[llvm] [ASAN][AMDGPU] Make address sanitizer checks more efficient for the divergent target. (PR #72247)

[Matt Arsenault via llvm-commits]

================
@@ -1758,7 +1786,15 @@ void AddressSanitizer::instrumentAddress(Instruction *OrigIns,
   size_t Granularity = 1ULL << Mapping.Scale;
   Instruction *CrashTerm = nullptr;
 
-  if (ClAlwaysSlowPath || (TypeStoreSize < 8 * Granularity)) {
+  bool GenSlowPath = (ClAlwaysSlowPath || (TypeStoreSize < 8 * Granularity));
+
+  if (TargetTriple.isAMDGPU()) {
----------------
arsenm wrote:

Should restrict to amdgcn, the intrinsics you are using won't work for r600 

https://github.com/llvm/llvm-project/pull/72247