[X86] Lowering of load atomic float via cast

X86 backend does not lower load atomic float, so we can cast to an
integer before lowering.

Author: jofrn

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -30976,6 +30976,14 @@ bool X86TargetLowering::needsCmpXchgNb(Type *MemType) const {
   return false;
 }
 
+TargetLoweringBase::AtomicExpansionKind
+X86TargetLowering::shouldCastAtomicLoadInIR(LoadInst *LI) const {
+  if (LI->getType()->isVectorTy())
+    if (cast<VectorType>(LI->getType())->getElementType()->isFloatingPointTy())
+      return AtomicExpansionKind::CastToInteger;
+  return TargetLowering::shouldCastAtomicLoadInIR(LI);
+}
+
 TargetLoweringBase::AtomicExpansionKind
 X86TargetLowering::shouldExpandAtomicStoreInIR(StoreInst *SI) const {
   Type *MemType = SI->getValueOperand()->getType();

llvm/lib/Target/X86/X86ISelLowering.h

@@ -1808,6 +1808,8 @@ namespace llvm {
     const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const override;
     ArrayRef<MCPhysReg> getRoundingControlRegisters() const override;
 
+    TargetLoweringBase::AtomicExpansionKind
+    shouldCastAtomicLoadInIR(LoadInst *LI) const override;
     TargetLoweringBase::AtomicExpansionKind
     shouldExpandAtomicLoadInIR(LoadInst *LI) const override;
     TargetLoweringBase::AtomicExpansionKind

llvm/test/CodeGen/X86/atomic-float.ll

@@ -0,0 +1,15 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s --mtriple=x86_64 --passes=atomic-expand -S -o - | FileCheck %s
+
+define float @load_atomic_float() {
+; CHECK-LABEL: define float @load_atomic_float() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca float, align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = load atomic i32, ptr [[SRC]] acquire, align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32 [[TMP1]] to float
+; CHECK-NEXT:    ret float [[TMP2]]
+;
+  %src = alloca float
+  %ret = load atomic float, ptr %src acquire, align 4
+  ret float %ret
+}
+