[llvm-branch-commits] [llvm] [AMDGPU] Enable atomic optimizer for divergent i64 and double values (PR #96934)

[Matt Arsenault via llvm-branch-commits]

================
@@ -178,6 +178,21 @@ bool AMDGPUAtomicOptimizerImpl::run(Function &F) {
   return Changed;
 }
 
+static bool isOptimizableAtomic(Type *Ty) {
----------------
arsenm wrote:

How about isLegalCrossLaneType? 

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