[clang] [Clang][CodeGen] Fix type for atomic float incdec operators (PR #107075)
via cfe-commits
cfe-commits at lists.llvm.org
Tue Sep 3 03:03:50 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-clang-codegen
@llvm/pr-subscribers-backend-x86
Author: Yingwei Zheng (dtcxzyw)
<details>
<summary>Changes</summary>
`llvm::ConstantFP::get(llvm::LLVMContext&, APFloat(float))` always returns a f32 constant.
Fix https://github.com/llvm/llvm-project/issues/107054.
---
Patch is 46.54 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/107075.diff
4 Files Affected:
- (modified) clang/lib/CodeGen/CGExprScalar.cpp (+14-11)
- (modified) clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c (+40-72)
- (modified) clang/test/CodeGen/X86/x86-atomic-double.c (+44-44)
- (modified) clang/test/CodeGen/X86/x86-atomic-long_double.c (+241-52)
``````````diff
diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index af11bc20a3b639..7aa2d3d89c2936 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -2865,19 +2865,22 @@ ScalarExprEmitter::EmitScalarPrePostIncDec(const UnaryOperator *E, LValue LV,
llvm::AtomicOrdering::SequentiallyConsistent);
return isPre ? Builder.CreateBinOp(op, old, amt) : old;
}
- // Special case for atomic increment/decrement on floats
+ // Special case for atomic increment/decrement on floats.
+ // Bail out non-power-of-2-sized floating point types (e.g., x86_fp80).
if (type->isFloatingType()) {
- llvm::AtomicRMWInst::BinOp aop =
- isInc ? llvm::AtomicRMWInst::FAdd : llvm::AtomicRMWInst::FSub;
- llvm::Instruction::BinaryOps op =
- isInc ? llvm::Instruction::FAdd : llvm::Instruction::FSub;
- llvm::Value *amt = llvm::ConstantFP::get(
- VMContext, llvm::APFloat(static_cast<float>(1.0)));
- llvm::AtomicRMWInst *old =
- CGF.emitAtomicRMWInst(aop, LV.getAddress(), amt,
- llvm::AtomicOrdering::SequentiallyConsistent);
+ llvm::Type *Ty = ConvertType(type);
+ if (llvm::has_single_bit(Ty->getScalarSizeInBits())) {
+ llvm::AtomicRMWInst::BinOp aop =
+ isInc ? llvm::AtomicRMWInst::FAdd : llvm::AtomicRMWInst::FSub;
+ llvm::Instruction::BinaryOps op =
+ isInc ? llvm::Instruction::FAdd : llvm::Instruction::FSub;
+ llvm::Value *amt = llvm::ConstantFP::get(Ty, 1.0);
+ llvm::AtomicRMWInst *old =
+ CGF.emitAtomicRMWInst(aop, LV.getAddress(), amt,
+ llvm::AtomicOrdering::SequentiallyConsistent);
- return isPre ? Builder.CreateBinOp(op, old, amt) : old;
+ return isPre ? Builder.CreateBinOp(op, old, amt) : old;
+ }
}
value = EmitLoadOfLValue(LV, E->getExprLoc());
input = value;
diff --git a/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c b/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c
index 6deff1116e1d81..a8fb989b64de50 100644
--- a/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c
+++ b/clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c
@@ -99,20 +99,16 @@ float test_float_pre_inc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 8
-// SAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: ret double [[TMP1]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_post_inc.n to ptr), double 1.000000e+00 seq_cst, align 8
+// SAFE-NEXT: ret double [[TMP0]]
//
// UNSAFE-LABEL: define dso_local double @test_double_post_inc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
-// UNSAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: ret double [[TMP1]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_post_inc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: ret double [[TMP0]]
//
double test_double_post_inc()
{
@@ -125,20 +121,16 @@ double test_double_post_inc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_post_dc.n to ptr), float 1.000000e+00 seq_cst, align 8
-// SAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: ret double [[TMP1]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_post_dc.n to ptr), double 1.000000e+00 seq_cst, align 8
+// SAFE-NEXT: ret double [[TMP0]]
//
// UNSAFE-LABEL: define dso_local double @test_double_post_dc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_post_dc.n to ptr), float 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
-// UNSAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: ret double [[TMP1]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_post_dc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: ret double [[TMP0]]
//
double test_double_post_dc()
{
@@ -151,22 +143,18 @@ double test_double_post_dc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_pre_dc.n to ptr), float 1.000000e+00 seq_cst, align 8
-// SAFE-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00
-// SAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: ret double [[TMP2]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_pre_dc.n to ptr), double 1.000000e+00 seq_cst, align 8
+// SAFE-NEXT: [[TMP1:%.*]] = fsub double [[TMP0]], 1.000000e+00
+// SAFE-NEXT: ret double [[TMP1]]
//
// UNSAFE-LABEL: define dso_local double @test_double_pre_dc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_pre_dc.n to ptr), float 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
-// UNSAFE-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00
-// UNSAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: ret double [[TMP2]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test_double_pre_dc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: [[TMP1:%.*]] = fsub double [[TMP0]], 1.000000e+00
+// UNSAFE-NEXT: ret double [[TMP1]]
//
double test_double_pre_dc()
{
@@ -179,22 +167,18 @@ double test_double_pre_dc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 8
-// SAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
-// SAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// SAFE-NEXT: ret double [[TMP2]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_pre_inc.n to ptr), double 1.000000e+00 seq_cst, align 8
+// SAFE-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00
+// SAFE-NEXT: ret double [[TMP1]]
//
// UNSAFE-LABEL: define dso_local double @test_double_pre_inc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca double, align 8, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
-// UNSAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
-// UNSAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL_ASCAST]], align 8
-// UNSAFE-NEXT: ret double [[TMP2]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test_double_pre_inc.n to ptr), double 1.000000e+00 seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00
+// UNSAFE-NEXT: ret double [[TMP1]]
//
double test_double_pre_inc()
{
@@ -207,20 +191,16 @@ double test_double_pre_inc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 2
-// SAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: [[TMP1:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: ret half [[TMP1]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_post_inc.n to ptr), half 0xH3C00 seq_cst, align 2
+// SAFE-NEXT: ret half [[TMP0]]
//
// UNSAFE-LABEL: define dso_local half @test__Float16_post_inc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_post_inc.n to ptr), float 1.000000e+00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
-// UNSAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: [[TMP1:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: ret half [[TMP1]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_post_inc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: ret half [[TMP0]]
//
_Float16 test__Float16_post_inc()
{
@@ -233,20 +213,16 @@ _Float16 test__Float16_post_inc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_post_dc.n to ptr), float 1.000000e+00 seq_cst, align 2
-// SAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: [[TMP1:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: ret half [[TMP1]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_post_dc.n to ptr), half 0xH3C00 seq_cst, align 2
+// SAFE-NEXT: ret half [[TMP0]]
//
// UNSAFE-LABEL: define dso_local half @test__Float16_post_dc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_post_dc.n to ptr), float 1.000000e+00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
-// UNSAFE-NEXT: store float [[TMP0]], ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: [[TMP1:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: ret half [[TMP1]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_post_dc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: ret half [[TMP0]]
//
_Float16 test__Float16_post_dc()
{
@@ -259,22 +235,18 @@ _Float16 test__Float16_post_dc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_dc.n to ptr), float 1.000000e+00 seq_cst, align 2
-// SAFE-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00
-// SAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: [[TMP2:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: ret half [[TMP2]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_dc.n to ptr), half 0xH3C00 seq_cst, align 2
+// SAFE-NEXT: [[TMP1:%.*]] = fsub half [[TMP0]], 0xH3C00
+// SAFE-NEXT: ret half [[TMP1]]
//
// UNSAFE-LABEL: define dso_local half @test__Float16_pre_dc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_dc.n to ptr), float 1.000000e+00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
-// UNSAFE-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00
-// UNSAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: [[TMP2:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: ret half [[TMP2]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_dc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: [[TMP1:%.*]] = fsub half [[TMP0]], 0xH3C00
+// UNSAFE-NEXT: ret half [[TMP1]]
//
_Float16 test__Float16_pre_dc()
{
@@ -287,22 +259,18 @@ _Float16 test__Float16_pre_dc()
// SAFE-NEXT: [[ENTRY:.*:]]
// SAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// SAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 2
-// SAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
-// SAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: [[TMP2:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// SAFE-NEXT: ret half [[TMP2]]
+// SAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_inc.n to ptr), half 0xH3C00 seq_cst, align 2
+// SAFE-NEXT: [[TMP1:%.*]] = fadd half [[TMP0]], 0xH3C00
+// SAFE-NEXT: ret half [[TMP1]]
//
// UNSAFE-LABEL: define dso_local half @test__Float16_pre_inc(
// UNSAFE-SAME: ) #[[ATTR0]] {
// UNSAFE-NEXT: [[ENTRY:.*:]]
// UNSAFE-NEXT: [[RETVAL:%.*]] = alloca half, align 2, addrspace(5)
// UNSAFE-NEXT: [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
-// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_inc.n to ptr), float 1.000000e+00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
-// UNSAFE-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00
-// UNSAFE-NEXT: store float [[TMP1]], ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: [[TMP2:%.*]] = load half, ptr [[RETVAL_ASCAST]], align 2
-// UNSAFE-NEXT: ret half [[TMP2]]
+// UNSAFE-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @test__Float16_pre_inc.n to ptr), half 0xH3C00 seq_cst, align 2, !amdgpu.no.fine.grained.memory [[META3]]
+// UNSAFE-NEXT: [[TMP1:%.*]] = fadd half [[TMP0]], 0xH3C00
+// UNSAFE-NEXT: ret half [[TMP1]]
//
_Float16 test__Float16_pre_inc()
{
diff --git a/clang/test/CodeGen/X86/x86-atomic-double.c b/clang/test/CodeGen/X86/x86-atomic-double.c
index 2354c89cc2b170..09c8f70c3db854 100644
--- a/clang/test/CodeGen/X86/x86-atomic-double.c
+++ b/clang/test/CodeGen/X86/x86-atomic-double.c
@@ -6,20 +6,14 @@
// X64-LABEL: define dso_local double @test_double_post_inc(
// X64-SAME: ) #[[ATTR0:[0-9]+]] {
// X64-NEXT: entry:
-// X64-NEXT: [[RETVAL:%.*]] = alloca double, align 8
-// X64-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_post_inc.n, float 1.000000e+00 seq_cst, align 8
-// X64-NEXT: store float [[TMP0]], ptr [[RETVAL]], align 8
-// X64-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL]], align 8
-// X64-NEXT: ret double [[TMP1]]
+// X64-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_post_inc.n, double 1.000000e+00 seq_cst, align 8
+// X64-NEXT: ret double [[TMP0]]
//
// X86-LABEL: define dso_local double @test_double_post_inc(
// X86-SAME: ) #[[ATTR0:[0-9]+]] {
// X86-NEXT: entry:
-// X86-NEXT: [[RETVAL:%.*]] = alloca double, align 4
-// X86-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_post_inc.n, float 1.000000e+00 seq_cst, align 8
-// X86-NEXT: store float [[TMP0]], ptr [[RETVAL]], align 4
-// X86-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL]], align 4
-// X86-NEXT: ret double [[TMP1]]
+// X86-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_post_inc.n, double 1.000000e+00 seq_cst, align 8
+// X86-NEXT: ret double [[TMP0]]
//
double test_double_post_inc()
{
@@ -30,20 +24,14 @@ double test_double_post_inc()
// X64-LABEL: define dso_local double @test_double_post_dc(
// X64-SAME: ) #[[ATTR0]] {
// X64-NEXT: entry:
-// X64-NEXT: [[RETVAL:%.*]] = alloca double, align 8
-// X64-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_post_dc.n, float 1.000000e+00 seq_cst, align 8
-// X64-NEXT: store float [[TMP0]], ptr [[RETVAL]], align 8
-// X64-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL]], align 8
-// X64-NEXT: ret double [[TMP1]]
+// X64-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_post_dc.n, double 1.000000e+00 seq_cst, align 8
+// X64-NEXT: ret double [[TMP0]]
//
// X86-LABEL: define dso_local double @test_double_post_dc(
// X86-SAME: ) #[[ATTR0]] {
// X86-NEXT: entry:
-// X86-NEXT: [[RETVAL:%.*]] = alloca double, align 4
-// X86-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_post_dc.n, float 1.000000e+00 seq_cst, align 8
-// X86-NEXT: store float [[TMP0]], ptr [[RETVAL]], align 4
-// X86-NEXT: [[TMP1:%.*]] = load double, ptr [[RETVAL]], align 4
-// X86-NEXT: ret double [[TMP1]]
+// X86-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_post_dc.n, double 1.000000e+00 seq_cst, align 8
+// X86-NEXT: ret double [[TMP0]]
//
double test_double_post_dc()
{
@@ -54,22 +42,16 @@ double test_double_post_dc()
// X64-LABEL: define dso_local double @test_double_pre_dc(
// X64-SAME: ) #[[ATTR0]] {
// X64-NEXT: entry:
-// X64-NEXT: [[RETVAL:%.*]] = alloca double, align 8
-// X64-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_pre_dc.n, float 1.000000e+00 seq_cst, align 8
-// X64-NEXT: [[TMP1:%.*]] = fsub fl...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/107075
More information about the cfe-commits
mailing list