Index: llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp =================================================================== --- llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp +++ llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp @@ -13,6 +13,7 @@ //===----------------------------------------------------------------------===// #include "llvm/Transforms/Utils/SimplifyLibCalls.h" +#include "llvm/ADT/APSInt.h" #include "llvm/ADT/SmallString.h" #include "llvm/ADT/StringMap.h" #include "llvm/ADT/Triple.h" @@ -1183,12 +1184,13 @@ } /// Use exp{,2}(x * y) for pow(exp{,2}(x), y); -/// exp2(x) for pow(2.0, x); exp10(x) for pow(10.0, x). +/// exp2(n * x) for pow(2.0 ** n, x); exp10(x) for pow(10.0, x). Value *LibCallSimplifier::replacePowWithExp(CallInst *Pow, IRBuilder<> &B) { Value *Base = Pow->getArgOperand(0), *Expo = Pow->getArgOperand(1); AttributeList Attrs = Pow->getCalledFunction()->getAttributes(); Module *Mod = Pow->getModule(); Type *Ty = Pow->getType(); + bool Ignored; // Evaluate special cases related to a nested function as the base. @@ -1249,10 +1251,30 @@ // Evaluate special cases related to a constant base. - // pow(2.0, x) -> exp2(x) - if (match(Base, m_SpecificFP(2.0))) { - Value *Exp2 = Intrinsic::getDeclaration(Mod, Intrinsic::exp2, Ty); - return B.CreateCall(Exp2, Expo, "exp2"); + const APFloat *BaseF; + if (!match(Pow->getArgOperand(0), m_APFloat(BaseF))) + return nullptr; + + // pow(2.0 ** n, x) -> exp2(n * x) + if (hasUnaryFloatFn(TLI, Ty, LibFunc_exp2, LibFunc_exp2f, LibFunc_exp2l)) { + APFloat BaseR = APFloat(1.0); + BaseR.convert(BaseF->getSemantics(), APFloat::rmTowardZero, &Ignored); + BaseR = BaseR / *BaseF; + bool IsInteger = BaseF->isInteger(), + IsReciprocal = BaseR.isInteger(); + const APFloat *NF = IsReciprocal ? &BaseR : BaseF; + APSInt NI(64, false); + if ((IsInteger || IsReciprocal) && + !NF->convertToInteger(NI, APFloat::rmTowardZero, &Ignored) && + NI > 1 && NI.isPowerOf2()) { + double N = NI.logBase2() * (IsReciprocal ? -1.0 : 1.0); + Value *FMul = B.CreateFMul(Expo, ConstantFP::get(Ty, N), "mul"); + if (Pow->doesNotAccessMemory()) + return B.CreateCall(Intrinsic::getDeclaration(Mod, Intrinsic::exp2, Ty), + FMul, "exp2"); + else + return emitUnaryFloatFnCall(FMul, TLI->getName(LibFunc_exp2), B, Attrs); + } } // pow(10.0, x) -> exp10(x) Index: llvm/test/Transforms/InstCombine/pow-1.ll =================================================================== --- llvm/test/Transforms/InstCombine/pow-1.ll +++ llvm/test/Transforms/InstCombine/pow-1.ll @@ -1,4 +1,3 @@ -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; Test that the pow library call simplifier works correctly. ; ; RUN: opt -instcombine -S < %s | FileCheck %s --check-prefixes=ANY @@ -10,12 +9,14 @@ ; RUN: opt -instcombine -S < %s -mtriple=arm-apple-tvos9.0 | FileCheck %s --check-prefixes=ANY,CHECK-EXP10 ; RUN: opt -instcombine -S < %s -mtriple=arm-apple-watchos2.0 | FileCheck %s --check-prefixes=ANY,CHECK-EXP10 ; rdar://7251832 +; RUN: opt -instcombine -S < %s -mtriple=x86_64-pc-windows-msvc | FileCheck %s --check-prefixes=CHECK-WIN ; NOTE: The readonly attribute on the pow call should be preserved ; in the cases below where pow is transformed into another function call. declare float @powf(float, float) nounwind readonly declare double @pow(double, double) nounwind readonly +declare double @llvm.pow.f64(double, double) declare <2 x float> @llvm.pow.v2f32(<2 x float>, <2 x float>) nounwind readonly declare <2 x double> @llvm.pow.v2f64(<2 x double>, <2 x double>) nounwind readonly @@ -57,18 +58,26 @@ define float @test_simplify3(float %x) { ; ANY-LABEL: @test_simplify3( -; ANY-NEXT: [[EXP2:%.*]] = call float @llvm.exp2.f32(float [[X:%.*]]) -; ANY-NEXT: ret float [[EXP2]] +; ANY-NEXT: [[EXP2F:%.*]] = call float @exp2f(float [[X:%.*]]) [[NUW_RO:#[0-9]+]] +; ANY-NEXT: ret float [[EXP2F]] +; +; CHECK-WIN-LABEL: @test_simplify3( +; CHECK-WIN-NEXT: [[POW:%.*]] = call float @powf(float 2.000000e+00, float [[X:%.*]]) +; CHECK-WIN-NEXT: ret float [[POW]] ; %retval = call float @powf(float 2.0, float %x) ret float %retval } -; TODO: Should result in exp2(-2.0 * x). define double @test_simplify3n(double %x) { ; ANY-LABEL: @test_simplify3n( -; ANY-NEXT: [[RETVAL:%.*]] = call double @pow(double 2.500000e-01, double [[X:%.*]]) -; ANY-NEXT: ret double [[RETVAL]] +; ANY-NEXT: [[MUL:%.*]] = fmul double [[X:%.*]], -2.000000e+00 +; ANY-NEXT: [[EXP2:%.*]] = call double @exp2(double [[MUL]]) [[NUW_RO]] +; ANY-NEXT: ret double [[EXP2]] +; +; CHECK-WIN-LABEL: @test_simplify3n( +; CHECK-WIN-NEXT: [[POW:%.*]] = call double @pow(double 2.500000e-01, double [[X:%.*]]) +; CHECK-WIN-NEXT: ret double [[POW]] ; %retval = call double @pow(double 0.25, double %x) ret double %retval @@ -78,16 +87,20 @@ ; ANY-LABEL: @test_simplify3v( ; ANY-NEXT: [[EXP2:%.*]] = call <2 x float> @llvm.exp2.v2f32(<2 x float> [[X:%.*]]) ; ANY-NEXT: ret <2 x float> [[EXP2]] +; +; CHECK-WIN-LABEL: @test_simplify3v( +; CHECK-WIN-NEXT: [[POW:%.*]] = call <2 x float> @llvm.pow.v2f32(<2 x float> , <2 x float> [[X:%.*]]) +; CHECK-WIN-NEXT: ret <2 x float> [[POW]] ; %retval = call <2 x float> @llvm.pow.v2f32(<2 x float> , <2 x float> %x) ret <2 x float> %retval } -; TODO: Should result in exp2(2.0 * x). define <2 x double> @test_simplify3vn(<2 x double> %x) { ; ANY-LABEL: @test_simplify3vn( -; ANY-NEXT: [[RETVAL:%.*]] = call <2 x double> @llvm.pow.v2f64(<2 x double> , <2 x double> [[X:%.*]]) -; ANY-NEXT: ret <2 x double> [[RETVAL]] +; ANY-NEXT: [[MUL:%.*]] = fmul <2 x double> [[X:%.*]], +; ANY-NEXT: [[EXP2:%.*]] = call <2 x double> @llvm.exp2.v2f64(<2 x double> [[MUL]]) +; ANY-NEXT: ret <2 x double> [[EXP2]] ; %retval = call <2 x double> @llvm.pow.v2f64(<2 x double> , <2 x double> %x) ret <2 x double> %retval @@ -95,18 +108,26 @@ define double @test_simplify4(double %x) { ; ANY-LABEL: @test_simplify4( -; ANY-NEXT: [[EXP2:%.*]] = call double @llvm.exp2.f64(double [[X:%.*]]) +; ANY-NEXT: [[EXP2:%.*]] = call double @exp2(double [[X:%.*]]) [[NUW_RO]] ; ANY-NEXT: ret double [[EXP2]] +; +; CHECK-WIN-LABEL: @test_simplify4( +; CHECK-WIN-NEXT: [[POW:%.*]] = call double @pow(double 2.000000e+00, double [[X:%.*]]) +; CHECK-WIN-NEXT: ret double [[POW]] ; %retval = call double @pow(double 2.0, double %x) ret double %retval } -; TODO: Should result in exp2f(3.0 * x). define float @test_simplify4n(float %x) { ; ANY-LABEL: @test_simplify4n( -; ANY-NEXT: [[RETVAL:%.*]] = call float @powf(float 8.000000e+00, float [[X:%.*]]) -; ANY-NEXT: ret float [[RETVAL]] +; ANY-NEXT: [[MUL:%.*]] = fmul float [[X:%.*]], 3.000000e+00 +; ANY-NEXT: [[EXP2F:%.*]] = call float @exp2f(float [[MUL]]) [[NUW_RO]] +; ANY-NEXT: ret float [[EXP2F]] +; +; CHECK-WIN-LABEL: @test_simplify4n( +; CHECK-WIN-NEXT: [[POW:%.*]] = call float @powf(float 8.000000e+00, float [[X:%.*]]) +; CHECK-WIN-NEXT: ret float [[POW]] ; %retval = call float @powf(float 8.0, float %x) ret float %retval @@ -121,11 +142,11 @@ ret <2 x double> %retval } -; TODO: Should result in exp2f(-x). define <2 x float> @test_simplify4vn(<2 x float> %x) { ; ANY-LABEL: @test_simplify4vn( -; ANY-NEXT: [[RETVAL:%.*]] = call <2 x float> @llvm.pow.v2f32(<2 x float> , <2 x float> [[X:%.*]]) -; ANY-NEXT: ret <2 x float> [[RETVAL]] +; ANY-NEXT: [[MUL:%.*]] = fsub <2 x float> , [[X:%.*]] +; ANY-NEXT: [[EXP2:%.*]] = call <2 x float> @llvm.exp2.v2f32(<2 x float> [[MUL]]) +; ANY-NEXT: ret <2 x float> [[EXP2]] ; %retval = call <2 x float> @llvm.pow.v2f32(<2 x float> , <2 x float> %x) ret <2 x float> %retval @@ -169,7 +190,7 @@ define float @test_simplify7(float %x) { ; ANY-LABEL: @test_simplify7( -; ANY-NEXT: [[SQRTF:%.*]] = call float @sqrtf(float [[X:%.*]]) [[NUW_RO:#[0-9]+]] +; ANY-NEXT: [[SQRTF:%.*]] = call float @sqrtf(float [[X:%.*]]) [[NUW_RO]] ; ANY-NEXT: [[ABS:%.*]] = call float @llvm.fabs.f32(float [[SQRTF]]) ; ANY-NEXT: [[ISINF:%.*]] = fcmp oeq float [[X]], 0xFFF0000000000000 ; ANY-NEXT: [[TMP1:%.*]] = select i1 [[ISINF]], float 0x7FF0000000000000, float [[ABS]] @@ -330,7 +351,6 @@ ret <2 x double> %r } -declare double @llvm.pow.f64(double %Val, double %Power) define double @test_simplify17(double %x) { ; ANY-LABEL: @test_simplify17( ; ANY-NEXT: [[SQRT:%.*]] = call double @llvm.sqrt.f64(double [[X:%.*]])