Index: llvm/include/llvm/Target/TargetLowering.h =================================================================== --- llvm/include/llvm/Target/TargetLowering.h +++ llvm/include/llvm/Target/TargetLowering.h @@ -2993,21 +2993,24 @@ /// Hooks for building estimates in place of slower divisions and square /// roots. - /// Return a reciprocal square root estimate value for the input operand. + /// Return either a square root or its reciprocal estimate value for the input + /// operand. /// \p Enabled is a ReciprocalEstimate enum with value either 'Unspecified' or /// 'Enabled' as set by a potential default override attribute. /// If \p RefinementSteps is 'Unspecified', the number of Newton-Raphson /// refinement iterations required to generate a sufficient (though not /// necessarily IEEE-754 compliant) estimate is returned in that parameter. /// The boolean UseOneConstNR output is used to select a Newton-Raphson - /// algorithm implementation that uses one constant or two constants. + /// algorithm implementation that uses either one or two constants. + /// The boolean Reciprocal is used to select whether the estimate is for the + /// square root of the input operand or the reciprocal of its square root. /// A target may choose to implement its own refinement within this function. /// If that's true, then return '0' as the number of RefinementSteps to avoid /// any further refinement of the estimate. /// An empty SDValue return means no estimate sequence can be created. - virtual SDValue getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, - int Enabled, int &RefinementSteps, - bool &UseOneConstNR) const { + virtual SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, + int Enabled, int &RefinementSteps, + bool &UseOneConstNR, bool Reciprocal) const { return SDValue(); } Index: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp =================================================================== --- llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -14858,6 +14858,12 @@ return S; } +/// Newton iteration for a function: F(X) is X_{i+1} = X_i - F(X_i)/F'(X_i) +/// For the reciprocal, we need to find the zero of the function: +/// F(X) = A X - 1 [which has a zero at X = 1/A] +/// => +/// X_{i+1} = X_i (2 - A X_i) = X_i + X_i (1 - A X_i) [this second form +/// does not require additional intermediate precision] SDValue DAGCombiner::BuildReciprocalEstimate(SDValue Op, SDNodeFlags *Flags) { if (Level >= AfterLegalizeDAG) return SDValue(); @@ -14877,19 +14883,13 @@ // refinement steps. int Iterations = TLI.getDivRefinementSteps(VT, MF); if (SDValue Est = TLI.getRecipEstimate(Op, DAG, Enabled, Iterations)) { + AddToWorklist(Est.getNode()); + if (Iterations) { - // Newton iteration for a function: F(X) is X_{i+1} = X_i - F(X_i)/F'(X_i) - // For the reciprocal, we need to find the zero of the function: - // F(X) = A X - 1 [which has a zero at X = 1/A] - // => - // X_{i+1} = X_i (2 - A X_i) = X_i + X_i (1 - A X_i) [this second form - // does not require additional intermediate precision] EVT VT = Op.getValueType(); SDLoc DL(Op); SDValue FPOne = DAG.getConstantFP(1.0, DL, VT); - AddToWorklist(Est.getNode()); - // Newton iterations: Est = Est + Est (1 - Arg * Est) for (int i = 0; i < Iterations; ++i) { SDValue NewEst = DAG.getNode(ISD::FMUL, DL, VT, Op, Est, Flags); @@ -15030,12 +15030,30 @@ bool UseOneConstNR = false; if (SDValue Est = - TLI.getRsqrtEstimate(Op, DAG, Enabled, Iterations, UseOneConstNR)) { + TLI.getSqrtEstimate(Op, DAG, Enabled, Iterations, UseOneConstNR, + Reciprocal)) { AddToWorklist(Est.getNode()); + if (Iterations) { Est = UseOneConstNR - ? buildSqrtNROneConst(Op, Est, Iterations, Flags, Reciprocal) - : buildSqrtNRTwoConst(Op, Est, Iterations, Flags, Reciprocal); + ? buildSqrtNROneConst(Op, Est, Iterations, Flags, Reciprocal) + : buildSqrtNRTwoConst(Op, Est, Iterations, Flags, Reciprocal); + + if (!Reciprocal) { + // Unfortunately, Est is now NaN if the input was exactly 0.0. + // Select out this case and force the answer to 0.0. + EVT VT = Op.getValueType(); + SDLoc DL(Op); + + SDValue FPZero = DAG.getConstantFP(0.0, DL, VT); + EVT CCVT = getSetCCResultType(VT); + SDValue ZeroCmp = DAG.getSetCC(DL, CCVT, Op, FPZero, ISD::SETEQ); + AddToWorklist(ZeroCmp.getNode()); + + Est = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT, DL, VT, + ZeroCmp, FPZero, Est); + AddToWorklist(Est.getNode()); + } } return Est; } @@ -15048,23 +15066,7 @@ } SDValue DAGCombiner::buildSqrtEstimate(SDValue Op, SDNodeFlags *Flags) { - SDValue Est = buildSqrtEstimateImpl(Op, Flags, false); - if (!Est) - return SDValue(); - - // Unfortunately, Est is now NaN if the input was exactly 0. - // Select out this case and force the answer to 0. - EVT VT = Est.getValueType(); - SDLoc DL(Op); - SDValue Zero = DAG.getConstantFP(0.0, DL, VT); - EVT CCVT = getSetCCResultType(VT); - SDValue ZeroCmp = DAG.getSetCC(DL, CCVT, Op, Zero, ISD::SETEQ); - AddToWorklist(ZeroCmp.getNode()); - - Est = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT, DL, VT, ZeroCmp, - Zero, Est); - AddToWorklist(Est.getNode()); - return Est; + return buildSqrtEstimateImpl(Op, Flags, false); } /// Return true if base is a frame index, which is known not to alias with Index: llvm/lib/Target/AArch64/AArch64ISelLowering.h =================================================================== --- llvm/lib/Target/AArch64/AArch64ISelLowering.h +++ llvm/lib/Target/AArch64/AArch64ISelLowering.h @@ -187,9 +187,9 @@ SMULL, UMULL, - // Reciprocal estimates. - FRECPE, - FRSQRTE, + // Reciprocal estimates and steps. + FRECPE, FRECPS, + FRSQRTE, FRSQRTS, // NEON Load/Store with post-increment base updates LD2post = ISD::FIRST_TARGET_MEMORY_OPCODE, @@ -534,8 +534,9 @@ SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor, SelectionDAG &DAG, std::vector *Created) const override; - SDValue getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, - int &ExtraSteps, bool &UseOneConst) const override; + SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, + int &ExtraSteps, bool &UseOneConst, + bool Reciprocal) const override; SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, int &ExtraSteps) const override; unsigned combineRepeatedFPDivisors() const override; Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp =================================================================== --- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp +++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp @@ -959,8 +959,10 @@ case AArch64ISD::ST4LANEpost: return "AArch64ISD::ST4LANEpost"; case AArch64ISD::SMULL: return "AArch64ISD::SMULL"; case AArch64ISD::UMULL: return "AArch64ISD::UMULL"; - case AArch64ISD::FRSQRTE: return "AArch64ISD::FRSQRTE"; case AArch64ISD::FRECPE: return "AArch64ISD::FRECPE"; + case AArch64ISD::FRECPS: return "AArch64ISD::FRECPS"; + case AArch64ISD::FRSQRTE: return "AArch64ISD::FRSQRTE"; + case AArch64ISD::FRSQRTS: return "AArch64ISD::FRSQRTS"; } return nullptr; } @@ -4632,15 +4634,43 @@ return SDValue(); } -SDValue AArch64TargetLowering::getRsqrtEstimate(SDValue Operand, - SelectionDAG &DAG, int Enabled, - int &ExtraSteps, - bool &UseOneConst) const { +SDValue AArch64TargetLowering::getSqrtEstimate(SDValue Operand, + SelectionDAG &DAG, int Enabled, + int &ExtraSteps, + bool &UseOneConst, + bool Reciprocal) const { if (Enabled == ReciprocalEstimate::Enabled || (Enabled == ReciprocalEstimate::Unspecified && Subtarget->useRSqrt())) if (SDValue Estimate = getEstimate(Subtarget, AArch64ISD::FRSQRTE, Operand, DAG, ExtraSteps)) { - UseOneConst = true; + SDLoc DL(Operand); + EVT VT = Operand.getValueType(); + + SDNodeFlags Flags; + Flags.setUnsafeAlgebra(true); + + // Newton reciprocal square root iteration: E * 0.5 * (3 - X * E^2) + // AArch64 reciprocal square root iteration instruction: 0.5 * (3 - M * N) + for (int i = ExtraSteps; i > 0; --i) { + SDValue Step = DAG.getNode(ISD::FMUL, DL, VT, Estimate, Estimate, + &Flags); + Step = DAG.getNode(AArch64ISD::FRSQRTS, DL, VT, Operand, Step, &Flags); + Estimate = DAG.getNode(ISD::FMUL, DL, VT, Estimate, Step, &Flags); + } + + if (!Reciprocal) { + EVT CCVT = getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), + VT); + SDValue FPZero = DAG.getConstantFP(0.0, DL, VT); + SDValue Eq = DAG.getSetCC(DL, CCVT, Operand, FPZero, ISD::SETEQ); + + Estimate = DAG.getNode(ISD::FMUL, DL, VT, Operand, Estimate, &Flags); + // Correct the result if the operand is 0.0. + Estimate = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT, DL, + VT, Eq, Operand, Estimate); + } + + ExtraSteps = 0; return Estimate; } @@ -4652,8 +4682,24 @@ int &ExtraSteps) const { if (Enabled == ReciprocalEstimate::Enabled) if (SDValue Estimate = getEstimate(Subtarget, AArch64ISD::FRECPE, Operand, - DAG, ExtraSteps)) + DAG, ExtraSteps)) { + SDLoc DL(Operand); + EVT VT = Operand.getValueType(); + + SDNodeFlags Flags; + Flags.setUnsafeAlgebra(true); + + // Newton reciprocal iteration: E * (2 - X * E) + // AArch64 reciprocal iteration instruction: (2 - M * N) + for (int i = ExtraSteps; i > 0; --i) { + SDValue Step = DAG.getNode(AArch64ISD::FRECPS, DL, VT, Operand, + Estimate, &Flags); + Estimate = DAG.getNode(ISD::FMUL, DL, VT, Estimate, Step, &Flags); + } + + ExtraSteps = 0; return Estimate; + } return SDValue(); } Index: llvm/lib/Target/AArch64/AArch64InstrInfo.td =================================================================== --- llvm/lib/Target/AArch64/AArch64InstrInfo.td +++ llvm/lib/Target/AArch64/AArch64InstrInfo.td @@ -287,7 +287,9 @@ def AArch64umull : SDNode<"AArch64ISD::UMULL", SDT_AArch64mull>; def AArch64frecpe : SDNode<"AArch64ISD::FRECPE", SDTFPUnaryOp>; +def AArch64frecps : SDNode<"AArch64ISD::FRECPS", SDTFPBinOp>; def AArch64frsqrte : SDNode<"AArch64ISD::FRSQRTE", SDTFPUnaryOp>; +def AArch64frsqrts : SDNode<"AArch64ISD::FRSQRTS", SDTFPBinOp>; def AArch64saddv : SDNode<"AArch64ISD::SADDV", SDT_AArch64UnaryVec>; def AArch64uaddv : SDNode<"AArch64ISD::UADDV", SDT_AArch64UnaryVec>; @@ -3422,6 +3424,17 @@ def : Pat<(v2f64 (AArch64frecpe (v2f64 FPR128:$Rn))), (FRECPEv2f64 FPR128:$Rn)>; +def : Pat<(f32 (AArch64frecps (f32 FPR32:$Rn), (f32 FPR32:$Rm))), + (FRECPS32 FPR32:$Rn, FPR32:$Rm)>; +def : Pat<(v2f32 (AArch64frecps (v2f32 V64:$Rn), (v2f32 V64:$Rm))), + (FRECPSv2f32 V64:$Rn, V64:$Rm)>; +def : Pat<(v4f32 (AArch64frecps (v4f32 FPR128:$Rn), (v4f32 FPR128:$Rm))), + (FRECPSv4f32 FPR128:$Rn, FPR128:$Rm)>; +def : Pat<(f64 (AArch64frecps (f64 FPR64:$Rn), (f64 FPR64:$Rm))), + (FRECPS64 FPR64:$Rn, FPR64:$Rm)>; +def : Pat<(v2f64 (AArch64frecps (v2f64 FPR128:$Rn), (v2f64 FPR128:$Rm))), + (FRECPSv2f64 FPR128:$Rn, FPR128:$Rm)>; + def : Pat<(f32 (int_aarch64_neon_frecpx (f32 FPR32:$Rn))), (FRECPXv1i32 FPR32:$Rn)>; def : Pat<(f64 (int_aarch64_neon_frecpx (f64 FPR64:$Rn))), @@ -3447,6 +3460,17 @@ def : Pat<(v2f64 (AArch64frsqrte (v2f64 FPR128:$Rn))), (FRSQRTEv2f64 FPR128:$Rn)>; +def : Pat<(f32 (AArch64frsqrts (f32 FPR32:$Rn), (f32 FPR32:$Rm))), + (FRSQRTS32 FPR32:$Rn, FPR32:$Rm)>; +def : Pat<(v2f32 (AArch64frsqrts (v2f32 V64:$Rn), (v2f32 V64:$Rm))), + (FRSQRTSv2f32 V64:$Rn, V64:$Rm)>; +def : Pat<(v4f32 (AArch64frsqrts (v4f32 FPR128:$Rn), (v4f32 FPR128:$Rm))), + (FRSQRTSv4f32 FPR128:$Rn, FPR128:$Rm)>; +def : Pat<(f64 (AArch64frsqrts (f64 FPR64:$Rn), (f64 FPR64:$Rm))), + (FRSQRTS64 FPR64:$Rn, FPR64:$Rm)>; +def : Pat<(v2f64 (AArch64frsqrts (v2f64 FPR128:$Rn), (v2f64 FPR128:$Rm))), + (FRSQRTSv2f64 FPR128:$Rn, FPR128:$Rm)>; + // If an integer is about to be converted to a floating point value, // just load it on the floating point unit. // Here are the patterns for 8 and 16-bits to float. Index: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h =================================================================== --- llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h +++ llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h @@ -164,9 +164,9 @@ bool isFsqrtCheap(SDValue Operand, SelectionDAG &DAG) const override { return true; } - SDValue getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, - int &RefinementSteps, - bool &UseOneConstNR) const override; + SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, + int &RefinementSteps, bool &UseOneConstNR, + bool Reciprocal) const override; SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, int &RefinementSteps) const override; Index: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp =================================================================== --- llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp +++ llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp @@ -2858,10 +2858,11 @@ return nullptr; } -SDValue AMDGPUTargetLowering::getRsqrtEstimate(SDValue Operand, - SelectionDAG &DAG, int Enabled, - int &RefinementSteps, - bool &UseOneConstNR) const { +SDValue AMDGPUTargetLowering::getSqrtEstimate(SDValue Operand, + SelectionDAG &DAG, int Enabled, + int &RefinementSteps, + bool &UseOneConstNR, + bool Reciprocal) const { EVT VT = Operand.getValueType(); if (VT == MVT::f32) { Index: llvm/lib/Target/PowerPC/PPCISelLowering.h =================================================================== --- llvm/lib/Target/PowerPC/PPCISelLowering.h +++ llvm/lib/Target/PowerPC/PPCISelLowering.h @@ -967,9 +967,9 @@ SDValue DAGCombineTruncBoolExt(SDNode *N, DAGCombinerInfo &DCI) const; SDValue combineFPToIntToFP(SDNode *N, DAGCombinerInfo &DCI) const; - SDValue getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, - int &RefinementSteps, - bool &UseOneConstNR) const override; + SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, + int &RefinementSteps, bool &UseOneConstNR, + bool Reciprocal) const override; SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, int &RefinementSteps) const override; unsigned combineRepeatedFPDivisors() const override; Index: llvm/lib/Target/PowerPC/PPCISelLowering.cpp =================================================================== --- llvm/lib/Target/PowerPC/PPCISelLowering.cpp +++ llvm/lib/Target/PowerPC/PPCISelLowering.cpp @@ -9633,9 +9633,10 @@ return RefinementSteps; } -SDValue PPCTargetLowering::getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, - int Enabled, int &RefinementSteps, - bool &UseOneConstNR) const { +SDValue PPCTargetLowering::getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, + int Enabled, int &RefinementSteps, + bool &UseOneConstNR, + bool Reciprocal) const { EVT VT = Operand.getValueType(); if ((VT == MVT::f32 && Subtarget.hasFRSQRTES()) || (VT == MVT::f64 && Subtarget.hasFRSQRTE()) || Index: llvm/lib/Target/X86/X86ISelLowering.h =================================================================== --- llvm/lib/Target/X86/X86ISelLowering.h +++ llvm/lib/Target/X86/X86ISelLowering.h @@ -1268,9 +1268,9 @@ bool isFsqrtCheap(SDValue Operand, SelectionDAG &DAG) const override; /// Use rsqrt* to speed up sqrt calculations. - SDValue getRsqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, - int &RefinementSteps, - bool &UseOneConstNR) const override; + SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, + int &RefinementSteps, bool &UseOneConstNR, + bool Reciprocal) const override; /// Use rcp* to speed up fdiv calculations. SDValue getRecipEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled, Index: llvm/lib/Target/X86/X86ISelLowering.cpp =================================================================== --- llvm/lib/Target/X86/X86ISelLowering.cpp +++ llvm/lib/Target/X86/X86ISelLowering.cpp @@ -15228,10 +15228,11 @@ /// The minimum architected relative accuracy is 2^-12. We need one /// Newton-Raphson step to have a good float result (24 bits of precision). -SDValue X86TargetLowering::getRsqrtEstimate(SDValue Op, - SelectionDAG &DAG, int Enabled, - int &RefinementSteps, - bool &UseOneConstNR) const { +SDValue X86TargetLowering::getSqrtEstimate(SDValue Op, + SelectionDAG &DAG, int Enabled, + int &RefinementSteps, + bool &UseOneConstNR, + bool Reciprocal) const { EVT VT = Op.getValueType(); // SSE1 has rsqrtss and rsqrtps. AVX adds a 256-bit variant for rsqrtps. Index: llvm/test/CodeGen/AArch64/recp-fastmath.ll =================================================================== --- llvm/test/CodeGen/AArch64/recp-fastmath.ll +++ llvm/test/CodeGen/AArch64/recp-fastmath.ll @@ -16,8 +16,8 @@ ; CHECK-LABEL: frecp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: frecpe -; CHECK-NEXT: fmov +; CHECK-NEXT: frecpe [[R:s[0-7]]] +; CHECK-NEXT: frecps {{s[0-7](, s[0-7])?}}, [[R]] } define <2 x float> @f2recp0(<2 x float> %x) #0 { @@ -36,8 +36,8 @@ ; CHECK-LABEL: f2recp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frecpe +; CHECK-NEXT: frecpe [[R:v[0-7]\.2s]] +; CHECK-NEXT: frecps {{v[0-7]\.2s(, v[0-7].2s)?}}, [[R]] } define <4 x float> @f4recp0(<4 x float> %x) #0 { @@ -56,8 +56,8 @@ ; CHECK-LABEL: f4recp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frecpe +; CHECK-NEXT: frecpe [[R:v[0-7]\.4s]] +; CHECK-NEXT: frecps {{v[0-7]\.4s(, v[0-7].4s)?}}, [[R]] } define <8 x float> @f8recp0(<8 x float> %x) #0 { @@ -77,9 +77,10 @@ ; CHECK-LABEL: f8recp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frecpe -; CHECK: frecpe +; CHECK-NEXT: frecpe [[RA:v[0-7]\.4s]] +; CHECK-NEXT: frecpe [[RB:v[0-7]\.4s]] +; CHECK-NEXT: frecps {{v[0-7]\.4s(, v[0-7].4s)?}}, [[RA]] +; CHECK: frecps {{v[0-7]\.4s(, v[0-7].4s)?}}, [[RB]] } define double @drecp0(double %x) #0 { @@ -98,8 +99,8 @@ ; CHECK-LABEL: drecp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: frecpe -; CHECK-NEXT: fmov +; CHECK-NEXT: frecpe [[R:d[0-7]]] +; CHECK-NEXT: frecps {{d[0-7](, d[0-7])?}}, [[R]] } define <2 x double> @d2recp0(<2 x double> %x) #0 { @@ -118,8 +119,8 @@ ; CHECK-LABEL: d2recp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frecpe +; CHECK-NEXT: frecpe [[R:v[0-7]\.2d]] +; CHECK-NEXT: frecps {{v[0-7]\.2d(, v[0-7].2d)?}}, [[R]] } define <4 x double> @d4recp0(<4 x double> %x) #0 { @@ -139,9 +140,10 @@ ; CHECK-LABEL: d4recp1: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frecpe -; CHECK: frecpe +; CHECK-NEXT: frecpe [[RA:v[0-7]\.2d]] +; CHECK-NEXT: frecpe [[RB:v[0-7]\.2d]] +; CHECK-NEXT: frecps {{v[0-7]\.2d(, v[0-7].2d)?}}, [[RA]] +; CHECK: frecps {{v[0-7]\.2d(, v[0-7].2d)?}}, [[RB]] } attributes #0 = { nounwind "unsafe-fp-math"="true" } Index: llvm/test/CodeGen/AArch64/sqrt-fastmath.ll =================================================================== --- llvm/test/CodeGen/AArch64/sqrt-fastmath.ll +++ llvm/test/CodeGen/AArch64/sqrt-fastmath.ll @@ -19,8 +19,10 @@ ; CHECK-LABEL: fsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:s[0-7]]] +; CHECK-NEXT: fmul [[RB:s[0-7]]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{s[0-7](, s[0-7])?}}, [[RB]] +; CHECK: fcmp s0, #0 } define <2 x float> @f2sqrt(<2 x float> %a) #0 { @@ -33,9 +35,10 @@ ; CHECK-LABEL: f2sqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: mov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2s]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.2s]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.2s(, v[0-7]\.2s)?}}, [[RB]] +; CHECK: fcmeq {{v[0-7]\.2s, v0\.2s}}, #0 } define <4 x float> @f4sqrt(<4 x float> %a) #0 { @@ -48,9 +51,10 @@ ; CHECK-LABEL: f4sqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: mov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]] +; CHECK: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0 } define <8 x float> @f8sqrt(<8 x float> %a) #0 { @@ -64,10 +68,10 @@ ; CHECK-LABEL: f8sqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: mov -; CHECK-NEXT: frsqrte -; CHECK: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]] +; CHECK: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]] +; CHECK: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]] +; CHECK: fcmeq {{v[0-7]\.4s, v[0-1]\.4s}}, #0 } define double @dsqrt(double %a) #0 { @@ -80,8 +84,10 @@ ; CHECK-LABEL: dsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:d[0-7]]] +; CHECK-NEXT: fmul [[RB:d[0-7]]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{d[0-7](, d[0-7])?}}, [[RB]] +; CHECK: fcmp d0, #0 } define <2 x double> @d2sqrt(<2 x double> %a) #0 { @@ -94,9 +100,10 @@ ; CHECK-LABEL: d2sqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: mov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]] +; CHECK: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0 } define <4 x double> @d4sqrt(<4 x double> %a) #0 { @@ -110,10 +117,10 @@ ; CHECK-LABEL: d4sqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: mov -; CHECK-NEXT: frsqrte -; CHECK: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]] +; CHECK: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]] +; CHECK: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]] +; CHECK: fcmeq {{v[0-7]\.2d, v[0-1]\.2d}}, #0 } define float @frsqrt(float %a) #0 { @@ -127,8 +134,10 @@ ; CHECK-LABEL: frsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:s[0-7]]] +; CHECK-NEXT: fmul [[RB:s[0-7]]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{s[0-7](, s[0-7])?}}, [[RB]] +; CHECK-NOT: fcmp {{s[0-7]}}, #0 } define <2 x float> @f2rsqrt(<2 x float> %a) #0 { @@ -142,8 +151,10 @@ ; CHECK-LABEL: f2rsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2s]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.2s]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.2s(, v[0-7]\.2s)?}}, [[RB]] +; CHECK-NOT: fcmeq {{v[0-7]\.2s, v0\.2s}}, #0 } define <4 x float> @f4rsqrt(<4 x float> %a) #0 { @@ -157,8 +168,10 @@ ; CHECK-LABEL: f4rsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]] +; CHECK-NOT: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0 } define <8 x float> @f8rsqrt(<8 x float> %a) #0 { @@ -173,9 +186,10 @@ ; CHECK-LABEL: f8rsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte -; CHECK: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]] +; CHECK: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]] +; CHECK: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]] +; CHECK-NOT: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0 } define double @drsqrt(double %a) #0 { @@ -189,8 +203,10 @@ ; CHECK-LABEL: drsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:d[0-7]]] +; CHECK-NEXT: fmul [[RB:d[0-7]]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{d[0-7](, d[0-7])?}}, [[RB]] +; CHECK-NOT: fcmp d0, #0 } define <2 x double> @d2rsqrt(<2 x double> %a) #0 { @@ -204,8 +220,10 @@ ; CHECK-LABEL: d2rsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]] +; CHECK-NEXT: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]] +; CHECK-NEXT: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]] +; CHECK-NOT: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0 } define <4 x double> @d4rsqrt(<4 x double> %a) #0 { @@ -220,9 +238,10 @@ ; CHECK-LABEL: d4rsqrt: ; CHECK-NEXT: BB#0 -; CHECK-NEXT: fmov -; CHECK-NEXT: frsqrte -; CHECK: frsqrte +; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]] +; CHECK: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]] +; CHECK: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]] +; CHECK-NOT: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0 } attributes #0 = { nounwind "unsafe-fp-math"="true" }