpr const char *Tag = "amdgpu-as";
----------------
ssahasra wrote:

Just bikeshedding a bit, but do we really need the "amdgpu" prefix on the tag? Clang will only generate these for AMDGPU anyway. It's not a blocker, but feels like we are being cautious for no reason.

https://github.com/llvm/llvm-project/pull/78572