[InstCombine] pow(C,x) -> exp2(log2(C)*x)

Summary:
Transform
pow(C,x) 

To
exp2(log2(C)*x) 

if C > 0, C != inf, C != NaN (and C is not power of 2, since we have some fold for such case already).

log(C) is folded by the compiler and exp2 is much faster to compute than pow.

Reviewers: spatel, efriedma, evandro

Reviewed By: evandro

Subscribers: lebedev.ri, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D64099

llvm-svn: 365637

3 files changed, 64 insertions, 25 deletions

diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
index 54961f375d8..b481d2b50a8 100644
--- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -1235,7 +1235,8 @@ static Value *getPow(Value *InnerChain[33], unsigned Exp, IRBuilder<> &B) {
 }
 
 /// Use exp{,2}(x * y) for pow(exp{,2}(x), y);
-/// exp2(n * x) for pow(2.0 ** n, x); exp10(x) for pow(10.0, x).
+/// exp2(n * x) for pow(2.0 ** n, x); exp10(x) for pow(10.0, x);
+/// exp2(log2(C)*x) for pow(C,x).
 Value *LibCallSimplifier::replacePowWithExp(CallInst *Pow, IRBuilder<> &B) {
   Value *Base = Pow->getArgOperand(0), *Expo = Pow->getArgOperand(1);
   AttributeList Attrs = Pow->getCalledFunction()->getAttributes();
@@ -1347,6 +1348,28 @@ Value *LibCallSimplifier::replacePowWithExp(CallInst *Pow, IRBuilder<> &B) {
     return emitUnaryFloatFnCall(Expo, TLI, LibFunc_exp10, LibFunc_exp10f,
                                 LibFunc_exp10l, B, Attrs);
 
+  // pow(C,x) -> exp2(log2(C)*x)
+  if (Pow->hasOneUse() && Pow->hasApproxFunc() && Pow->hasNoNaNs() &&
+      Pow->hasNoInfs() && BaseF->isNormal() && !BaseF->isNegative()) {
+    Value *Log = nullptr;
+    if (Ty->isFloatTy())
+      Log = ConstantFP::get(Ty, std::log2(BaseF->convertToFloat()));
+    else if (Ty->isDoubleTy())
+      Log = ConstantFP::get(Ty, std::log2(BaseF->convertToDouble()));
+
+    if (Log) {
+      Value *FMul = B.CreateFMul(Log, Expo, "mul");
+      if (Pow->doesNotAccessMemory()) {
+        return B.CreateCall(Intrinsic::getDeclaration(Mod, Intrinsic::exp2, Ty),
+                            FMul, "exp2");
+      } else {
+        if (hasUnaryFloatFn(TLI, Ty, LibFunc_exp2, LibFunc_exp2f,
+                            LibFunc_exp2l))
+          return emitUnaryFloatFnCall(FMul, TLI, LibFunc_exp2, LibFunc_exp2f,
+                                      LibFunc_exp2l, B, Attrs);
+      }
+    }
+  }
   return nullptr;
 }
 
diff --git a/llvm/test/Transforms/InstCombine/pow-exp.ll b/llvm/test/Transforms/InstCombine/pow-exp.ll
index 9bc871cfc1e..d5ed5111781 100644
--- a/llvm/test/Transforms/InstCombine/pow-exp.ll
+++ b/llvm/test/Transforms/InstCombine/pow-exp.ll
@@ -205,13 +205,16 @@ define double @function_pointer(double ()* %fptr, double %p1) {
   ret double %pow
 }
 
+; pow(C,x) -> exp2(log2(C)*x)
+
 declare void @use_d(double)
 declare void @use_f(float)
 
 define double @pow_ok_base(double %e) {
 ; CHECK-LABEL: @pow_ok_base(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn double @pow(double 0x3FE6666666666666, double [[E:%.*]])
-; CHECK-NEXT:    ret double [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn double [[E:%.*]], 0xBFE0776228967D13
+; CHECK-NEXT:    [[EXP2:%.*]] = call nnan ninf afn double @exp2(double [[MUL]])
+; CHECK-NEXT:    ret double [[EXP2]]
 ;
   %call = tail call afn nnan ninf double @pow(double 0x3FE6666666666666, double %e)
   ret double %call
@@ -219,8 +222,9 @@ define double @pow_ok_base(double %e) {
 
 define double @pow_ok_base_fast(double %e) {
 ; CHECK-LABEL: @pow_ok_base_fast(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call fast double @pow(double 0x3FE6666666666666, double [[E:%.*]])
-; CHECK-NEXT:    ret double [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul fast double [[E:%.*]], 0xBFE0776228967D13
+; CHECK-NEXT:    [[EXP2:%.*]] = call fast double @exp2(double [[MUL]])
+; CHECK-NEXT:    ret double [[EXP2]]
 ;
   %call = tail call fast double @pow(double 0x3FE6666666666666, double %e)
   ret double %call
@@ -228,8 +232,9 @@ define double @pow_ok_base_fast(double %e) {
 
 define double @pow_ok_base2(double %e) {
 ; CHECK-LABEL: @pow_ok_base2(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn double @pow(double 1.770000e+01, double [[E:%.*]])
-; CHECK-NEXT:    ret double [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn double [[E:%.*]], 0x4010952C788751AC
+; CHECK-NEXT:    [[EXP2:%.*]] = call nnan ninf afn double @exp2(double [[MUL]])
+; CHECK-NEXT:    ret double [[EXP2]]
 ;
   %call = tail call afn nnan ninf double @pow(double 1.770000e+01, double %e)
   ret double %call
@@ -237,8 +242,9 @@ define double @pow_ok_base2(double %e) {
 
 define double @pow_ok_base3(double %e) {
 ; CHECK-LABEL: @pow_ok_base3(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn double @pow(double 1.010000e+01, double [[E:%.*]])
-; CHECK-NEXT:    ret double [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn double [[E:%.*]], 0x400AB0B5584886CD
+; CHECK-NEXT:    [[EXP2:%.*]] = call nnan ninf afn double @exp2(double [[MUL]])
+; CHECK-NEXT:    ret double [[EXP2]]
 ;
   %call = tail call afn nnan ninf double @pow(double 1.010000e+01, double %e)
   ret double %call
@@ -246,8 +252,9 @@ define double @pow_ok_base3(double %e) {
 
 define double @pow_ok_ten_base(double %e) {
 ; CHECK-LABEL: @pow_ok_ten_base(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn double @pow(double 1.000000e+01, double [[E:%.*]])
-; CHECK-NEXT:    ret double [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn double [[E:%.*]], 0x400A934F0979A371
+; CHECK-NEXT:    [[EXP2:%.*]] = call nnan ninf afn double @exp2(double [[MUL]])
+; CHECK-NEXT:    ret double [[EXP2]]
 ;
   %call = tail call afn nnan ninf double @pow(double 1.000000e+01, double %e)
   ret double %call
@@ -255,8 +262,9 @@ define double @pow_ok_ten_base(double %e) {
 
 define float @powf_ok_base(float %e) {
 ; CHECK-LABEL: @powf_ok_base(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn float @powf(float 0x3FE6666660000000, float [[E:%.*]])
-; CHECK-NEXT:    ret float [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn float [[E:%.*]], 0xBFE0776240000000
+; CHECK-NEXT:    [[EXP2F:%.*]] = call nnan ninf afn float @exp2f(float [[MUL]])
+; CHECK-NEXT:    ret float [[EXP2F]]
 ;
   %call = tail call afn nnan ninf float @powf(float 0x3FE6666660000000, float %e)
   ret float %call
@@ -264,8 +272,9 @@ define float @powf_ok_base(float %e) {
 
 define float @powf_ok_base2(float %e) {
 ; CHECK-LABEL: @powf_ok_base2(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn float @powf(float 0x4031B33340000000, float [[E:%.*]])
-; CHECK-NEXT:    ret float [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn float [[E:%.*]], 0x4010952C80000000
+; CHECK-NEXT:    [[EXP2F:%.*]] = call nnan ninf afn float @exp2f(float [[MUL]])
+; CHECK-NEXT:    ret float [[EXP2F]]
 ;
   %call = tail call afn nnan ninf float @powf(float 0x4031B33340000000, float %e)
   ret float %call
@@ -273,8 +282,9 @@ define float @powf_ok_base2(float %e) {
 
 define float @powf_ok_base3(float %e) {
 ; CHECK-LABEL: @powf_ok_base3(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn float @powf(float 0x4024333340000000, float [[E:%.*]])
-; CHECK-NEXT:    ret float [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn float [[E:%.*]], 0x400AB0B560000000
+; CHECK-NEXT:    [[EXP2F:%.*]] = call nnan ninf afn float @exp2f(float [[MUL]])
+; CHECK-NEXT:    ret float [[EXP2F]]
 ;
   %call = tail call afn nnan ninf float @powf(float 0x4024333340000000, float %e)
   ret float %call
@@ -282,13 +292,16 @@ define float @powf_ok_base3(float %e) {
 
 define float @powf_ok_ten_base(float %e) {
 ; CHECK-LABEL: @powf_ok_ten_base(
-; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn float @powf(float 1.000000e+01, float [[E:%.*]])
-; CHECK-NEXT:    ret float [[CALL]]
+; CHECK-NEXT:    [[MUL:%.*]] = fmul nnan ninf afn float [[E:%.*]], 0x400A934F00000000
+; CHECK-NEXT:    [[EXP2F:%.*]] = call nnan ninf afn float @exp2f(float [[MUL]])
+; CHECK-NEXT:    ret float [[EXP2F]]
 ;
   %call = tail call afn nnan ninf float @powf(float 1.000000e+01, float %e)
   ret float %call
 }
 
+; Negative tests
+
 define double @pow_zero_base(double %e) {
 ; CHECK-LABEL: @pow_zero_base(
 ; CHECK-NEXT:    [[CALL:%.*]] = tail call nnan ninf afn double @pow(double 0.000000e+00, double [[E:%.*]])
diff --git a/llvm/test/Transforms/InstCombine/pow_fp_int.ll b/llvm/test/Transforms/InstCombine/pow_fp_int.ll
index ff5ac896073..f89353cd707 100644
--- a/llvm/test/Transforms/InstCombine/pow_fp_int.ll
+++ b/llvm/test/Transforms/InstCombine/pow_fp_int.ll
@@ -196,8 +196,9 @@ define double @powf_exp_const2_int_fast(double %base) {
 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:    [[MUL:%.*]] = fmul fast float [[SUBFP]], 0x4006757680000000
+; 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
@@ -247,8 +248,9 @@ define double @pow_uitofp_double_base_fast_i32(double %base, i32 %x) {
 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:    [[MUL:%.*]] = fmul fast float [[SUBFP]], 0x4006757680000000
+; 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 = sitofp i64 %x to float
@@ -260,8 +262,9 @@ define double @pow_sitofp_const_base_fast_i64(i64 %x) {
 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:    [[MUL:%.*]] = fmul fast float [[SUBFP]], 0x4006757680000000
+; 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 i64 %x to float