[llvm-branch-commits] [llvm] [X86] Manage atomic store of fp -> int promotion in DAG (PR #197166)

[Matt Arsenault via llvm-branch-commits]

================
@@ -222,6 +222,140 @@ define void @store_atomic_vec1_ptr(ptr %x, <1 x ptr> %v) nounwind {
   ret void
 }
 
+define void @store_atomic_vec1_bfloat(ptr %x, <1 x bfloat> %v) {
----------------
arsenm wrote:

This doesn't make sense, you only changed the rules for the scalar types. This also will not be reached since AtomicExpand will have replaced the float atomics unless you do something to shouldExpandAtomicStoreInIR / shouldCastAtomicStoreInIR

https://github.com/llvm/llvm-project/pull/197166