Index: llvm/trunk/include/llvm/CodeGen/CommandFlags.h =================================================================== --- llvm/trunk/include/llvm/CodeGen/CommandFlags.h +++ llvm/trunk/include/llvm/CodeGen/CommandFlags.h @@ -27,7 +27,6 @@ #include "llvm/Support/Host.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetOptions.h" -#include "llvm/Target/TargetRecip.h" #include using namespace llvm; @@ -201,12 +200,6 @@ "Only fuse FP ops when the result won't be affected."), clEnumValEnd)); -cl::list -ReciprocalOps("recip", - cl::CommaSeparated, - cl::desc("Choose reciprocal operation types and parameters."), - cl::value_desc("all,none,default,divf,!vec-sqrtd,vec-divd:0,sqrt:9...")); - cl::opt DontPlaceZerosInBSS("nozero-initialized-in-bss", cl::desc("Don't place zero-initialized symbols into bss section"), @@ -305,7 +298,6 @@ TargetOptions Options; Options.LessPreciseFPMADOption = EnableFPMAD; Options.AllowFPOpFusion = FuseFPOps; - Options.Reciprocals = TargetRecip(ReciprocalOps); Options.UnsafeFPMath = EnableUnsafeFPMath; Options.NoInfsFPMath = EnableNoInfsFPMath; Options.NoNaNsFPMath = EnableNoNaNsFPMath; Index: llvm/trunk/include/llvm/Target/TargetLowering.h =================================================================== --- llvm/trunk/include/llvm/Target/TargetLowering.h +++ llvm/trunk/include/llvm/Target/TargetLowering.h @@ -61,6 +61,7 @@ class MCSymbol; template class SmallVectorImpl; class DataLayout; + struct TargetRecip; class TargetRegisterClass; class TargetLibraryInfo; class TargetLoweringObjectFile; @@ -541,6 +542,12 @@ } } + /// Return the reciprocal estimate code generation preferences for this target + /// after potentially overriding settings using the function's attributes. + /// FIXME: Like all unsafe-math target settings, this should really be an + /// instruction-level attribute/metadata/FMF. + TargetRecip getTargetRecipForFunc(MachineFunction &MF) const; + /// Vector types are broken down into some number of legal first class types. /// For example, EVT::v8f32 maps to 2 EVT::v4f32 with Altivec or SSE1, or 8 /// promoted EVT::f64 values with the X86 FP stack. Similarly, EVT::v2i64 @@ -2174,6 +2181,7 @@ /// sequence of memory operands that is recognized by PrologEpilogInserter. MachineBasicBlock *emitPatchPoint(MachineInstr &MI, MachineBasicBlock *MBB) const; + TargetRecip ReciprocalEstimates; }; /// This class defines information used to lower LLVM code to legal SelectionDAG Index: llvm/trunk/include/llvm/Target/TargetOptions.h =================================================================== --- llvm/trunk/include/llvm/Target/TargetOptions.h +++ llvm/trunk/include/llvm/Target/TargetOptions.h @@ -111,7 +111,7 @@ DataSections(false), UniqueSectionNames(true), TrapUnreachable(false), EmulatedTLS(false), EnableIPRA(false), FloatABIType(FloatABI::Default), - AllowFPOpFusion(FPOpFusion::Standard), Reciprocals(TargetRecip()), + AllowFPOpFusion(FPOpFusion::Standard), JTType(JumpTable::Single), ThreadModel(ThreadModel::POSIX), EABIVersion(EABI::Default), DebuggerTuning(DebuggerKind::Default), FPDenormalMode(FPDenormal::IEEE), @@ -252,9 +252,6 @@ /// the value of this option. FPOpFusion::FPOpFusionMode AllowFPOpFusion; - /// This class encapsulates options for reciprocal-estimate code generation. - TargetRecip Reciprocals; - /// JTType - This flag specifies the type of jump-instruction table to /// create for functions that have the jumptable attribute. JumpTable::JumpTableType JTType; @@ -301,7 +298,6 @@ ARE_EQUAL(EmulatedTLS) && ARE_EQUAL(FloatABIType) && ARE_EQUAL(AllowFPOpFusion) && - ARE_EQUAL(Reciprocals) && ARE_EQUAL(JTType) && ARE_EQUAL(ThreadModel) && ARE_EQUAL(EABIVersion) && Index: llvm/trunk/include/llvm/Target/TargetRecip.h =================================================================== --- llvm/trunk/include/llvm/Target/TargetRecip.h +++ llvm/trunk/include/llvm/Target/TargetRecip.h @@ -17,7 +17,6 @@ #ifndef LLVM_TARGET_TARGETRECIP_H #define LLVM_TARGET_TARGETRECIP_H -#include "llvm/ADT/StringRef.h" #include #include #include @@ -25,22 +24,21 @@ namespace llvm { +class StringRef; + struct TargetRecip { public: TargetRecip(); - /// Initialize all or part of the operations from command-line options or - /// a front end. - TargetRecip(const std::vector &Args); - - /// Set whether a particular reciprocal operation is enabled and how many - /// refinement steps are needed when using it. Use "all" to set enablement - /// and refinement steps for all operations. - void setDefaults(StringRef Key, bool Enable, unsigned RefSteps); - - /// Return true if the reciprocal operation has been enabled by default or - /// from the command-line. Return false if the operation has been disabled - /// by default or from the command-line. + /// Parse a comma-separated string of reciprocal settings to set values in + /// this struct. + void set(StringRef &Args); + + /// Set enablement and refinement steps for a particular reciprocal operation. + /// Use "all" to give all operations the same values. + void set(StringRef Key, bool Enable, unsigned RefSteps); + + /// Return true if the reciprocal operation has been enabled. bool isEnabled(StringRef Key) const; /// Return the number of iterations necessary to refine the @@ -50,15 +48,14 @@ bool operator==(const TargetRecip &Other) const; private: - enum { - Uninitialized = -1 - }; - + // TODO: We should be able to use special values (enums) to simplify this into + // just an int, but we have to be careful because the user is allowed to + // specify "default" as a setting and just change the refinement step count. struct RecipParams { - int8_t Enabled; + bool Enabled; int8_t RefinementSteps; - RecipParams() : Enabled(Uninitialized), RefinementSteps(Uninitialized) {} + RecipParams() : Enabled(false), RefinementSteps(0) {} }; std::map RecipMap; Index: llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp =================================================================== --- llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp +++ llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp @@ -838,6 +838,7 @@ InitLibcallNames(LibcallRoutineNames, TM.getTargetTriple()); InitCmpLibcallCCs(CmpLibcallCCs); InitLibcallCallingConvs(LibcallCallingConvs); + ReciprocalEstimates.set("all", false, 0); } void TargetLoweringBase::initActions() { @@ -1485,6 +1486,22 @@ return MVT::i32; // return the default value } +TargetRecip +TargetLoweringBase::getTargetRecipForFunc(MachineFunction &MF) const { + const Function *F = MF.getFunction(); + StringRef RecipAttrName = "reciprocal-estimates"; + if (!F->hasFnAttribute(RecipAttrName)) + return ReciprocalEstimates; + + // Make a copy of the target's default reciprocal codegen settings. + TargetRecip Recips = ReciprocalEstimates; + + // Override any settings that are customized for this function. + StringRef RecipString = F->getFnAttribute(RecipAttrName).getValueAsString(); + Recips.set(RecipString); + return Recips; +} + /// getVectorTypeBreakdown - Vector types are broken down into some number of /// legal first class types. For example, MVT::v8f32 maps to 2 MVT::v4f32 /// with Altivec or SSE1, or 8 promoted MVT::f64 values with the X86 FP stack. Index: llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp +++ llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp @@ -901,6 +901,23 @@ setTargetDAGCombine(ISD::FSQRT); } + // For the estimates, convergence is quadratic, so we essentially double the + // number of digits correct after every iteration. For both FRE and FRSQRTE, + // the minimum architected relative accuracy is 2^-5. When hasRecipPrec(), + // this is 2^-14. IEEE float has 23 digits and double has 52 digits. + unsigned RefinementSteps = Subtarget.hasRecipPrec() ? 1 : 3, + RefinementSteps64 = RefinementSteps + 1; + + ReciprocalEstimates.set("sqrtf", true, RefinementSteps); + ReciprocalEstimates.set("vec-sqrtf", true, RefinementSteps); + ReciprocalEstimates.set("divf", true, RefinementSteps); + ReciprocalEstimates.set("vec-divf", true, RefinementSteps); + + ReciprocalEstimates.set("sqrtd", true, RefinementSteps64); + ReciprocalEstimates.set("vec-sqrtd", true, RefinementSteps64); + ReciprocalEstimates.set("divd", true, RefinementSteps64); + ReciprocalEstimates.set("vec-divd", true, RefinementSteps64); + // Darwin long double math library functions have $LDBL128 appended. if (Subtarget.isDarwin()) { setLibcallName(RTLIB::COS_PPCF128, "cosl$LDBL128"); @@ -9646,7 +9663,7 @@ (VT == MVT::v2f64 && Subtarget.hasVSX()) || (VT == MVT::v4f32 && Subtarget.hasQPX()) || (VT == MVT::v4f64 && Subtarget.hasQPX())) { - TargetRecip Recips = DCI.DAG.getTarget().Options.Reciprocals; + TargetRecip Recips = getTargetRecipForFunc(DCI.DAG.getMachineFunction()); std::string RecipOp = getRecipOp("sqrt", VT); if (!Recips.isEnabled(RecipOp)) return SDValue(); @@ -9668,7 +9685,7 @@ (VT == MVT::v2f64 && Subtarget.hasVSX()) || (VT == MVT::v4f32 && Subtarget.hasQPX()) || (VT == MVT::v4f64 && Subtarget.hasQPX())) { - TargetRecip Recips = DCI.DAG.getTarget().Options.Reciprocals; + TargetRecip Recips = getTargetRecipForFunc(DCI.DAG.getMachineFunction()); std::string RecipOp = getRecipOp("div", VT); if (!Recips.isEnabled(RecipOp)) return SDValue(); Index: llvm/trunk/lib/Target/PowerPC/PPCTargetMachine.cpp =================================================================== --- llvm/trunk/lib/Target/PowerPC/PPCTargetMachine.cpp +++ llvm/trunk/lib/Target/PowerPC/PPCTargetMachine.cpp @@ -204,23 +204,6 @@ TargetABI(computeTargetABI(TT, Options)), Subtarget(TargetTriple, CPU, computeFSAdditions(FS, OL, TT), *this) { - // For the estimates, convergence is quadratic, so we essentially double the - // number of digits correct after every iteration. For both FRE and FRSQRTE, - // the minimum architected relative accuracy is 2^-5. When hasRecipPrec(), - // this is 2^-14. IEEE float has 23 digits and double has 52 digits. - unsigned RefinementSteps = Subtarget.hasRecipPrec() ? 1 : 3, - RefinementSteps64 = RefinementSteps + 1; - - this->Options.Reciprocals.setDefaults("sqrtf", true, RefinementSteps); - this->Options.Reciprocals.setDefaults("vec-sqrtf", true, RefinementSteps); - this->Options.Reciprocals.setDefaults("divf", true, RefinementSteps); - this->Options.Reciprocals.setDefaults("vec-divf", true, RefinementSteps); - - this->Options.Reciprocals.setDefaults("sqrtd", true, RefinementSteps64); - this->Options.Reciprocals.setDefaults("vec-sqrtd", true, RefinementSteps64); - this->Options.Reciprocals.setDefaults("divd", true, RefinementSteps64); - this->Options.Reciprocals.setDefaults("vec-divd", true, RefinementSteps64); - initAsmInfo(); } Index: llvm/trunk/lib/Target/TargetRecip.cpp =================================================================== --- llvm/trunk/lib/Target/TargetRecip.cpp +++ llvm/trunk/lib/Target/TargetRecip.cpp @@ -16,7 +16,9 @@ #include "llvm/Target/TargetRecip.h" #include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/StringExtras.h" #include "llvm/ADT/StringRef.h" +#include "llvm/ADT/SmallVector.h" #include "llvm/Support/ErrorHandling.h" using namespace llvm; @@ -36,9 +38,7 @@ "vec-sqrtf", }; -// The uninitialized state is needed for the enabled settings and refinement -// steps because custom settings may arrive via the command-line before target -// defaults are set. +/// All operations are disabled by default and refinement steps are set to zero. TargetRecip::TargetRecip() { unsigned NumStrings = llvm::array_lengthof(RecipOps); for (unsigned i = 0; i < NumStrings; ++i) @@ -137,18 +137,8 @@ assert(Iter == RecipMap.end() && "Float entry missing from map"); report_fatal_error("Invalid option for -recip."); } - - // The option was specified without a float or double suffix. - if (RecipMap[Val.str() + 'd'].Enabled != Uninitialized) { - // Make sure that the double entry was not already specified. - // The float entry will be checked below. - report_fatal_error("Duplicate option for -recip."); - } } - if (Iter->second.Enabled != Uninitialized) - report_fatal_error("Duplicate option for -recip."); - // Mark the matched option as found. Do not allow duplicate specifiers. Iter->second.Enabled = !IsDisabled; if (!RefStepString.empty()) @@ -164,50 +154,45 @@ } } -TargetRecip::TargetRecip(const std::vector &Args) : - TargetRecip() { - unsigned NumArgs = Args.size(); +void TargetRecip::set(StringRef &RecipString) { + SmallVector RecipStringVector; + SplitString(RecipString, RecipStringVector, ","); + std::vector RecipVector; + for (unsigned i = 0; i < RecipStringVector.size(); ++i) + RecipVector.push_back(RecipStringVector[i].str()); + + unsigned NumArgs = RecipVector.size(); // Check if "all", "default", or "none" was specified. - if (NumArgs == 1 && parseGlobalParams(Args[0])) + if (NumArgs == 1 && parseGlobalParams(RecipVector[0])) return; - - parseIndividualParams(Args); + + parseIndividualParams(RecipVector); } bool TargetRecip::isEnabled(StringRef Key) const { ConstRecipIter Iter = RecipMap.find(Key); assert(Iter != RecipMap.end() && "Unknown name for reciprocal map"); - assert(Iter->second.Enabled != Uninitialized && - "Enablement setting was not initialized"); return Iter->second.Enabled; } unsigned TargetRecip::getRefinementSteps(StringRef Key) const { ConstRecipIter Iter = RecipMap.find(Key); assert(Iter != RecipMap.end() && "Unknown name for reciprocal map"); - assert(Iter->second.RefinementSteps != Uninitialized && - "Refinement step setting was not initialized"); return Iter->second.RefinementSteps; } -/// Custom settings (previously initialized values) override target defaults. -void TargetRecip::setDefaults(StringRef Key, bool Enable, - unsigned RefSteps) { +void TargetRecip::set(StringRef Key, bool Enable, unsigned RefSteps) { if (Key == "all") { for (auto &KV : RecipMap) { RecipParams &RP = KV.second; - if (RP.Enabled == Uninitialized) - RP.Enabled = Enable; - if (RP.RefinementSteps == Uninitialized) - RP.RefinementSteps = RefSteps; + RP.Enabled = Enable; + RP.RefinementSteps = RefSteps; } } else { RecipParams &RP = RecipMap[Key]; - if (RP.Enabled == Uninitialized) - RP.Enabled = Enable; - if (RP.RefinementSteps == Uninitialized) - RP.RefinementSteps = RefSteps; + RP.Enabled = Enable; + RP.RefinementSteps = RefSteps; } } Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp =================================================================== --- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp +++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp @@ -53,6 +53,7 @@ #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/MathExtras.h" #include "llvm/Target/TargetOptions.h" +#include "llvm/Target/TargetRecip.h" #include "X86IntrinsicsInfo.h" #include #include @@ -84,6 +85,15 @@ // X86-SSE is even stranger. It uses -1 or 0 for vector masks. setBooleanVectorContents(ZeroOrNegativeOneBooleanContent); + // By default (and when -ffast-math is on), enable estimate codegen with 1 + // refinement step for floats (not doubles) except scalar division. Scalar + // division estimates are disabled because they break too much real-world + // code. These defaults are intended to match GCC behavior. + ReciprocalEstimates.set("sqrtf", true, 1); + ReciprocalEstimates.set("divf", false, 1); + ReciprocalEstimates.set("vec-sqrtf", true, 1); + ReciprocalEstimates.set("vec-divf", true, 1); + // For 64-bit, since we have so many registers, use the ILP scheduler. // For 32-bit, use the register pressure specific scheduling. // For Atom, always use ILP scheduling. @@ -15206,7 +15216,7 @@ else return SDValue(); - TargetRecip Recips = DCI.DAG.getTarget().Options.Reciprocals; + TargetRecip Recips = getTargetRecipForFunc(DCI.DAG.getMachineFunction()); if (!Recips.isEnabled(RecipOp)) return SDValue(); @@ -15238,7 +15248,7 @@ else return SDValue(); - TargetRecip Recips = DCI.DAG.getTarget().Options.Reciprocals; + TargetRecip Recips = getTargetRecipForFunc(DCI.DAG.getMachineFunction()); if (!Recips.isEnabled(RecipOp)) return SDValue(); Index: llvm/trunk/lib/Target/X86/X86TargetMachine.cpp =================================================================== --- llvm/trunk/lib/Target/X86/X86TargetMachine.cpp +++ llvm/trunk/lib/Target/X86/X86TargetMachine.cpp @@ -166,16 +166,6 @@ if ((TT.isOSWindows() && TT.getArch() == Triple::x86_64) || TT.isPS4()) this->Options.TrapUnreachable = true; - // By default (and when -ffast-math is on), enable estimate codegen for - // everything except scalar division. By default, use 1 refinement step for - // all operations. Defaults may be overridden by using command-line options. - // Scalar division estimates are disabled because they break too much - // real-world code. These defaults match GCC behavior. - this->Options.Reciprocals.setDefaults("sqrtf", true, 1); - this->Options.Reciprocals.setDefaults("divf", false, 1); - this->Options.Reciprocals.setDefaults("vec-sqrtf", true, 1); - this->Options.Reciprocals.setDefaults("vec-divf", true, 1); - initAsmInfo(); } Index: llvm/trunk/test/CodeGen/PowerPC/recipest.ll =================================================================== --- llvm/trunk/test/CodeGen/PowerPC/recipest.ll +++ llvm/trunk/test/CodeGen/PowerPC/recipest.ll @@ -1,6 +1,6 @@ ; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -enable-unsafe-fp-math -mattr=-vsx | FileCheck %s -; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -enable-unsafe-fp-math -mattr=-vsx -recip=sqrtf:0,sqrtd:0 | FileCheck %s -check-prefix=CHECK-NONR ; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -mattr=-vsx | FileCheck -check-prefix=CHECK-SAFE %s + target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64" target triple = "powerpc64-unknown-linux-gnu" @@ -25,19 +25,26 @@ ; CHECK-NEXT: fmul ; CHECK: blr -; CHECK-NONR: @foo -; CHECK-NONR: frsqrte -; CHECK-NONR-NOT: fmadd -; CHECK-NONR: fmul -; CHECK-NONR-NOT: fmadd -; CHECK-NONR: blr - ; CHECK-SAFE: @foo ; CHECK-SAFE: fsqrt ; CHECK-SAFE: fdiv ; CHECK-SAFE: blr } +define double @no_estimate_refinement_f64(double %a, double %b) #0 { + %x = call double @llvm.sqrt.f64(double %b) + %r = fdiv double %a, %x + ret double %r + +; CHECK-LABEL: @no_estimate_refinement_f64 +; CHECK: frsqrte +; CHECK-NOT: fmadd +; CHECK: fmul +; CHECK-NOT: fmadd +; CHECK: blr +} + + define double @foof(double %a, float %b) nounwind { %x = call float @llvm.sqrt.f32(float %b) %y = fpext float %x to double @@ -98,19 +105,26 @@ ; CHECK-NEXT: fmuls ; CHECK-NEXT: blr -; CHECK-NONR: @goo -; CHECK-NONR: frsqrtes -; CHECK-NONR-NOT: fmadds -; CHECK-NONR: fmuls -; CHECK-NONR-NOT: fmadds -; CHECK-NONR: blr - ; CHECK-SAFE: @goo ; CHECK-SAFE: fsqrts ; CHECK-SAFE: fdivs ; CHECK-SAFE: blr } + +define float @no_estimate_refinement_f32(float %a, float %b) #0 { + %x = call float @llvm.sqrt.f32(float %b) + %r = fdiv float %a, %x + ret float %r + +; CHECK-LABEL: @no_estimate_refinement_f32 +; CHECK: frsqrtes +; CHECK-NOT: fmadds +; CHECK: fmuls +; CHECK-NOT: fmadds +; CHECK: blr +} + ; Recognize that this is rsqrt(a) * rcp(b) * c, ; not 1 / ( 1 / sqrt(a)) * rcp(b) * c. define float @rsqrt_fmul(float %a, float %b, float %c) { @@ -252,3 +266,5 @@ ; CHECK-SAFE: blr } +attributes #0 = { nounwind "reciprocal-estimates"="sqrtf:0,sqrtd:0" } + Index: llvm/trunk/test/CodeGen/X86/recip-fastmath.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/recip-fastmath.ll +++ llvm/trunk/test/CodeGen/X86/recip-fastmath.ll @@ -1,6 +1,5 @@ -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf,vec-divf | FileCheck %s --check-prefix=RECIP -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=divf:2,vec-divf:2 | FileCheck %s --check-prefix=REFINE +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=AVX ; If the target's divss/divps instructions are substantially ; slower than rcpss/rcpps with a Newton-Raphson refinement, @@ -10,100 +9,142 @@ ; for details about the accuracy, speed, and implementation ; differences of x86 reciprocal estimates. -define float @reciprocal_estimate(float %x) #0 { +define float @f32_no_estimate(float %x) #0 { +; AVX-LABEL: f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; AVX-NEXT: vdivss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; %div = fdiv fast float 1.0, %x ret float %div +} + +define float @f32_one_step(float %x) #1 { +; AVX-LABEL: f32_one_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpss %xmm0, %xmm0, %xmm1 +; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0 +; AVX-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero +; AVX-NEXT: vsubss %xmm0, %xmm2, %xmm0 +; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: vaddss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %div = fdiv fast float 1.0, %x + ret float %div +} + +define float @f32_two_step(float %x) #2 { +; AVX-LABEL: f32_two_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpss %xmm0, %xmm0, %xmm1 +; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm2 +; AVX-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero +; AVX-NEXT: vsubss %xmm2, %xmm3, %xmm2 +; AVX-NEXT: vmulss %xmm2, %xmm1, %xmm2 +; AVX-NEXT: vaddss %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0 +; AVX-NEXT: vsubss %xmm0, %xmm3, %xmm0 +; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: vaddss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %div = fdiv fast float 1.0, %x + ret float %div +} + +define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 { +; AVX-LABEL: v4f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vdivps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %div = fdiv fast <4 x float> , %x + ret <4 x float> %div +} -; NORECIP-LABEL: reciprocal_estimate: -; NORECIP: movss -; NORECIP-NEXT: divss -; NORECIP-NEXT: movaps -; NORECIP-NEXT: retq - -; RECIP-LABEL: reciprocal_estimate: -; RECIP: vrcpss -; RECIP: vmulss -; RECIP: vsubss -; RECIP: vmulss -; RECIP: vaddss -; RECIP-NEXT: retq - -; REFINE-LABEL: reciprocal_estimate: -; REFINE: vrcpss -; REFINE: vmulss -; REFINE: vsubss -; REFINE: vmulss -; REFINE: vaddss -; REFINE: vmulss -; REFINE: vsubss -; REFINE: vmulss -; REFINE: vaddss -; REFINE-NEXT: retq +define <4 x float> @v4f32_one_step(<4 x float> %x) #1 { +; AVX-LABEL: v4f32_one_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpps %xmm0, %xmm1 +; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm0 +; AVX-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vsubps %xmm0, %xmm2, %xmm0 +; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %div = fdiv fast <4 x float> , %x + ret <4 x float> %div } -define <4 x float> @reciprocal_estimate_v4f32(<4 x float> %x) #0 { +define <4 x float> @v4f32_two_step(<4 x float> %x) #2 { +; AVX-LABEL: v4f32_two_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpps %xmm0, %xmm1 +; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm2 +; AVX-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vsubps %xmm2, %xmm3, %xmm2 +; AVX-NEXT: vmulps %xmm2, %xmm1, %xmm2 +; AVX-NEXT: vaddps %xmm2, %xmm1, %xmm1 +; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm0 +; AVX-NEXT: vsubps %xmm0, %xmm3, %xmm0 +; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; %div = fdiv fast <4 x float> , %x ret <4 x float> %div +} -; NORECIP-LABEL: reciprocal_estimate_v4f32: -; NORECIP: movaps -; NORECIP-NEXT: divps -; NORECIP-NEXT: movaps -; NORECIP-NEXT: retq - -; RECIP-LABEL: reciprocal_estimate_v4f32: -; RECIP: vrcpps -; RECIP: vmulps -; RECIP: vsubps -; RECIP: vmulps -; RECIP: vaddps -; RECIP-NEXT: retq - -; REFINE-LABEL: reciprocal_estimate_v4f32: -; REFINE: vrcpps -; REFINE: vmulps -; REFINE: vsubps -; REFINE: vmulps -; REFINE: vaddps -; REFINE: vmulps -; REFINE: vsubps -; REFINE: vmulps -; REFINE: vaddps -; REFINE-NEXT: retq +define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 { +; AVX-LABEL: v8f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vdivps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq +; + %div = fdiv fast <8 x float> , %x + ret <8 x float> %div } -define <8 x float> @reciprocal_estimate_v8f32(<8 x float> %x) #0 { +define <8 x float> @v8f32_one_step(<8 x float> %x) #1 { +; AVX-LABEL: v8f32_one_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpps %ymm0, %ymm1 +; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm0 +; AVX-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vsubps %ymm0, %ymm2, %ymm0 +; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: vaddps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq +; %div = fdiv fast <8 x float> , %x ret <8 x float> %div +} -; NORECIP-LABEL: reciprocal_estimate_v8f32: -; NORECIP: movaps -; NORECIP: movaps -; NORECIP-NEXT: divps -; NORECIP-NEXT: divps -; NORECIP-NEXT: movaps -; NORECIP-NEXT: movaps -; NORECIP-NEXT: retq - -; RECIP-LABEL: reciprocal_estimate_v8f32: -; RECIP: vrcpps -; RECIP: vmulps -; RECIP: vsubps -; RECIP: vmulps -; RECIP: vaddps -; RECIP-NEXT: retq - -; REFINE-LABEL: reciprocal_estimate_v8f32: -; REFINE: vrcpps -; REFINE: vmulps -; REFINE: vsubps -; REFINE: vmulps -; REFINE: vaddps -; REFINE: vmulps -; REFINE: vsubps -; REFINE: vmulps -; REFINE: vaddps -; REFINE-NEXT: retq +define <8 x float> @v8f32_two_step(<8 x float> %x) #2 { +; AVX-LABEL: v8f32_two_step: +; AVX: # BB#0: +; AVX-NEXT: vrcpps %ymm0, %ymm1 +; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm2 +; AVX-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vsubps %ymm2, %ymm3, %ymm2 +; AVX-NEXT: vmulps %ymm2, %ymm1, %ymm2 +; AVX-NEXT: vaddps %ymm2, %ymm1, %ymm1 +; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm0 +; AVX-NEXT: vsubps %ymm0, %ymm3, %ymm0 +; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: vaddps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq +; + %div = fdiv fast <8 x float> , %x + ret <8 x float> %div } -attributes #0 = { "unsafe-fp-math"="true" } +attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!divf,!vec-divf" } +attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" } +attributes #2 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:2,vec-divf:2" } + Index: llvm/trunk/test/CodeGen/X86/sqrt-fastmath-mir.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/sqrt-fastmath-mir.ll +++ llvm/trunk/test/CodeGen/X86/sqrt-fastmath-mir.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2,fma -recip=sqrt:2 -stop-after=expand-isel-pseudos 2>&1 | FileCheck %s +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2,fma -stop-after=expand-isel-pseudos 2>&1 | FileCheck %s declare float @llvm.sqrt.f32(float) #0 @@ -48,5 +48,5 @@ ret float %div } -attributes #0 = { "unsafe-fp-math"="true" } +attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="sqrt:2" } attributes #1 = { nounwind readnone } Index: llvm/trunk/test/CodeGen/X86/sqrt-fastmath.ll =================================================================== --- llvm/trunk/test/CodeGen/X86/sqrt-fastmath.ll +++ llvm/trunk/test/CodeGen/X86/sqrt-fastmath.ll @@ -1,141 +1,177 @@ -; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!sqrtf,!vec-sqrtf,!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP -; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=sqrtf,vec-sqrtf | FileCheck %s --check-prefix=ESTIMATE - -declare double @__sqrt_finite(double) #0 -declare float @__sqrtf_finite(float) #0 -declare x86_fp80 @__sqrtl_finite(x86_fp80) #0 -declare float @llvm.sqrt.f32(float) #0 -declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #0 -declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #0 - - -define double @fd(double %d) #0 { -; NORECIP-LABEL: fd: -; NORECIP: # BB#0: -; NORECIP-NEXT: sqrtsd %xmm0, %xmm0 -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: fd: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0 -; ESTIMATE-NEXT: retq - %call = tail call double @__sqrt_finite(double %d) #1 +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=AVX + +declare double @__sqrt_finite(double) +declare float @__sqrtf_finite(float) +declare x86_fp80 @__sqrtl_finite(x86_fp80) +declare float @llvm.sqrt.f32(float) +declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) +declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) + + +define double @finite_f64_no_estimate(double %d) #0 { +; AVX-LABEL: finite_f64_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0 +; AVX-NEXT: retq +; + %call = tail call double @__sqrt_finite(double %d) #2 ret double %call } +; No estimates for doubles. -define float @ff(float %f) #0 { -; NORECIP-LABEL: ff: -; NORECIP: # BB#0: -; NORECIP-NEXT: sqrtss %xmm0, %xmm0 -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: ff: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1 -; ESTIMATE-NEXT: vmulss %xmm1, %xmm0, %xmm2 -; ESTIMATE-NEXT: vmulss %xmm1, %xmm2, %xmm1 -; ESTIMATE-NEXT: vaddss {{.*}}(%rip), %xmm1, %xmm1 -; ESTIMATE-NEXT: vmulss {{.*}}(%rip), %xmm2, %xmm2 -; ESTIMATE-NEXT: vmulss %xmm1, %xmm2, %xmm1 -; ESTIMATE-NEXT: vxorps %xmm2, %xmm2, %xmm2 -; ESTIMATE-NEXT: vcmpeqss %xmm2, %xmm0, %xmm0 -; ESTIMATE-NEXT: vandnps %xmm1, %xmm0, %xmm0 -; ESTIMATE-NEXT: retq - %call = tail call float @__sqrtf_finite(float %f) #1 +define double @finite_f64_estimate(double %d) #1 { +; AVX-LABEL: finite_f64_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0 +; AVX-NEXT: retq +; + %call = tail call double @__sqrt_finite(double %d) #2 + ret double %call +} + +define float @finite_f32_no_estimate(float %f) #0 { +; AVX-LABEL: finite_f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0 +; AVX-NEXT: retq +; + %call = tail call float @__sqrtf_finite(float %f) #2 ret float %call } +define float @finite_f32_estimate(float %f) #1 { +; AVX-LABEL: finite_f32_estimate: +; AVX: # BB#0: +; AVX-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1 +; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm2 +; AVX-NEXT: vmulss %xmm1, %xmm2, %xmm1 +; AVX-NEXT: vaddss {{.*}}(%rip), %xmm1, %xmm1 +; AVX-NEXT: vmulss {{.*}}(%rip), %xmm2, %xmm2 +; AVX-NEXT: vmulss %xmm1, %xmm2, %xmm1 +; AVX-NEXT: vxorps %xmm2, %xmm2, %xmm2 +; AVX-NEXT: vcmpeqss %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vandnps %xmm1, %xmm0, %xmm0 +; AVX-NEXT: retq +; + %call = tail call float @__sqrtf_finite(float %f) #2 + ret float %call +} -define x86_fp80 @fld(x86_fp80 %ld) #0 { -; NORECIP-LABEL: fld: -; NORECIP: # BB#0: -; NORECIP-NEXT: fldt {{[0-9]+}}(%rsp) -; NORECIP-NEXT: fsqrt -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: fld: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: fldt {{[0-9]+}}(%rsp) -; ESTIMATE-NEXT: fsqrt -; ESTIMATE-NEXT: retq - %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #1 +define x86_fp80 @finite_f80_no_estimate(x86_fp80 %ld) #0 { +; AVX-LABEL: finite_f80_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: fldt {{[0-9]+}}(%rsp) +; AVX-NEXT: fsqrt +; AVX-NEXT: retq +; + %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #2 ret x86_fp80 %call } +; Don't die on the impossible. +define x86_fp80 @finite_f80_estimate_but_no(x86_fp80 %ld) #1 { +; AVX-LABEL: finite_f80_estimate_but_no: +; AVX: # BB#0: +; AVX-NEXT: fldt {{[0-9]+}}(%rsp) +; AVX-NEXT: fsqrt +; AVX-NEXT: retq +; + %call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #2 + ret x86_fp80 %call +} -define float @reciprocal_square_root(float %x) #0 { -; NORECIP-LABEL: reciprocal_square_root: -; NORECIP: # BB#0: -; NORECIP-NEXT: sqrtss %xmm0, %xmm1 -; NORECIP-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero -; NORECIP-NEXT: divss %xmm1, %xmm0 -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: reciprocal_square_root: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1 -; ESTIMATE-NEXT: vmulss %xmm1, %xmm1, %xmm2 -; ESTIMATE-NEXT: vmulss %xmm2, %xmm0, %xmm0 -; ESTIMATE-NEXT: vaddss {{.*}}(%rip), %xmm0, %xmm0 -; ESTIMATE-NEXT: vmulss {{.*}}(%rip), %xmm1, %xmm1 -; ESTIMATE-NEXT: vmulss %xmm0, %xmm1, %xmm0 -; ESTIMATE-NEXT: retq +define float @f32_no_estimate(float %x) #0 { +; AVX-LABEL: f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0 +; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; AVX-NEXT: vdivss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; %sqrt = tail call float @llvm.sqrt.f32(float %x) %div = fdiv fast float 1.0, %sqrt ret float %div } -define <4 x float> @reciprocal_square_root_v4f32(<4 x float> %x) #0 { -; NORECIP-LABEL: reciprocal_square_root_v4f32: -; NORECIP: # BB#0: -; NORECIP-NEXT: sqrtps %xmm0, %xmm1 -; NORECIP-NEXT: movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] -; NORECIP-NEXT: divps %xmm1, %xmm0 -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: reciprocal_square_root_v4f32: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: vrsqrtps %xmm0, %xmm1 -; ESTIMATE-NEXT: vmulps %xmm1, %xmm1, %xmm2 -; ESTIMATE-NEXT: vmulps %xmm2, %xmm0, %xmm0 -; ESTIMATE-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0 -; ESTIMATE-NEXT: vmulps {{.*}}(%rip), %xmm1, %xmm1 -; ESTIMATE-NEXT: vmulps %xmm0, %xmm1, %xmm0 -; ESTIMATE-NEXT: retq +define float @f32_estimate(float %x) #1 { +; AVX-LABEL: f32_estimate: +; AVX: # BB#0: +; AVX-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1 +; AVX-NEXT: vmulss %xmm1, %xmm1, %xmm2 +; AVX-NEXT: vmulss %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vaddss {{.*}}(%rip), %xmm0, %xmm0 +; AVX-NEXT: vmulss {{.*}}(%rip), %xmm1, %xmm1 +; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %sqrt = tail call float @llvm.sqrt.f32(float %x) + %div = fdiv fast float 1.0, %sqrt + ret float %div +} + +define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 { +; AVX-LABEL: v4f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtps %xmm0, %xmm0 +; AVX-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vdivps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; %sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x) %div = fdiv fast <4 x float> , %sqrt ret <4 x float> %div } -define <8 x float> @reciprocal_square_root_v8f32(<8 x float> %x) #0 { -; NORECIP-LABEL: reciprocal_square_root_v8f32: -; NORECIP: # BB#0: -; NORECIP-NEXT: sqrtps %xmm1, %xmm2 -; NORECIP-NEXT: sqrtps %xmm0, %xmm3 -; NORECIP-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] -; NORECIP-NEXT: movaps %xmm1, %xmm0 -; NORECIP-NEXT: divps %xmm3, %xmm0 -; NORECIP-NEXT: divps %xmm2, %xmm1 -; NORECIP-NEXT: retq -; -; ESTIMATE-LABEL: reciprocal_square_root_v8f32: -; ESTIMATE: # BB#0: -; ESTIMATE-NEXT: vrsqrtps %ymm0, %ymm1 -; ESTIMATE-NEXT: vmulps %ymm1, %ymm1, %ymm2 -; ESTIMATE-NEXT: vmulps %ymm2, %ymm0, %ymm0 -; ESTIMATE-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0 -; ESTIMATE-NEXT: vmulps {{.*}}(%rip), %ymm1, %ymm1 -; ESTIMATE-NEXT: vmulps %ymm0, %ymm1, %ymm0 -; ESTIMATE-NEXT: retq +define <4 x float> @v4f32_estimate(<4 x float> %x) #1 { +; AVX-LABEL: v4f32_estimate: +; AVX: # BB#0: +; AVX-NEXT: vrsqrtps %xmm0, %xmm1 +; AVX-NEXT: vmulps %xmm1, %xmm1, %xmm2 +; AVX-NEXT: vmulps %xmm2, %xmm0, %xmm0 +; AVX-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0 +; AVX-NEXT: vmulps {{.*}}(%rip), %xmm1, %xmm1 +; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0 +; AVX-NEXT: retq +; + %sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x) + %div = fdiv fast <4 x float> , %sqrt + ret <4 x float> %div +} + +define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 { +; AVX-LABEL: v8f32_no_estimate: +; AVX: # BB#0: +; AVX-NEXT: vsqrtps %ymm0, %ymm0 +; AVX-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] +; AVX-NEXT: vdivps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq +; + %sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x) + %div = fdiv fast <8 x float> , %sqrt + ret <8 x float> %div +} + +define <8 x float> @v8f32_estimate(<8 x float> %x) #1 { +; AVX-LABEL: v8f32_estimate: +; AVX: # BB#0: +; AVX-NEXT: vrsqrtps %ymm0, %ymm1 +; AVX-NEXT: vmulps %ymm1, %ymm1, %ymm2 +; AVX-NEXT: vmulps %ymm2, %ymm0, %ymm0 +; AVX-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0 +; AVX-NEXT: vmulps {{.*}}(%rip), %ymm1, %ymm1 +; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0 +; AVX-NEXT: retq +; %sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x) %div = fdiv fast <8 x float> , %sqrt ret <8 x float> %div } -attributes #0 = { "unsafe-fp-math"="true" } -attributes #1 = { nounwind readnone } +attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!sqrtf,!vec-sqrtf,!divf,!vec-divf" } +attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="sqrt,vec-sqrt" } +attributes #2 = { nounwind readnone }