[llvm-branch-commits] [llvm] [AMDGPU] Enable atomic optimizer for 64 bit divergent values (PR #96934)

[Matt Arsenault via llvm-branch-commits]

================
@@ -178,6 +178,20 @@ bool AMDGPUAtomicOptimizerImpl::run(Function &F) {
   return Changed;
 }
 
+static bool shouldOptimizeForType(Type *Ty) {
----------------
arsenm wrote:

Name this something that states why this should be handled, not a vague "shouldOptimize" 

https://github.com/llvm/llvm-project/pull/96934