[llvm] r364940 - [SimplifyLibCalls] powf(x, sitofp(n)) -> powi(x, n)
David Bolvansky via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 2 08:58:46 PDT 2019
Author: xbolva00
Date: Tue Jul 2 08:58:45 2019
New Revision: 364940
URL: http://llvm.org/viewvc/llvm-project?rev=364940&view=rev
Log:
[SimplifyLibCalls] powf(x, sitofp(n)) -> powi(x, n)
Summary:
Partially solves https://bugs.llvm.org/show_bug.cgi?id=42190
Reviewers: spatel, nikic, efriedma
Reviewed By: efriedma
Subscribers: efriedma, nikic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63038
Modified:
llvm/trunk/lib/Transforms/Utils/SimplifyLibCalls.cpp
llvm/trunk/test/Transforms/InstCombine/pow-4.ll
llvm/trunk/test/Transforms/InstCombine/pow_fp_int.ll
Modified: llvm/trunk/lib/Transforms/Utils/SimplifyLibCalls.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Utils/SimplifyLibCalls.cpp?rev=364940&r1=364939&r2=364940&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Utils/SimplifyLibCalls.cpp (original)
+++ llvm/trunk/lib/Transforms/Utils/SimplifyLibCalls.cpp Tue Jul 2 08:58:45 2019
@@ -1322,12 +1322,12 @@ Value *LibCallSimplifier::replacePowWith
APFloat BaseR = APFloat(1.0);
BaseR.convert(BaseF->getSemantics(), APFloat::rmTowardZero, &Ignored);
BaseR = BaseR / *BaseF;
- bool IsInteger = BaseF->isInteger(),
- IsReciprocal = BaseR.isInteger();
+ 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) &&
+ NF->convertToInteger(NI, APFloat::rmTowardZero, &Ignored) ==
+ APFloat::opOK &&
NI > 1 && NI.isPowerOf2()) {
double N = NI.logBase2() * (IsReciprocal ? -1.0 : 1.0);
Value *FMul = B.CreateFMul(Expo, ConstantFP::get(Ty, N), "mul");
@@ -1410,12 +1410,22 @@ Value *LibCallSimplifier::replacePowWith
return Sqrt;
}
+static Value *createPowWithIntegerExponent(Value *Base, Value *Expo, Module *M,
+ IRBuilder<> &B) {
+ Value *Args[] = {Base, Expo};
+ Function *F = Intrinsic::getDeclaration(M, Intrinsic::powi, Base->getType());
+ return B.CreateCall(F, Args);
+}
+
Value *LibCallSimplifier::optimizePow(CallInst *Pow, IRBuilder<> &B) {
- Value *Base = Pow->getArgOperand(0), *Expo = Pow->getArgOperand(1);
+ Value *Base = Pow->getArgOperand(0);
+ Value *Expo = Pow->getArgOperand(1);
Function *Callee = Pow->getCalledFunction();
StringRef Name = Callee->getName();
Type *Ty = Pow->getType();
+ Module *M = Pow->getModule();
Value *Shrunk = nullptr;
+ bool AllowApprox = Pow->hasApproxFunc();
bool Ignored;
// Bail out if simplifying libcalls to pow() is disabled.
@@ -1428,8 +1438,8 @@ Value *LibCallSimplifier::optimizePow(Ca
// Shrink pow() to powf() if the arguments are single precision,
// unless the result is expected to be double precision.
- if (UnsafeFPShrink &&
- Name == TLI->getName(LibFunc_pow) && hasFloatVersion(Name))
+ if (UnsafeFPShrink && Name == TLI->getName(LibFunc_pow) &&
+ hasFloatVersion(Name))
Shrunk = optimizeBinaryDoubleFP(Pow, B, true);
// Evaluate special cases related to the base.
@@ -1438,6 +1448,21 @@ Value *LibCallSimplifier::optimizePow(Ca
if (match(Base, m_FPOne()))
return Base;
+ // powf(x, sitofp(e)) -> powi(x, e)
+ // powf(x, uitofp(e)) -> powi(x, e)
+ if (AllowApprox && (isa<SIToFPInst>(Expo) || isa<UIToFPInst>(Expo))) {
+ Value *IntExpo = cast<Instruction>(Expo)->getOperand(0);
+ Value *NewExpo = nullptr;
+ unsigned BitWidth = IntExpo->getType()->getPrimitiveSizeInBits();
+ if (isa<SIToFPInst>(Expo) && BitWidth == 32)
+ NewExpo = IntExpo;
+ else if (BitWidth < 32)
+ NewExpo = isa<SIToFPInst>(Expo) ? B.CreateSExt(IntExpo, B.getInt32Ty())
+ : B.CreateZExt(IntExpo, B.getInt32Ty());
+ if (NewExpo)
+ return createPowWithIntegerExponent(Base, NewExpo, M, B);
+ }
+
if (Value *Exp = replacePowWithExp(Pow, B))
return Exp;
@@ -1449,7 +1474,7 @@ Value *LibCallSimplifier::optimizePow(Ca
// pow(x, 0.0) -> 1.0
if (match(Expo, m_SpecificFP(0.0)))
- return ConstantFP::get(Ty, 1.0);
+ return ConstantFP::get(Ty, 1.0);
// pow(x, 1.0) -> x
if (match(Expo, m_FPOne()))
@@ -1462,9 +1487,12 @@ Value *LibCallSimplifier::optimizePow(Ca
if (Value *Sqrt = replacePowWithSqrt(Pow, B))
return Sqrt;
+ if (!AllowApprox)
+ return Shrunk;
+
// pow(x, n) -> x * x * x * ...
const APFloat *ExpoF;
- if (Pow->isFast() && match(Expo, m_APFloat(ExpoF))) {
+ if (match(Expo, m_APFloat(ExpoF))) {
// We limit to a max of 7 multiplications, thus the maximum exponent is 32.
// If the exponent is an integer+0.5 we generate a call to sqrt and an
// additional fmul.
@@ -1488,9 +1516,8 @@ Value *LibCallSimplifier::optimizePow(Ca
if (!Expo2.isInteger())
return nullptr;
- Sqrt =
- getSqrtCall(Base, Pow->getCalledFunction()->getAttributes(),
- Pow->doesNotAccessMemory(), Pow->getModule(), B, TLI);
+ Sqrt = getSqrtCall(Base, Pow->getCalledFunction()->getAttributes(),
+ Pow->doesNotAccessMemory(), M, B, TLI);
}
// We will memoize intermediate products of the Addition Chain.
@@ -1513,6 +1540,14 @@ Value *LibCallSimplifier::optimizePow(Ca
return FMul;
}
+
+ APSInt IntExpo(32, /*isUnsigned=*/false);
+ // powf(x, C) -> powi(x, C) iff C is a constant signed integer value
+ if (ExpoF->convertToInteger(IntExpo, APFloat::rmTowardZero, &Ignored) ==
+ APFloat::opOK) {
+ return createPowWithIntegerExponent(
+ Base, ConstantInt::get(B.getInt32Ty(), IntExpo), M, B);
+ }
}
return Shrunk;
@@ -3101,4 +3136,4 @@ Value *FortifiedLibCallSimplifier::optim
FortifiedLibCallSimplifier::FortifiedLibCallSimplifier(
const TargetLibraryInfo *TLI, bool OnlyLowerUnknownSize)
- : TLI(TLI), OnlyLowerUnknownSize(OnlyLowerUnknownSize) {}
+ : TLI(TLI), OnlyLowerUnknownSize(OnlyLowerUnknownSize) {}
\ No newline at end of file
Modified: llvm/trunk/test/Transforms/InstCombine/pow-4.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/pow-4.ll?rev=364940&r1=364939&r2=364940&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/pow-4.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/pow-4.ll Tue Jul 2 08:58:45 2019
@@ -11,9 +11,9 @@ declare double @pow(double, double)
; pow(x, 3.0)
define double @test_simplify_3(double %x) {
; CHECK-LABEL: @test_simplify_3(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[X:%.*]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast double [[TMP1]], [[X]]
-; CHECK-NEXT: ret double [[TMP2]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[SQUARE]], [[X]]
+; CHECK-NEXT: ret double [[TMP1]]
;
%1 = call fast double @llvm.pow.f64(double %x, double 3.000000e+00)
ret double %1
@@ -22,9 +22,9 @@ define double @test_simplify_3(double %x
; powf(x, 4.0)
define float @test_simplify_4f(float %x) {
; CHECK-LABEL: @test_simplify_4f(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[TMP1]], [[TMP1]]
-; CHECK-NEXT: ret float [[TMP2]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast float [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[SQUARE]], [[SQUARE]]
+; CHECK-NEXT: ret float [[TMP1]]
;
%1 = call fast float @llvm.pow.f32(float %x, float 4.000000e+00)
ret float %1
@@ -33,9 +33,9 @@ define float @test_simplify_4f(float %x)
; pow(x, 4.0)
define double @test_simplify_4(double %x) {
; CHECK-LABEL: @test_simplify_4(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[X:%.*]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast double [[TMP1]], [[TMP1]]
-; CHECK-NEXT: ret double [[TMP2]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[SQUARE]], [[SQUARE]]
+; CHECK-NEXT: ret double [[TMP1]]
;
%1 = call fast double @llvm.pow.f64(double %x, double 4.000000e+00)
ret double %1
@@ -44,12 +44,12 @@ define double @test_simplify_4(double %x
; powf(x, <15.0, 15.0>)
define <2 x float> @test_simplify_15(<2 x float> %x) {
; CHECK-LABEL: @test_simplify_15(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <2 x float> [[X:%.*]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <2 x float> [[TMP1]], [[X]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast <2 x float> [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <2 x float> [[SQUARE]], [[X]]
+; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <2 x float> [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <2 x float> [[TMP2]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = fmul fast <2 x float> [[TMP3]], [[TMP3]]
-; CHECK-NEXT: [[TMP5:%.*]] = fmul fast <2 x float> [[TMP2]], [[TMP4]]
-; CHECK-NEXT: ret <2 x float> [[TMP5]]
+; CHECK-NEXT: [[TMP4:%.*]] = fmul fast <2 x float> [[TMP1]], [[TMP3]]
+; CHECK-NEXT: ret <2 x float> [[TMP4]]
;
%1 = call fast <2 x float> @llvm.pow.v2f32(<2 x float> %x, <2 x float> <float 1.500000e+01, float 1.500000e+01>)
ret <2 x float> %1
@@ -58,12 +58,12 @@ define <2 x float> @test_simplify_15(<2
; pow(x, -7.0)
define <2 x double> @test_simplify_neg_7(<2 x double> %x) {
; CHECK-LABEL: @test_simplify_neg_7(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <2 x double> [[X:%.*]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <2 x double> [[TMP1]], [[TMP1]]
-; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <2 x double> [[TMP2]], [[X]]
-; CHECK-NEXT: [[TMP4:%.*]] = fmul fast <2 x double> [[TMP1]], [[TMP3]]
-; CHECK-NEXT: [[TMP5:%.*]] = fdiv fast <2 x double> <double 1.000000e+00, double 1.000000e+00>, [[TMP4]]
-; CHECK-NEXT: ret <2 x double> [[TMP5]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast <2 x double> [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <2 x double> [[SQUARE]], [[SQUARE]]
+; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <2 x double> [[TMP1]], [[X]]
+; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <2 x double> [[SQUARE]], [[TMP2]]
+; CHECK-NEXT: [[RECIPROCAL:%.*]] = fdiv fast <2 x double> <double 1.000000e+00, double 1.000000e+00>, [[TMP3]]
+; CHECK-NEXT: ret <2 x double> [[RECIPROCAL]]
;
%1 = call fast <2 x double> @llvm.pow.v2f64(<2 x double> %x, <2 x double> <double -7.000000e+00, double -7.000000e+00>)
ret <2 x double> %1
@@ -72,14 +72,14 @@ define <2 x double> @test_simplify_neg_7
; powf(x, -19.0)
define float @test_simplify_neg_19(float %x) {
; CHECK-LABEL: @test_simplify_neg_19(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[X]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast float [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[SQUARE]], [[SQUARE]]
; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast float [[TMP2]], [[TMP2]]
-; CHECK-NEXT: [[TMP4:%.*]] = fmul fast float [[TMP3]], [[TMP3]]
-; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[TMP1]], [[TMP4]]
-; CHECK-NEXT: [[TMP6:%.*]] = fmul fast float [[TMP5]], [[X]]
-; CHECK-NEXT: [[TMP7:%.*]] = fdiv fast float 1.000000e+00, [[TMP6]]
-; CHECK-NEXT: ret float [[TMP7]]
+; CHECK-NEXT: [[TMP4:%.*]] = fmul fast float [[SQUARE]], [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[TMP4]], [[X]]
+; CHECK-NEXT: [[RECIPROCAL:%.*]] = fdiv fast float 1.000000e+00, [[TMP5]]
+; CHECK-NEXT: ret float [[RECIPROCAL]]
;
%1 = call fast float @llvm.pow.f32(float %x, float -1.900000e+01)
ret float %1
@@ -98,12 +98,12 @@ define double @test_simplify_11_23(doubl
; powf(x, 32.0)
define float @test_simplify_32(float %x) {
; CHECK-LABEL: @test_simplify_32(
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[X]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast float [[X:%.*]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast float [[SQUARE]], [[SQUARE]]
; CHECK-NEXT: [[TMP2:%.*]] = fmul fast float [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast float [[TMP2]], [[TMP2]]
; CHECK-NEXT: [[TMP4:%.*]] = fmul fast float [[TMP3]], [[TMP3]]
-; CHECK-NEXT: [[TMP5:%.*]] = fmul fast float [[TMP4]], [[TMP4]]
-; CHECK-NEXT: ret float [[TMP5]]
+; CHECK-NEXT: ret float [[TMP4]]
;
%1 = call fast float @llvm.pow.f32(float %x, float 3.200000e+01)
ret float %1
@@ -112,7 +112,7 @@ define float @test_simplify_32(float %x)
; pow(x, 33.0)
define double @test_simplify_33(double %x) {
; CHECK-LABEL: @test_simplify_33(
-; CHECK-NEXT: [[TMP1:%.*]] = call fast double @llvm.pow.f64(double [[X:%.*]], double 3.300000e+01)
+; CHECK-NEXT: [[TMP1:%.*]] = call fast double @llvm.powi.f64(double [[X:%.*]], i32 33)
; CHECK-NEXT: ret double [[TMP1]]
;
%1 = call fast double @llvm.pow.f64(double %x, double 3.300000e+01)
@@ -122,8 +122,8 @@ define double @test_simplify_33(double %
; pow(x, 16.5) with double
define double @test_simplify_16_5(double %x) {
; CHECK-LABEL: @test_simplify_16_5(
-; CHECK-NEXT: [[SQRT:%.*]] = call fast double @llvm.sqrt.f64(double [[X]])
-; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X:%.*]], [[X]]
+; CHECK-NEXT: [[SQRT:%.*]] = call fast double @llvm.sqrt.f64(double [[X:%.*]])
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[SQUARE]], [[SQUARE]]
; CHECK-NEXT: [[TMP2:%.*]] = fmul fast double [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast double [[TMP2]], [[TMP2]]
@@ -137,8 +137,8 @@ define double @test_simplify_16_5(double
; pow(x, -16.5) with double
define double @test_simplify_neg_16_5(double %x) {
; CHECK-LABEL: @test_simplify_neg_16_5(
-; CHECK-NEXT: [[SQRT:%.*]] = call fast double @llvm.sqrt.f64(double [[X]])
-; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X:%.*]], [[X]]
+; CHECK-NEXT: [[SQRT:%.*]] = call fast double @llvm.sqrt.f64(double [[X:%.*]])
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast double [[X]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast double [[SQUARE]], [[SQUARE]]
; CHECK-NEXT: [[TMP2:%.*]] = fmul fast double [[TMP1]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = fmul fast double [[TMP2]], [[TMP2]]
@@ -214,10 +214,10 @@ define <2 x double> @test_simplify_7_5(<
define <4 x float> @test_simplify_3_5(<4 x float> %x) {
; CHECK-LABEL: @test_simplify_3_5(
; CHECK-NEXT: [[SQRT:%.*]] = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> [[X:%.*]])
-; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <4 x float> [[X]], [[X]]
-; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <4 x float> [[TMP1]], [[X]]
-; CHECK-NEXT: [[TMP3:%.*]] = fmul fast <4 x float> [[TMP2]], [[SQRT]]
-; CHECK-NEXT: ret <4 x float> [[TMP3]]
+; CHECK-NEXT: [[SQUARE:%.*]] = fmul fast <4 x float> [[X]], [[X]]
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <4 x float> [[SQUARE]], [[X]]
+; CHECK-NEXT: [[TMP2:%.*]] = fmul fast <4 x float> [[TMP1]], [[SQRT]]
+; CHECK-NEXT: ret <4 x float> [[TMP2]]
;
%1 = call fast <4 x float> @llvm.pow.v4f32(<4 x float> %x, <4 x float> <float 3.500000e+00, float 3.500000e+00, float 3.500000e+00, float 3.500000e+00>)
ret <4 x float> %1
Modified: llvm/trunk/test/Transforms/InstCombine/pow_fp_int.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/pow_fp_int.ll?rev=364940&r1=364939&r2=364940&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/pow_fp_int.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/pow_fp_int.ll Tue Jul 2 08:58:45 2019
@@ -5,74 +5,294 @@
define double @pow_sitofp_const_base_fast(i32 %x) {
; CHECK-LABEL: @pow_sitofp_const_base_fast(
-; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to float
-; CHECK-NEXT: [[POWI:%.*]] = tail call fast float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
-; CHECK-NEXT: [[RES:%.*]] = fpext float [[POWI]] to double
+; CHECK-NEXT: [[TMP1:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[X:%.*]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP1]] to double
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call fast float @llvm.pow.f32(float 7.000000e+00, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
-define double @pow_sitofp_const_base_power_of_2_fast(i32 %x) {
-; CHECK-LABEL: @pow_sitofp_const_base_power_of_2_fast(
-; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to float
-; CHECK-NEXT: [[MUL:%.*]] = fmul fast float [[SUBFP]], 4.000000e+00
-; CHECK-NEXT: [[EXP2:%.*]] = call fast float @llvm.exp2.f32(float [[MUL]])
-; CHECK-NEXT: [[RES:%.*]] = fpext float [[EXP2]] to double
+define double @pow_uitofp_const_base_fast(i31 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i31 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i31 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_sitofp_double_const_base_fast(i32 %x) {
+; CHECK-LABEL: @pow_sitofp_double_const_base_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = call afn double @llvm.powi.f64(double 7.000000e+00, i32 [[X:%.*]])
+; CHECK-NEXT: ret double [[TMP1]]
+;
+ %subfp = sitofp i32 %x to double
+ %pow = tail call afn double @llvm.pow.f64(double 7.000000e+00, double %subfp)
+ ret double %pow
+}
+
+define double @pow_uitofp_double_const_base_fast(i31 %x) {
+; CHECK-LABEL: @pow_uitofp_double_const_base_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i31 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn double @llvm.powi.f64(double 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: ret double [[TMP2]]
+;
+ %subfp = uitofp i31 %x to double
+ %pow = tail call afn double @llvm.pow.f64(double 7.000000e+00, double %subfp)
+ ret double %pow
+}
+
+define double @pow_sitofp_double_const_base_power_of_2_fast(i32 %x) {
+; CHECK-LABEL: @pow_sitofp_double_const_base_power_of_2_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = call afn float @llvm.powi.f32(float 1.600000e+01, i32 [[X:%.*]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP1]] to double
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call fast float @llvm.pow.f32(float 16.000000e+00, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call afn float @llvm.pow.f32(float 16.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_power_of_2_fast(i31 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_power_of_2_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i31 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 1.600000e+01, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i31 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 16.000000e+00, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
define double @pow_sitofp_float_base_fast(float %base, i32 %x) {
; CHECK-LABEL: @pow_sitofp_float_base_fast(
-; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to float
-; CHECK-NEXT: [[POWI:%.*]] = tail call fast float @llvm.pow.f32(float [[BASE:%.*]], float [[SUBFP]])
-; CHECK-NEXT: [[RES:%.*]] = fpext float [[POWI]] to double
+; CHECK-NEXT: [[TMP1:%.*]] = call afn float @llvm.powi.f32(float [[BASE:%.*]], i32 [[X:%.*]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP1]] to double
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call fast float @llvm.pow.f32(float %base, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call afn float @llvm.pow.f32(float %base, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_float_base_fast(float %base, i31 %x) {
+; CHECK-LABEL: @pow_uitofp_float_base_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i31 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float [[BASE:%.*]], i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i31 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float %base, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
define double @pow_sitofp_double_base_fast(double %base, i32 %x) {
; CHECK-LABEL: @pow_sitofp_double_base_fast(
-; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to double
-; CHECK-NEXT: [[RES:%.*]] = tail call fast double @llvm.pow.f64(double [[BASE:%.*]], double [[SUBFP]])
-; CHECK-NEXT: ret double [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = call afn double @llvm.powi.f64(double [[BASE:%.*]], i32 [[X:%.*]])
+; CHECK-NEXT: ret double [[TMP1]]
;
%subfp = sitofp i32 %x to double
- %res = tail call fast double @llvm.pow.f64(double %base, double %subfp)
+ %res = tail call afn double @llvm.pow.f64(double %base, double %subfp)
+ ret double %res
+}
+
+define double @pow_uitofp_double_base_fast(double %base, i31 %x) {
+; CHECK-LABEL: @pow_uitofp_double_base_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i31 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn double @llvm.powi.f64(double [[BASE:%.*]], i32 [[TMP1]])
+; CHECK-NEXT: ret double [[TMP2]]
+;
+ %subfp = uitofp i31 %x to double
+ %res = tail call afn double @llvm.pow.f64(double %base, double %subfp)
+ ret double %res
+}
+
+define double @pow_sitofp_const_base_fast_i8(i8 %x) {
+; CHECK-LABEL: @pow_sitofp_const_base_fast_i8(
+; CHECK-NEXT: [[TMP1:%.*]] = sext i8 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = sitofp i8 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_sitofp_const_base_fast_i16(i16 %x) {
+; CHECK-LABEL: @pow_sitofp_const_base_fast_i16(
+; CHECK-NEXT: [[TMP1:%.*]] = sext i16 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = sitofp i16 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+
+define double @pow_uitofp_const_base_fast_i8(i8 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_fast_i8(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i8 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_fast_i16(i16 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_fast_i16(
+; CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[X:%.*]] to i32
+; CHECK-NEXT: [[TMP2:%.*]] = call afn float @llvm.powi.f32(float 7.000000e+00, i32 [[TMP1]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[TMP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i16 %x to float
+ %pow = tail call afn float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
define double @powf_exp_const_int_fast(double %base) {
; CHECK-LABEL: @powf_exp_const_int_fast(
-; CHECK-NEXT: [[RES:%.*]] = tail call fast double @llvm.pow.f64(double [[BASE:%.*]], double 4.000000e+01)
-; CHECK-NEXT: ret double [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = call fast double @llvm.powi.f64(double [[BASE:%.*]], i32 40)
+; CHECK-NEXT: ret double [[TMP1]]
;
%res = tail call fast double @llvm.pow.f64(double %base, double 4.000000e+01)
ret double %res
}
+define double @powf_exp_const2_int_fast(double %base) {
+; CHECK-LABEL: @powf_exp_const2_int_fast(
+; CHECK-NEXT: [[TMP1:%.*]] = call fast double @llvm.powi.f64(double [[BASE:%.*]], i32 -40)
+; CHECK-NEXT: ret double [[TMP1]]
+;
+ %res = tail call fast double @llvm.pow.f64(double %base, double -4.000000e+01)
+ ret double %res
+}
+
+; Negative tests
+
+define double @pow_uitofp_const_base_fast_i32(i32 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_fast_i32(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call fast float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call fast float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_power_of_2_fast_i32(i32 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_power_of_2_fast_i32(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[MUL:%.*]] = fmul fast float [[SUBFP]], 4.000000e+00
+; CHECK-NEXT: [[EXP2:%.*]] = call fast float @llvm.exp2.f32(float [[MUL]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[EXP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call fast float @llvm.pow.f32(float 16.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_float_base_fast_i32(float %base, i32 %x) {
+; CHECK-LABEL: @pow_uitofp_float_base_fast_i32(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call fast float @llvm.pow.f32(float [[BASE:%.*]], float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call fast float @llvm.pow.f32(float %base, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_double_base_fast_i32(double %base, i32 %x) {
+; CHECK-LABEL: @pow_uitofp_double_base_fast_i32(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to double
+; CHECK-NEXT: [[RES:%.*]] = tail call fast double @llvm.pow.f64(double [[BASE:%.*]], double [[SUBFP]])
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to double
+ %res = tail call fast double @llvm.pow.f64(double %base, double %subfp)
+ ret double %res
+}
+
+define double @pow_sitofp_const_base_fast_i64(i64 %x) {
+; CHECK-LABEL: @pow_sitofp_const_base_fast_i64(
+; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i64 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call fast float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = sitofp i64 %x to float
+ %pow = tail call fast float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_fast_i64(i64 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_fast_i64(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i64 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call fast float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i64 %x to float
+ %pow = tail call fast float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
define double @pow_sitofp_const_base_no_fast(i32 %x) {
; CHECK-LABEL: @pow_sitofp_const_base_no_fast(
; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to float
-; CHECK-NEXT: [[POWI:%.*]] = tail call float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
-; CHECK-NEXT: [[RES:%.*]] = fpext float [[POWI]] to double
+; CHECK-NEXT: [[POW:%.*]] = tail call float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call float @llvm.pow.f32(float 7.000000e+00, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_no_fast(i32 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_no_fast(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call float @llvm.pow.f32(float 7.000000e+00, float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call float @llvm.pow.f32(float 7.000000e+00, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
@@ -85,33 +305,71 @@ define double @pow_sitofp_const_base_pow
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call float @llvm.pow.f32(float 16.000000e+00, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call float @llvm.pow.f32(float 16.000000e+00, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_const_base_power_of_2_no_fast(i32 %x) {
+; CHECK-LABEL: @pow_uitofp_const_base_power_of_2_no_fast(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[MUL:%.*]] = fmul float [[SUBFP]], 4.000000e+00
+; CHECK-NEXT: [[EXP2:%.*]] = call float @llvm.exp2.f32(float [[MUL]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[EXP2]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call float @llvm.pow.f32(float 16.000000e+00, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
define double @pow_sitofp_float_base_no_fast(float %base, i32 %x) {
; CHECK-LABEL: @pow_sitofp_float_base_no_fast(
; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to float
-; CHECK-NEXT: [[POWI:%.*]] = tail call float @llvm.pow.f32(float [[BASE:%.*]], float [[SUBFP]])
-; CHECK-NEXT: [[RES:%.*]] = fpext float [[POWI]] to double
+; CHECK-NEXT: [[POW:%.*]] = tail call float @llvm.pow.f32(float [[BASE:%.*]], float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
; CHECK-NEXT: ret double [[RES]]
;
%subfp = sitofp i32 %x to float
- %powi = tail call float @llvm.pow.f32(float %base, float %subfp)
- %res = fpext float %powi to double
+ %pow = tail call float @llvm.pow.f32(float %base, float %subfp)
+ %res = fpext float %pow to double
+ ret double %res
+}
+
+define double @pow_uitofp_float_base_no_fast(float %base, i32 %x) {
+; CHECK-LABEL: @pow_uitofp_float_base_no_fast(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to float
+; CHECK-NEXT: [[POW:%.*]] = tail call float @llvm.pow.f32(float [[BASE:%.*]], float [[SUBFP]])
+; CHECK-NEXT: [[RES:%.*]] = fpext float [[POW]] to double
+; CHECK-NEXT: ret double [[RES]]
+;
+ %subfp = uitofp i32 %x to float
+ %pow = tail call float @llvm.pow.f32(float %base, float %subfp)
+ %res = fpext float %pow to double
ret double %res
}
define double @pow_sitofp_double_base_no_fast(double %base, i32 %x) {
; CHECK-LABEL: @pow_sitofp_double_base_no_fast(
; CHECK-NEXT: [[SUBFP:%.*]] = sitofp i32 [[X:%.*]] to double
-; CHECK-NEXT: [[POWI:%.*]] = tail call double @llvm.pow.f64(double [[BASE:%.*]], double [[SUBFP]])
-; CHECK-NEXT: ret double [[POWI]]
+; CHECK-NEXT: [[POW:%.*]] = tail call double @llvm.pow.f64(double [[BASE:%.*]], double [[SUBFP]])
+; CHECK-NEXT: ret double [[POW]]
;
%subfp = sitofp i32 %x to double
- %powi = tail call double @llvm.pow.f64(double %base, double %subfp)
- ret double %powi
+ %pow = tail call double @llvm.pow.f64(double %base, double %subfp)
+ ret double %pow
+}
+
+define double @pow_uitofp_double_base_no_fast(double %base, i32 %x) {
+; CHECK-LABEL: @pow_uitofp_double_base_no_fast(
+; CHECK-NEXT: [[SUBFP:%.*]] = uitofp i32 [[X:%.*]] to double
+; CHECK-NEXT: [[POW:%.*]] = tail call double @llvm.pow.f64(double [[BASE:%.*]], double [[SUBFP]])
+; CHECK-NEXT: ret double [[POW]]
+;
+ %subfp = uitofp i32 %x to double
+ %pow = tail call double @llvm.pow.f64(double %base, double %subfp)
+ ret double %pow
}
define double @powf_exp_const_int_no_fast(double %base) {
@@ -141,5 +399,14 @@ define double @powf_exp_const_not_int_no
ret double %res
}
+define double @powf_exp_const2_int_no_fast(double %base) {
+; CHECK-LABEL: @powf_exp_const2_int_no_fast(
+; CHECK-NEXT: [[RES:%.*]] = tail call double @llvm.pow.f64(double [[BASE:%.*]], double -4.000000e+01)
+; CHECK-NEXT: ret double [[RES]]
+;
+ %res = tail call double @llvm.pow.f64(double %base, double -4.000000e+01)
+ ret double %res
+}
+
declare float @llvm.pow.f32(float, float)
declare double @llvm.pow.f64(double, double)
More information about the llvm-commits
mailing list