diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp @@ -65,35 +65,60 @@ case ISD::EXTRACT_VECTOR_ELT: R = SoftenFloatRes_EXTRACT_VECTOR_ELT(N, ResNo); break; case ISD::FABS: R = SoftenFloatRes_FABS(N); break; + case ISD::STRICT_FMINNUM: case ISD::FMINNUM: R = SoftenFloatRes_FMINNUM(N); break; + case ISD::STRICT_FMAXNUM: case ISD::FMAXNUM: R = SoftenFloatRes_FMAXNUM(N); break; + case ISD::STRICT_FADD: case ISD::FADD: R = SoftenFloatRes_FADD(N); break; case ISD::FCBRT: R = SoftenFloatRes_FCBRT(N); break; + case ISD::STRICT_FCEIL: case ISD::FCEIL: R = SoftenFloatRes_FCEIL(N); break; case ISD::FCOPYSIGN: R = SoftenFloatRes_FCOPYSIGN(N); break; + case ISD::STRICT_FCOS: case ISD::FCOS: R = SoftenFloatRes_FCOS(N); break; + case ISD::STRICT_FDIV: case ISD::FDIV: R = SoftenFloatRes_FDIV(N); break; + case ISD::STRICT_FEXP: case ISD::FEXP: R = SoftenFloatRes_FEXP(N); break; + case ISD::STRICT_FEXP2: case ISD::FEXP2: R = SoftenFloatRes_FEXP2(N); break; + case ISD::STRICT_FFLOOR: case ISD::FFLOOR: R = SoftenFloatRes_FFLOOR(N); break; + case ISD::STRICT_FLOG: case ISD::FLOG: R = SoftenFloatRes_FLOG(N); break; + case ISD::STRICT_FLOG2: case ISD::FLOG2: R = SoftenFloatRes_FLOG2(N); break; + case ISD::STRICT_FLOG10: case ISD::FLOG10: R = SoftenFloatRes_FLOG10(N); break; + case ISD::STRICT_FMA: case ISD::FMA: R = SoftenFloatRes_FMA(N); break; + case ISD::STRICT_FMUL: case ISD::FMUL: R = SoftenFloatRes_FMUL(N); break; + case ISD::STRICT_FNEARBYINT: case ISD::FNEARBYINT: R = SoftenFloatRes_FNEARBYINT(N); break; case ISD::FNEG: R = SoftenFloatRes_FNEG(N); break; + case ISD::STRICT_FP_EXTEND: case ISD::FP_EXTEND: R = SoftenFloatRes_FP_EXTEND(N); break; case ISD::FP_ROUND: R = SoftenFloatRes_FP_ROUND(N); break; case ISD::FP16_TO_FP: R = SoftenFloatRes_FP16_TO_FP(N); break; + case ISD::STRICT_FPOW: case ISD::FPOW: R = SoftenFloatRes_FPOW(N); break; + case ISD::STRICT_FPOWI: case ISD::FPOWI: R = SoftenFloatRes_FPOWI(N); break; + case ISD::STRICT_FREM: case ISD::FREM: R = SoftenFloatRes_FREM(N); break; + case ISD::STRICT_FRINT: case ISD::FRINT: R = SoftenFloatRes_FRINT(N); break; + case ISD::STRICT_FROUND: case ISD::FROUND: R = SoftenFloatRes_FROUND(N); break; + case ISD::STRICT_FSIN: case ISD::FSIN: R = SoftenFloatRes_FSIN(N); break; + case ISD::STRICT_FSQRT: case ISD::FSQRT: R = SoftenFloatRes_FSQRT(N); break; + case ISD::STRICT_FSUB: case ISD::FSUB: R = SoftenFloatRes_FSUB(N); break; + case ISD::STRICT_FTRUNC: case ISD::FTRUNC: R = SoftenFloatRes_FTRUNC(N); break; case ISD::LOAD: R = SoftenFloatRes_LOAD(N); break; case ISD::ATOMIC_SWAP: R = BitcastToInt_ATOMIC_SWAP(N); break; @@ -113,25 +138,43 @@ } SDValue DAGTypeLegalizer::SoftenFloatRes_Unary(SDNode *N, RTLIB::Libcall LC) { + bool IsStrict = N->isStrictFPOpcode(); EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - assert(N->getNumOperands() == 1 && "Unexpected number of operands!"); - SDValue Op = GetSoftenedFloat(N->getOperand(0)); + unsigned Offset = IsStrict ? 1 : 0; + assert(N->getNumOperands() == (1 + Offset) && + "Unexpected number of operands!"); + SDValue Op = GetSoftenedFloat(N->getOperand(0 + Offset)); + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(0 + Offset).getValueType(); CallOptions.setTypeListBeforeSoften(OpVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, LC, NVT, Op, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) + ReplaceValueWith(SDValue(N, 1), Tmp.second); + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatRes_Binary(SDNode *N, RTLIB::Libcall LC) { + bool IsStrict = N->isStrictFPOpcode(); EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - assert(N->getNumOperands() == 2 && "Unexpected number of operands!"); - SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)), - GetSoftenedFloat(N->getOperand(1)) }; + unsigned Offset = IsStrict ? 1 : 0; + assert(N->getNumOperands() == (2 + Offset) && + "Unexpected number of operands!"); + SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0 + Offset)), + GetSoftenedFloat(N->getOperand(1 + Offset)) }; + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpsVT[2] = { N->getOperand(0).getValueType(), - N->getOperand(1).getValueType() }; + EVT OpsVT[2] = { N->getOperand(0 + Offset).getValueType(), + N->getOperand(1 + Offset).getValueType() }; CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, NVT, Ops, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, LC, NVT, Ops, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) + ReplaceValueWith(SDValue(N, 1), Tmp.second); + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatRes_BITCAST(SDNode *N) { @@ -368,22 +411,29 @@ } SDValue DAGTypeLegalizer::SoftenFloatRes_FMA(SDNode *N) { + bool IsStrict = N->isStrictFPOpcode(); EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - SDValue Ops[3] = { GetSoftenedFloat(N->getOperand(0)), - GetSoftenedFloat(N->getOperand(1)), - GetSoftenedFloat(N->getOperand(2)) }; + unsigned Offset = IsStrict ? 1 : 0; + SDValue Ops[3] = { GetSoftenedFloat(N->getOperand(0 + Offset)), + GetSoftenedFloat(N->getOperand(1 + Offset)), + GetSoftenedFloat(N->getOperand(2 + Offset)) }; + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpsVT[3] = { N->getOperand(0).getValueType(), - N->getOperand(1).getValueType(), - N->getOperand(2).getValueType() }; + EVT OpsVT[3] = { N->getOperand(0 + Offset).getValueType(), + N->getOperand(1 + Offset).getValueType(), + N->getOperand(2 + Offset).getValueType() }; CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0), - RTLIB::FMA_F32, - RTLIB::FMA_F64, - RTLIB::FMA_F80, - RTLIB::FMA_F128, - RTLIB::FMA_PPCF128), - NVT, Ops, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, + GetFPLibCall(N->getValueType(0), + RTLIB::FMA_F32, + RTLIB::FMA_F64, + RTLIB::FMA_F80, + RTLIB::FMA_F128, + RTLIB::FMA_PPCF128), + NVT, Ops, CallOptions, SDLoc(N), Chain); + if (IsStrict) + ReplaceValueWith(SDValue(N, 1), Tmp.second); + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatRes_FMUL(SDNode *N) { @@ -430,14 +480,24 @@ } SDValue DAGTypeLegalizer::SoftenFloatRes_FP_EXTEND(SDNode *N) { + bool IsStrict = N->isStrictFPOpcode(); EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - SDValue Op = N->getOperand(0); + SDValue Op = N->getOperand(IsStrict ? 1 : 0); + + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); // There's only a libcall for f16 -> f32, so proceed in two stages. Also, it's // entirely possible for both f16 and f32 to be legal, so use the fully // hard-float FP_EXTEND rather than FP16_TO_FP. if (Op.getValueType() == MVT::f16 && N->getValueType(0) != MVT::f32) { - Op = DAG.getNode(ISD::FP_EXTEND, SDLoc(N), MVT::f32, Op); + if (IsStrict) { + Op = DAG.getNode(ISD::STRICT_FP_EXTEND, SDLoc(N), + { MVT::f32, MVT::Other }, { Chain, Op }); + Chain = Op.getValue(1); + } else { + Op = DAG.getNode(ISD::FP_EXTEND, SDLoc(N), MVT::f32, Op); + } + if (getTypeAction(MVT::f32) == TargetLowering::TypeSoftenFloat) AddToWorklist(Op.getNode()); } @@ -456,7 +516,12 @@ TargetLowering::MakeLibCallOptions CallOptions; EVT OpsVT[1] = { N->getOperand(0).getValueType() }; CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, LC, NVT, Op, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) + ReplaceValueWith(SDValue(N, 1), Tmp.second); + return Tmp.first; } // FIXME: Should we just use 'normal' FP_EXTEND / FP_TRUNC instead of special @@ -505,7 +570,9 @@ } SDValue DAGTypeLegalizer::SoftenFloatRes_FPOWI(SDNode *N) { - assert(N->getOperand(1).getValueType() == MVT::i32 && + bool IsStrict = N->isStrictFPOpcode(); + unsigned Offset = IsStrict ? 1 : 0; + assert(N->getOperand(1 + Offset).getValueType() == MVT::i32 && "Unsupported power type!"); RTLIB::Libcall LC = GetFPLibCall(N->getValueType(0), RTLIB::POWI_F32, @@ -521,12 +588,19 @@ } EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)), N->getOperand(1) }; + SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0 + Offset)), + N->getOperand(1 + Offset) }; + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpsVT[2] = { N->getOperand(0).getValueType(), - N->getOperand(1).getValueType() }; + EVT OpsVT[2] = { N->getOperand(0 + Offset).getValueType(), + N->getOperand(1 + Offset).getValueType() }; CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, NVT, Ops, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, LC, NVT, Ops, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) + ReplaceValueWith(SDValue(N, 1), Tmp.second); + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatRes_FREM(SDNode *N) { @@ -718,12 +792,17 @@ case ISD::BR_CC: Res = SoftenFloatOp_BR_CC(N); break; case ISD::FP_EXTEND: Res = SoftenFloatOp_FP_EXTEND(N); break; case ISD::FP_TO_FP16: // Same as FP_ROUND for softening purposes + case ISD::STRICT_FP_ROUND: case ISD::FP_ROUND: Res = SoftenFloatOp_FP_ROUND(N); break; case ISD::FP_TO_SINT: case ISD::FP_TO_UINT: Res = SoftenFloatOp_FP_TO_XINT(N); break; + case ISD::STRICT_LROUND: case ISD::LROUND: Res = SoftenFloatOp_LROUND(N); break; + case ISD::STRICT_LLROUND: case ISD::LLROUND: Res = SoftenFloatOp_LLROUND(N); break; + case ISD::STRICT_LRINT: case ISD::LRINT: Res = SoftenFloatOp_LRINT(N); break; + case ISD::STRICT_LLRINT: case ISD::LLRINT: Res = SoftenFloatOp_LLRINT(N); break; case ISD::SELECT_CC: Res = SoftenFloatOp_SELECT_CC(N); break; case ISD::SETCC: Res = SoftenFloatOp_SETCC(N); break; @@ -774,20 +853,31 @@ SDValue DAGTypeLegalizer::SoftenFloatOp_FP_ROUND(SDNode *N) { // We actually deal with the partially-softened FP_TO_FP16 node too, which // returns an i16 so doesn't meet the constraints necessary for FP_ROUND. - assert(N->getOpcode() == ISD::FP_ROUND || N->getOpcode() == ISD::FP_TO_FP16); + assert(N->getOpcode() == ISD::FP_ROUND || N->getOpcode() == ISD::FP_TO_FP16 || + N->getOpcode() == ISD::STRICT_FP_ROUND); - EVT SVT = N->getOperand(0).getValueType(); + bool IsStrict = N->isStrictFPOpcode(); + SDValue Op = N->getOperand(IsStrict ? 1 : 0); + EVT SVT = Op.getValueType(); EVT RVT = N->getValueType(0); EVT FloatRVT = N->getOpcode() == ISD::FP_TO_FP16 ? MVT::f16 : RVT; RTLIB::Libcall LC = RTLIB::getFPROUND(SVT, FloatRVT); assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_ROUND libcall"); - SDValue Op = GetSoftenedFloat(N->getOperand(0)); + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); + Op = GetSoftenedFloat(Op); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpsVT[1] = { N->getOperand(0).getValueType() }; - CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, RVT, Op, CallOptions, SDLoc(N)).first; + CallOptions.setTypeListBeforeSoften(SVT, RVT, true); + std::pair Tmp = TLI.makeLibCall(DAG, LC, RVT, Op, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) { + ReplaceValueWith(SDValue(N, 1), Tmp.second); + ReplaceValueWith(SDValue(N, 0), Tmp.first); + return SDValue(); + } + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatOp_BR_CC(SDNode *N) { @@ -947,15 +1037,27 @@ SDValue DAGTypeLegalizer::SoftenFloatOp_Unary(SDNode *N, RTLIB::Libcall LC) { EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); - SDValue Op = GetSoftenedFloat(N->getOperand(0)); + bool IsStrict = N->isStrictFPOpcode(); + unsigned Offset = IsStrict ? 1 : 0; + SDValue Op = GetSoftenedFloat(N->getOperand(0 + Offset)); + SDValue Chain = IsStrict ? N->getOperand(0) : SDValue(); TargetLowering::MakeLibCallOptions CallOptions; - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(0 + Offset).getValueType(); CallOptions.setTypeListBeforeSoften(OpVT, N->getValueType(0), true); - return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first; + std::pair Tmp = TLI.makeLibCall(DAG, LC, NVT, Op, + CallOptions, SDLoc(N), + Chain); + if (IsStrict) { + ReplaceValueWith(SDValue(N, 1), Tmp.second); + ReplaceValueWith(SDValue(N, 0), Tmp.first); + return SDValue(); + } + + return Tmp.first; } SDValue DAGTypeLegalizer::SoftenFloatOp_LROUND(SDNode *N) { - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType(); return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT, RTLIB::LROUND_F32, RTLIB::LROUND_F64, @@ -965,7 +1067,7 @@ } SDValue DAGTypeLegalizer::SoftenFloatOp_LLROUND(SDNode *N) { - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType(); return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT, RTLIB::LLROUND_F32, RTLIB::LLROUND_F64, @@ -975,7 +1077,7 @@ } SDValue DAGTypeLegalizer::SoftenFloatOp_LRINT(SDNode *N) { - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType(); return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT, RTLIB::LRINT_F32, RTLIB::LRINT_F64, @@ -985,7 +1087,7 @@ } SDValue DAGTypeLegalizer::SoftenFloatOp_LLRINT(SDNode *N) { - EVT OpVT = N->getOperand(0).getValueType(); + EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType(); return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT, RTLIB::LLRINT_F32, RTLIB::LLRINT_F64, diff --git a/llvm/test/CodeGen/X86/fp128-libcalls-strict.ll b/llvm/test/CodeGen/X86/fp128-libcalls-strict.ll --- a/llvm/test/CodeGen/X86/fp128-libcalls-strict.ll +++ b/llvm/test/CodeGen/X86/fp128-libcalls-strict.ll @@ -1,10 +1,13 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -O2 -mtriple=x86_64-linux-android -mattr=+mmx \ +; RUN: llc < %s -O2 -mtriple=x86_64-linux-android \ ; RUN: -enable-legalize-types-checking \ ; RUN: -disable-strictnode-mutation | FileCheck %s -; RUN: llc < %s -O2 -mtriple=x86_64-linux-gnu -mattr=+mmx \ +; RUN: llc < %s -O2 -mtriple=x86_64-linux-gnu \ ; RUN: -enable-legalize-types-checking \ ; RUN: -disable-strictnode-mutation | FileCheck %s +; RUN: llc < %s -O2 -mtriple=i686-linux-gnu -mattr=+sse2 \ +; RUN: -enable-legalize-types-checking \ +; RUN: -disable-strictnode-mutation | FileCheck %s --check-prefix=X86 ; Check all soft floating point library function calls. @@ -15,6 +18,39 @@ ; CHECK-NEXT: callq __addtf3 ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: add: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll __addtf3 +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %add = call fp128 @llvm.experimental.constrained.fadd.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %add @@ -27,6 +63,39 @@ ; CHECK-NEXT: callq __subtf3 ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: sub: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll __subtf3 +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %sub = call fp128 @llvm.experimental.constrained.fsub.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %sub @@ -39,6 +108,39 @@ ; CHECK-NEXT: callq __multf3 ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: mul: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll __multf3 +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %mul = call fp128 @llvm.experimental.constrained.fmul.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %mul @@ -51,6 +153,39 @@ ; CHECK-NEXT: callq __divtf3 ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: div: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll __divtf3 +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %div = call fp128 @llvm.experimental.constrained.fdiv.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %div @@ -63,6 +198,43 @@ ; CHECK-NEXT: callq fmal ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: fma: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll fmal +; X86-NEXT: addl $60, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %fma = call fp128 @llvm.experimental.constrained.fma.f128(fp128 %x, fp128 %y, fp128 %z, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %fma @@ -75,6 +247,39 @@ ; CHECK-NEXT: callq fmodl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: frem: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll fmodl +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %div = call fp128 @llvm.experimental.constrained.frem.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %div @@ -87,6 +292,35 @@ ; CHECK-NEXT: callq ceill ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: ceil: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll ceill +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %ceil = call fp128 @llvm.experimental.constrained.ceil.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %ceil @@ -99,6 +333,35 @@ ; CHECK-NEXT: callq cosl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: cos: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll cosl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %cos = call fp128 @llvm.experimental.constrained.cos.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %cos @@ -111,6 +374,35 @@ ; CHECK-NEXT: callq expl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: exp: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll expl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %exp = call fp128 @llvm.experimental.constrained.exp.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %exp @@ -123,6 +415,35 @@ ; CHECK-NEXT: callq exp2l ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: exp2: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll exp2l +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %exp2 = call fp128 @llvm.experimental.constrained.exp2.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %exp2 @@ -135,6 +456,35 @@ ; CHECK-NEXT: callq floorl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: floor: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll floorl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %floor = call fp128 @llvm.experimental.constrained.floor.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %floor @@ -147,6 +497,35 @@ ; CHECK-NEXT: callq logl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: log: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll logl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %log = call fp128 @llvm.experimental.constrained.log.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %log @@ -159,6 +538,35 @@ ; CHECK-NEXT: callq log10l ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: log10: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll log10l +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %log10 = call fp128 @llvm.experimental.constrained.log10.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %log10 @@ -171,6 +579,35 @@ ; CHECK-NEXT: callq log2l ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: log2: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll log2l +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %log2 = call fp128 @llvm.experimental.constrained.log2.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %log2 @@ -183,6 +620,39 @@ ; CHECK-NEXT: callq fmaxl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: maxnum: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll fmaxl +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %maxnum = call fp128 @llvm.experimental.constrained.maxnum.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %maxnum @@ -195,6 +665,39 @@ ; CHECK-NEXT: callq fminl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: minnum: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll fminl +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %minnum = call fp128 @llvm.experimental.constrained.minnum.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %minnum @@ -207,6 +710,35 @@ ; CHECK-NEXT: callq nearbyintl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: nearbyint: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll nearbyintl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %nearbyint = call fp128 @llvm.experimental.constrained.nearbyint.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %nearbyint @@ -219,6 +751,39 @@ ; CHECK-NEXT: callq powl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: pow: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll powl +; X86-NEXT: addl $44, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %pow = call fp128 @llvm.experimental.constrained.pow.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %pow @@ -231,6 +796,36 @@ ; CHECK-NEXT: callq __powitf2 ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: powi: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $8, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll __powitf2 +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %powi = call fp128 @llvm.experimental.constrained.powi.f128(fp128 %x, i32 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %powi @@ -243,6 +838,35 @@ ; CHECK-NEXT: callq rintl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: rint: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll rintl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %rint = call fp128 @llvm.experimental.constrained.rint.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %rint @@ -255,6 +879,35 @@ ; CHECK-NEXT: callq roundl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: round: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll roundl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %round = call fp128 @llvm.experimental.constrained.round.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %round @@ -267,6 +920,35 @@ ; CHECK-NEXT: callq sinl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: sin: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll sinl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %sin = call fp128 @llvm.experimental.constrained.sin.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %sin @@ -279,6 +961,35 @@ ; CHECK-NEXT: callq sqrtl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: sqrt: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll sqrtl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %sqrt = call fp128 @llvm.experimental.constrained.sqrt.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %sqrt @@ -291,6 +1002,35 @@ ; CHECK-NEXT: callq truncl ; CHECK-NEXT: popq %rax ; CHECK-NEXT: retq +; +; X86-LABEL: trunc: +; X86: # %bb.0: # %entry +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: subl $20, %esp +; X86-NEXT: movl {{[0-9]+}}(%esp), %esi +; X86-NEXT: subl $12, %esp +; X86-NEXT: leal {{[0-9]+}}(%esp), %eax +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl %eax +; X86-NEXT: calll truncl +; X86-NEXT: addl $28, %esp +; X86-NEXT: movl (%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edi +; X86-NEXT: movl %edi, 8(%esi) +; X86-NEXT: movl %edx, 12(%esi) +; X86-NEXT: movl %eax, (%esi) +; X86-NEXT: movl %ecx, 4(%esi) +; X86-NEXT: movl %esi, %eax +; X86-NEXT: addl $20, %esp +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: retl $4 entry: %trunc = call fp128 @llvm.experimental.constrained.trunc.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret fp128 %trunc @@ -303,6 +1043,17 @@ ; CHECK-NEXT: callq lrintl ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq +; +; X86-LABEL: lrint: +; X86: # %bb.0: # %entry +; X86-NEXT: subl $12, %esp +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: calll lrintl +; X86-NEXT: addl $28, %esp +; X86-NEXT: retl entry: %rint = call i32 @llvm.experimental.constrained.lrint.i32.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret i32 %rint @@ -315,6 +1066,17 @@ ; CHECK-NEXT: callq llrintl ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq +; +; X86-LABEL: llrint: +; X86: # %bb.0: # %entry +; X86-NEXT: subl $12, %esp +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: calll llrintl +; X86-NEXT: addl $28, %esp +; X86-NEXT: retl entry: %rint = call i64 @llvm.experimental.constrained.llrint.i64.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0 ret i64 %rint @@ -327,6 +1089,17 @@ ; CHECK-NEXT: callq lroundl ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq +; +; X86-LABEL: lround: +; X86: # %bb.0: # %entry +; X86-NEXT: subl $12, %esp +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: calll lroundl +; X86-NEXT: addl $28, %esp +; X86-NEXT: retl entry: %round = call i32 @llvm.experimental.constrained.lround.i32.f128(fp128 %x, metadata !"fpexcept.strict") #0 ret i32 %round @@ -339,6 +1112,17 @@ ; CHECK-NEXT: callq llroundl ; CHECK-NEXT: popq %rcx ; CHECK-NEXT: retq +; +; X86-LABEL: llround: +; X86: # %bb.0: # %entry +; X86-NEXT: subl $12, %esp +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: pushl {{[0-9]+}}(%esp) +; X86-NEXT: calll llroundl +; X86-NEXT: addl $28, %esp +; X86-NEXT: retl entry: %round = call i64 @llvm.experimental.constrained.llround.i64.f128(fp128 %x, metadata !"fpexcept.strict") #0 ret i64 %round