Author: Yingwei Zheng Date: 2024-09-04T12:19:46+08:00 New Revision: 9fef09fd2918e7d8c357b98a9a798fe207941f73
URL: https://github.com/llvm/llvm-project/commit/9fef09fd2918e7d8c357b98a9a798fe207941f73 DIFF: https://github.com/llvm/llvm-project/commit/9fef09fd2918e7d8c357b98a9a798fe207941f73.diff LOG: [Clang][CodeGen] Fix type for atomic float incdec operators (#107075) `llvm::ConstantFP::get(llvm::LLVMContext&, APFloat(float))` always returns a f32 constant. Fix https://github.com/llvm/llvm-project/issues/107054. Added: Modified: clang/lib/CodeGen/CGExprScalar.cpp clang/test/CodeGen/AMDGPU/amdgpu-atomic-float.c clang/test/CodeGen/X86/x86-atomic-double.c clang/test/CodeGen/X86/x86-atomic-long_double.c Removed: ################################################################################ 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 float [[TMP0]], 1.000000e+00 -// X64-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 8 -// X64-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL]], align 8 -// X64-NEXT: ret double [[TMP2]] +// X64-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_pre_dc.n, double 1.000000e+00 seq_cst, align 8 +// X64-NEXT: [[TMP1:%.*]] = fsub double [[TMP0]], 1.000000e+00 +// X64-NEXT: ret double [[TMP1]] // // X86-LABEL: define dso_local double @test_double_pre_dc( // X86-SAME: ) #[[ATTR0]] { // X86-NEXT: entry: -// X86-NEXT: [[RETVAL:%.*]] = alloca double, align 4 -// X86-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_pre_dc.n, float 1.000000e+00 seq_cst, align 8 -// X86-NEXT: [[TMP1:%.*]] = fsub float [[TMP0]], 1.000000e+00 -// X86-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL]], align 4 -// X86-NEXT: ret double [[TMP2]] +// X86-NEXT: [[TMP0:%.*]] = atomicrmw fsub ptr @test_double_pre_dc.n, double 1.000000e+00 seq_cst, align 8 +// X86-NEXT: [[TMP1:%.*]] = fsub double [[TMP0]], 1.000000e+00 +// X86-NEXT: ret double [[TMP1]] // double test_double_pre_dc() { @@ -80,25 +62,43 @@ double test_double_pre_dc() // X64-LABEL: define dso_local double @test_double_pre_inc( // X64-SAME: ) #[[ATTR0]] { // X64-NEXT: entry: -// X64-NEXT: [[RETVAL:%.*]] = alloca double, align 8 -// X64-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_pre_inc.n, float 1.000000e+00 seq_cst, align 8 -// X64-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00 -// X64-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 8 -// X64-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL]], align 8 -// X64-NEXT: ret double [[TMP2]] +// X64-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_pre_inc.n, double 1.000000e+00 seq_cst, align 8 +// X64-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00 +// X64-NEXT: ret double [[TMP1]] // // X86-LABEL: define dso_local double @test_double_pre_inc( // X86-SAME: ) #[[ATTR0]] { // X86-NEXT: entry: -// X86-NEXT: [[RETVAL:%.*]] = alloca double, align 4 -// X86-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_pre_inc.n, float 1.000000e+00 seq_cst, align 8 -// X86-NEXT: [[TMP1:%.*]] = fadd float [[TMP0]], 1.000000e+00 -// X86-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP2:%.*]] = load double, ptr [[RETVAL]], align 4 -// X86-NEXT: ret double [[TMP2]] +// X86-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @test_double_pre_inc.n, double 1.000000e+00 seq_cst, align 8 +// X86-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00 +// X86-NEXT: ret double [[TMP1]] // double test_double_pre_inc() { static _Atomic double n; return ++n; } + +// X64-LABEL: define dso_local i32 @pr107054( +// X64-SAME: ) #[[ATTR0]] { +// X64-NEXT: entry: +// X64-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @pr107054.n, double 1.000000e+00 seq_cst, align 8 +// X64-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00 +// X64-NEXT: [[CMP:%.*]] = fcmp oeq double [[TMP1]], 1.000000e+00 +// X64-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +// X64-NEXT: ret i32 [[CONV]] +// +// X86-LABEL: define dso_local i32 @pr107054( +// X86-SAME: ) #[[ATTR0]] { +// X86-NEXT: entry: +// X86-NEXT: [[TMP0:%.*]] = atomicrmw fadd ptr @pr107054.n, double 1.000000e+00 seq_cst, align 8 +// X86-NEXT: [[TMP1:%.*]] = fadd double [[TMP0]], 1.000000e+00 +// X86-NEXT: [[CMP:%.*]] = fcmp oeq double [[TMP1]], 1.000000e+00 +// X86-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +// X86-NEXT: ret i32 [[CONV]] +// +int pr107054() +{ + static _Atomic double n; + return (++n) == 1; +} diff --git a/clang/test/CodeGen/X86/x86-atomic-long_double.c b/clang/test/CodeGen/X86/x86-atomic-long_double.c index 2c3f381f13511e..9c82784807daca 100644 --- a/clang/test/CodeGen/X86/x86-atomic-long_double.c +++ b/clang/test/CodeGen/X86/x86-atomic-long_double.c @@ -4,29 +4,60 @@ // X64-LABEL: define dso_local x86_fp80 @testinc( // X64-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0:[0-9]+]] { -// X64-NEXT: [[ENTRY:.*:]] -// X64-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ENTRY:.*]]: // X64-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 8 +// X64-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP3:%.*]] = alloca x86_fp80, align 16 // X64-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 8 // X64-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 8 -// X64-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr [[TMP0]], float 1.000000e+00 seq_cst, align 16 -// X64-NEXT: [[TMP2:%.*]] = fadd float [[TMP1]], 1.000000e+00 -// X64-NEXT: store float [[TMP2]], ptr [[RETVAL]], align 16 -// X64-NEXT: [[TMP3:%.*]] = load x86_fp80, ptr [[RETVAL]], align 16 -// X64-NEXT: ret x86_fp80 [[TMP3]] +// X64-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i128, ptr [[TMP0]] seq_cst, align 16 +// X64-NEXT: store i128 [[ATOMIC_LOAD]], ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: br label %[[ATOMIC_OP:.*]] +// X64: [[ATOMIC_OP]]: +// X64-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP8:%.*]], %[[ATOMIC_OP]] ] +// X64-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP2]], 0xK3FFF8000000000000000 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP1]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: [[TMP3:%.*]] = load i128, ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP2]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP4:%.*]] = load i128, ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP5:%.*]] = cmpxchg ptr [[TMP0]], i128 [[TMP3]], i128 [[TMP4]] seq_cst seq_cst, align 16 +// X64-NEXT: [[TMP6:%.*]] = extractvalue { i128, i1 } [[TMP5]], 0 +// X64-NEXT: [[TMP7:%.*]] = extractvalue { i128, i1 } [[TMP5]], 1 +// X64-NEXT: store i128 [[TMP6]], ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: [[TMP8]] = load x86_fp80, ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: br i1 [[TMP7]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X64: [[ATOMIC_CONT]]: +// X64-NEXT: ret x86_fp80 [[INC]] // // X86-LABEL: define dso_local x86_fp80 @testinc( // X86-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0:[0-9]+]] { -// X86-NEXT: [[ENTRY:.*:]] -// X86-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ENTRY:.*]]: // X86-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 4 +// X86-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 4 // X86-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 4 // X86-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 4 -// X86-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr [[TMP0]], float 1.000000e+00 seq_cst, align 4 -// X86-NEXT: [[TMP2:%.*]] = fadd float [[TMP1]], 1.000000e+00 -// X86-NEXT: store float [[TMP2]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP3:%.*]] = load x86_fp80, ptr [[RETVAL]], align 4 -// X86-NEXT: ret x86_fp80 [[TMP3]] +// X86-NEXT: call void @__atomic_load(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP]], i32 noundef 5) +// X86-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 4 +// X86-NEXT: br label %[[ATOMIC_OP:.*]] +// X86: [[ATOMIC_OP]]: +// X86-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP3:%.*]], %[[ATOMIC_OP]] ] +// X86-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP2]], 0xK3FFF8000000000000000 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP1]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP2]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 4 +// X86-NEXT: [[CALL:%.*]] = call zeroext i1 @__atomic_compare_exchange(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP1]], ptr noundef [[ATOMIC_TEMP2]], i32 noundef 5, i32 noundef 5) +// X86-NEXT: [[TMP3]] = load x86_fp80, ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: br i1 [[CALL]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X86: [[ATOMIC_CONT]]: +// X86-NEXT: ret x86_fp80 [[INC]] // long double testinc(_Atomic long double *addr) { @@ -35,27 +66,60 @@ long double testinc(_Atomic long double *addr) { // X64-LABEL: define dso_local x86_fp80 @testdec( // X64-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X64-NEXT: [[ENTRY:.*:]] -// X64-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ENTRY:.*]]: // X64-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 8 +// X64-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP3:%.*]] = alloca x86_fp80, align 16 // X64-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 8 // X64-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 8 -// X64-NEXT: [[TMP1:%.*]] = atomicrmw fsub ptr [[TMP0]], float 1.000000e+00 seq_cst, align 16 -// X64-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 16 -// X64-NEXT: [[TMP2:%.*]] = load x86_fp80, ptr [[RETVAL]], align 16 -// X64-NEXT: ret x86_fp80 [[TMP2]] +// X64-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i128, ptr [[TMP0]] seq_cst, align 16 +// X64-NEXT: store i128 [[ATOMIC_LOAD]], ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: br label %[[ATOMIC_OP:.*]] +// X64: [[ATOMIC_OP]]: +// X64-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP8:%.*]], %[[ATOMIC_OP]] ] +// X64-NEXT: [[DEC:%.*]] = fadd x86_fp80 [[TMP2]], 0xKBFFF8000000000000000 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP1]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: [[TMP3:%.*]] = load i128, ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP2]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[DEC]], ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP4:%.*]] = load i128, ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP5:%.*]] = cmpxchg ptr [[TMP0]], i128 [[TMP3]], i128 [[TMP4]] seq_cst seq_cst, align 16 +// X64-NEXT: [[TMP6:%.*]] = extractvalue { i128, i1 } [[TMP5]], 0 +// X64-NEXT: [[TMP7:%.*]] = extractvalue { i128, i1 } [[TMP5]], 1 +// X64-NEXT: store i128 [[TMP6]], ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: [[TMP8]] = load x86_fp80, ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: br i1 [[TMP7]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X64: [[ATOMIC_CONT]]: +// X64-NEXT: ret x86_fp80 [[TMP1]] // // X86-LABEL: define dso_local x86_fp80 @testdec( // X86-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X86-NEXT: [[ENTRY:.*:]] -// X86-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ENTRY:.*]]: // X86-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 4 +// X86-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 4 // X86-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 4 // X86-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 4 -// X86-NEXT: [[TMP1:%.*]] = atomicrmw fsub ptr [[TMP0]], float 1.000000e+00 seq_cst, align 4 -// X86-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP2:%.*]] = load x86_fp80, ptr [[RETVAL]], align 4 -// X86-NEXT: ret x86_fp80 [[TMP2]] +// X86-NEXT: call void @__atomic_load(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP]], i32 noundef 5) +// X86-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 4 +// X86-NEXT: br label %[[ATOMIC_OP:.*]] +// X86: [[ATOMIC_OP]]: +// X86-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP3:%.*]], %[[ATOMIC_OP]] ] +// X86-NEXT: [[DEC:%.*]] = fadd x86_fp80 [[TMP2]], 0xKBFFF8000000000000000 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP1]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP2]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[DEC]], ptr [[ATOMIC_TEMP2]], align 4 +// X86-NEXT: [[CALL:%.*]] = call zeroext i1 @__atomic_compare_exchange(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP1]], ptr noundef [[ATOMIC_TEMP2]], i32 noundef 5, i32 noundef 5) +// X86-NEXT: [[TMP3]] = load x86_fp80, ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: br i1 [[CALL]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X86: [[ATOMIC_CONT]]: +// X86-NEXT: ret x86_fp80 [[TMP1]] // long double testdec(_Atomic long double *addr) { @@ -175,29 +239,60 @@ long double testassign(_Atomic long double *addr) { // X64-LABEL: define dso_local x86_fp80 @test_volatile_inc( // X64-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X64-NEXT: [[ENTRY:.*:]] -// X64-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ENTRY:.*]]: // X64-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 8 +// X64-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP3:%.*]] = alloca x86_fp80, align 16 // X64-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 8 // X64-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 8 -// X64-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr [[TMP0]], float 1.000000e+00 seq_cst, align 16 -// X64-NEXT: [[TMP2:%.*]] = fadd float [[TMP1]], 1.000000e+00 -// X64-NEXT: store float [[TMP2]], ptr [[RETVAL]], align 16 -// X64-NEXT: [[TMP3:%.*]] = load x86_fp80, ptr [[RETVAL]], align 16 -// X64-NEXT: ret x86_fp80 [[TMP3]] +// X64-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic volatile i128, ptr [[TMP0]] seq_cst, align 16 +// X64-NEXT: store i128 [[ATOMIC_LOAD]], ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: br label %[[ATOMIC_OP:.*]] +// X64: [[ATOMIC_OP]]: +// X64-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP8:%.*]], %[[ATOMIC_OP]] ] +// X64-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP2]], 0xK3FFF8000000000000000 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP1]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: [[TMP3:%.*]] = load i128, ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP2]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP4:%.*]] = load i128, ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP5:%.*]] = cmpxchg volatile ptr [[TMP0]], i128 [[TMP3]], i128 [[TMP4]] seq_cst seq_cst, align 16 +// X64-NEXT: [[TMP6:%.*]] = extractvalue { i128, i1 } [[TMP5]], 0 +// X64-NEXT: [[TMP7:%.*]] = extractvalue { i128, i1 } [[TMP5]], 1 +// X64-NEXT: store i128 [[TMP6]], ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: [[TMP8]] = load x86_fp80, ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: br i1 [[TMP7]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X64: [[ATOMIC_CONT]]: +// X64-NEXT: ret x86_fp80 [[INC]] // // X86-LABEL: define dso_local x86_fp80 @test_volatile_inc( // X86-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X86-NEXT: [[ENTRY:.*:]] -// X86-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ENTRY:.*]]: // X86-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 4 +// X86-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 4 // X86-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 4 // X86-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 4 -// X86-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr [[TMP0]], float 1.000000e+00 seq_cst, align 4 -// X86-NEXT: [[TMP2:%.*]] = fadd float [[TMP1]], 1.000000e+00 -// X86-NEXT: store float [[TMP2]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP3:%.*]] = load x86_fp80, ptr [[RETVAL]], align 4 -// X86-NEXT: ret x86_fp80 [[TMP3]] +// X86-NEXT: call void @__atomic_load(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP]], i32 noundef 5) +// X86-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 4 +// X86-NEXT: br label %[[ATOMIC_OP:.*]] +// X86: [[ATOMIC_OP]]: +// X86-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP3:%.*]], %[[ATOMIC_OP]] ] +// X86-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP2]], 0xK3FFF8000000000000000 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP1]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP2]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 4 +// X86-NEXT: [[CALL:%.*]] = call zeroext i1 @__atomic_compare_exchange(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP1]], ptr noundef [[ATOMIC_TEMP2]], i32 noundef 5, i32 noundef 5) +// X86-NEXT: [[TMP3]] = load x86_fp80, ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: br i1 [[CALL]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X86: [[ATOMIC_CONT]]: +// X86-NEXT: ret x86_fp80 [[INC]] // long double test_volatile_inc(volatile _Atomic long double *addr) { return ++*addr; @@ -205,27 +300,60 @@ long double test_volatile_inc(volatile _Atomic long double *addr) { // X64-LABEL: define dso_local x86_fp80 @test_volatile_dec( // X64-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X64-NEXT: [[ENTRY:.*:]] -// X64-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ENTRY:.*]]: // X64-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 8 +// X64-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP3:%.*]] = alloca x86_fp80, align 16 // X64-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 8 // X64-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 8 -// X64-NEXT: [[TMP1:%.*]] = atomicrmw fsub ptr [[TMP0]], float 1.000000e+00 seq_cst, align 16 -// X64-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 16 -// X64-NEXT: [[TMP2:%.*]] = load x86_fp80, ptr [[RETVAL]], align 16 -// X64-NEXT: ret x86_fp80 [[TMP2]] +// X64-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic volatile i128, ptr [[TMP0]] seq_cst, align 16 +// X64-NEXT: store i128 [[ATOMIC_LOAD]], ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: br label %[[ATOMIC_OP:.*]] +// X64: [[ATOMIC_OP]]: +// X64-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP8:%.*]], %[[ATOMIC_OP]] ] +// X64-NEXT: [[DEC:%.*]] = fadd x86_fp80 [[TMP2]], 0xKBFFF8000000000000000 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP1]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: [[TMP3:%.*]] = load i128, ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP2]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[DEC]], ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP4:%.*]] = load i128, ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP5:%.*]] = cmpxchg volatile ptr [[TMP0]], i128 [[TMP3]], i128 [[TMP4]] seq_cst seq_cst, align 16 +// X64-NEXT: [[TMP6:%.*]] = extractvalue { i128, i1 } [[TMP5]], 0 +// X64-NEXT: [[TMP7:%.*]] = extractvalue { i128, i1 } [[TMP5]], 1 +// X64-NEXT: store i128 [[TMP6]], ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: [[TMP8]] = load x86_fp80, ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: br i1 [[TMP7]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X64: [[ATOMIC_CONT]]: +// X64-NEXT: ret x86_fp80 [[TMP1]] // // X86-LABEL: define dso_local x86_fp80 @test_volatile_dec( // X86-SAME: ptr noundef [[ADDR:%.*]]) #[[ATTR0]] { -// X86-NEXT: [[ENTRY:.*:]] -// X86-NEXT: [[RETVAL:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ENTRY:.*]]: // X86-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 4 +// X86-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 4 // X86-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR]], align 4 // X86-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR]], align 4 -// X86-NEXT: [[TMP1:%.*]] = atomicrmw fsub ptr [[TMP0]], float 1.000000e+00 seq_cst, align 4 -// X86-NEXT: store float [[TMP1]], ptr [[RETVAL]], align 4 -// X86-NEXT: [[TMP2:%.*]] = load x86_fp80, ptr [[RETVAL]], align 4 -// X86-NEXT: ret x86_fp80 [[TMP2]] +// X86-NEXT: call void @__atomic_load(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP]], i32 noundef 5) +// X86-NEXT: [[TMP1:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 4 +// X86-NEXT: br label %[[ATOMIC_OP:.*]] +// X86: [[ATOMIC_OP]]: +// X86-NEXT: [[TMP2:%.*]] = phi x86_fp80 [ [[TMP1]], %[[ENTRY]] ], [ [[TMP3:%.*]], %[[ATOMIC_OP]] ] +// X86-NEXT: [[DEC:%.*]] = fadd x86_fp80 [[TMP2]], 0xKBFFF8000000000000000 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP1]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[TMP2]], ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP2]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[DEC]], ptr [[ATOMIC_TEMP2]], align 4 +// X86-NEXT: [[CALL:%.*]] = call zeroext i1 @__atomic_compare_exchange(i32 noundef 12, ptr noundef [[TMP0]], ptr noundef [[ATOMIC_TEMP1]], ptr noundef [[ATOMIC_TEMP2]], i32 noundef 5, i32 noundef 5) +// X86-NEXT: [[TMP3]] = load x86_fp80, ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: br i1 [[CALL]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X86: [[ATOMIC_CONT]]: +// X86-NEXT: ret x86_fp80 [[TMP1]] // long double test_volatile_dec(volatile _Atomic long double *addr) { return (*addr)--; @@ -341,3 +469,64 @@ long double test_volatile_assign(volatile _Atomic long double *addr) { return *addr; } + +// X64-LABEL: define dso_local i32 @pr107054( +// X64-SAME: ) #[[ATTR0]] { +// X64-NEXT: [[ENTRY:.*]]: +// X64-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_TEMP3:%.*]] = alloca x86_fp80, align 16 +// X64-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i128, ptr @pr107054.n seq_cst, align 16 +// X64-NEXT: store i128 [[ATOMIC_LOAD]], ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 16 +// X64-NEXT: br label %[[ATOMIC_OP:.*]] +// X64: [[ATOMIC_OP]]: +// X64-NEXT: [[TMP1:%.*]] = phi x86_fp80 [ [[TMP0]], %[[ENTRY]] ], [ [[TMP7:%.*]], %[[ATOMIC_OP]] ] +// X64-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP1]], 0xK3FFF8000000000000000 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP1]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[TMP1]], ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: [[TMP2:%.*]] = load i128, ptr [[ATOMIC_TEMP1]], align 16 +// X64-NEXT: call void @llvm.memset.p0.i64(ptr align 16 [[ATOMIC_TEMP2]], i8 0, i64 16, i1 false) +// X64-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP3:%.*]] = load i128, ptr [[ATOMIC_TEMP2]], align 16 +// X64-NEXT: [[TMP4:%.*]] = cmpxchg ptr @pr107054.n, i128 [[TMP2]], i128 [[TMP3]] seq_cst seq_cst, align 16 +// X64-NEXT: [[TMP5:%.*]] = extractvalue { i128, i1 } [[TMP4]], 0 +// X64-NEXT: [[TMP6:%.*]] = extractvalue { i128, i1 } [[TMP4]], 1 +// X64-NEXT: store i128 [[TMP5]], ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: [[TMP7]] = load x86_fp80, ptr [[ATOMIC_TEMP3]], align 16 +// X64-NEXT: br i1 [[TMP6]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X64: [[ATOMIC_CONT]]: +// X64-NEXT: [[CMP:%.*]] = fcmp oeq x86_fp80 [[INC]], 0xK3FFF8000000000000000 +// X64-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +// X64-NEXT: ret i32 [[CONV]] +// +// X86-LABEL: define dso_local i32 @pr107054( +// X86-SAME: ) #[[ATTR0]] { +// X86-NEXT: [[ENTRY:.*]]: +// X86-NEXT: [[ATOMIC_TEMP:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP1:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: [[ATOMIC_TEMP2:%.*]] = alloca x86_fp80, align 4 +// X86-NEXT: call void @__atomic_load(i32 noundef 12, ptr noundef @pr107054.n, ptr noundef [[ATOMIC_TEMP]], i32 noundef 5) +// X86-NEXT: [[TMP0:%.*]] = load x86_fp80, ptr [[ATOMIC_TEMP]], align 4 +// X86-NEXT: br label %[[ATOMIC_OP:.*]] +// X86: [[ATOMIC_OP]]: +// X86-NEXT: [[TMP1:%.*]] = phi x86_fp80 [ [[TMP0]], %[[ENTRY]] ], [ [[TMP2:%.*]], %[[ATOMIC_OP]] ] +// X86-NEXT: [[INC:%.*]] = fadd x86_fp80 [[TMP1]], 0xK3FFF8000000000000000 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP1]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[TMP1]], ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: call void @llvm.memset.p0.i64(ptr align 4 [[ATOMIC_TEMP2]], i8 0, i64 12, i1 false) +// X86-NEXT: store x86_fp80 [[INC]], ptr [[ATOMIC_TEMP2]], align 4 +// X86-NEXT: [[CALL:%.*]] = call zeroext i1 @__atomic_compare_exchange(i32 noundef 12, ptr noundef @pr107054.n, ptr noundef [[ATOMIC_TEMP1]], ptr noundef [[ATOMIC_TEMP2]], i32 noundef 5, i32 noundef 5) +// X86-NEXT: [[TMP2]] = load x86_fp80, ptr [[ATOMIC_TEMP1]], align 4 +// X86-NEXT: br i1 [[CALL]], label %[[ATOMIC_CONT:.*]], label %[[ATOMIC_OP]] +// X86: [[ATOMIC_CONT]]: +// X86-NEXT: [[CMP:%.*]] = fcmp oeq x86_fp80 [[INC]], 0xK3FFF8000000000000000 +// X86-NEXT: [[CONV:%.*]] = zext i1 [[CMP]] to i32 +// X86-NEXT: ret i32 [[CONV]] +// +int pr107054() +{ + static _Atomic long double n; + return (++n) == 1; +} _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
