[llvm] [X86] Lowering of load atomic float via cast (PR #117189)

[Matt Arsenault via llvm-commits]

================
@@ -31158,6 +31158,14 @@ bool X86TargetLowering::needsCmpXchgNb(Type *MemType) const {
   return false;
 }
 
+TargetLoweringBase::AtomicExpansionKind
+X86TargetLowering::shouldCastAtomicLoadInIR(LoadInst *LI) const {
+  if (const auto VT = dyn_cast<VectorType>(LI->getType()))
+    if (VT->getElementType()->isFloatingPointTy())
+      return AtomicExpansionKind::CastToInteger;
+  return TargetLowering::shouldCastAtomicLoadInIR(LI);
+}
----------------
arsenm wrote:

This seems to be moving in the opposite direction. The existing tests atomic FP load already works, and this is regressing it to use the IR expansion (which should be deleted)

https://github.com/llvm/llvm-project/pull/117189