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

[via llvm-commits]

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

X86 backend does not lower load atomic float; yet it does so for integers, so we can cast to an integer before lowering in order to support this instruction.

>From 2d0ad97a69e0145fe8aec656c1a833970da17e77 Mon Sep 17 00:00:00 2001
From: jofernau <Joe.Fernau at amd.com>
Date: Thu, 21 Nov 2024 11:46:32 -0500
Subject: [PATCH] [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.
---
 llvm/lib/Target/X86/X86ISelLowering.cpp |  8 ++++++++
 llvm/lib/Target/X86/X86ISelLowering.h   |  2 ++
 llvm/test/CodeGen/X86/atomic-float.ll   | 15 +++++++++++++++
 3 files changed, 25 insertions(+)
 create mode 100644 llvm/test/CodeGen/X86/atomic-float.ll

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index bcb84add65d83e..b0abd1315bd812 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/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();
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index 14ada1721fd40e..75f8c46362327f 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/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
diff --git a/llvm/test/CodeGen/X86/atomic-float.ll b/llvm/test/CodeGen/X86/atomic-float.ll
new file mode 100644
index 00000000000000..fa5977808aed51
--- /dev/null
+++ b/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
+}
+