maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Allow constant folding of fma and fmuladd 

llvm-svn: 202914
This commit is contained in:
Matt Arsenault 2014-03-05 00:02:00 +00:00
parent f8ecf9b447
commit 8377858c55
2 changed files with 66 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
llvm/lib/Analysis/ConstantFolding.cpp
View File

@ -1193,6 +1193,8 @@ bool llvm::canConstantFoldCallTo(const Function *F) {
case Intrinsic::ctpop:
case Intrinsic::ctlz:
case Intrinsic::cttz:
case Intrinsic::fma:
case Intrinsic::fmuladd:
case Intrinsic::sadd_with_overflow:
case Intrinsic::uadd_with_overflow:
case Intrinsic::ssub_with_overflow:
@ -1615,5 +1617,30 @@ llvm::ConstantFoldCall(Function *F, ArrayRef<Constant *> Operands,
}
return 0;
}
if (Operands.size() != 3)
return 0;
if (const ConstantFP *Op1 = dyn_cast<ConstantFP>(Operands[0])) {
if (const ConstantFP *Op2 = dyn_cast<ConstantFP>(Operands[1])) {
if (const ConstantFP *Op3 = dyn_cast<ConstantFP>(Operands[2])) {
switch (F->getIntrinsicID()) {
default: break;
case Intrinsic::fma:
case Intrinsic::fmuladd: {
APFloat V = Op1->getValueAPF();
APFloat::opStatus s = V.fusedMultiplyAdd(Op2->getValueAPF(),
Op3->getValueAPF(),
APFloat::rmNearestTiesToEven);
if (s != APFloat::opInvalidOp)
return ConstantFP::get(Ty->getContext(), V);
return 0;
}
}
}
}
}
return 0;
}

39
llvm/test/Transforms/InstCombine/constant-fold-math.ll Normal file
View File

@ -0,0 +1,39 @@
; RUN: opt -S -instcombine < %s | FileCheck %s
declare float @llvm.fma.f32(float, float, float) #0
declare float @llvm.fmuladd.f32(float, float, float) #0
declare double @llvm.fma.f64(double, double, double) #0
declare double @llvm.fmuladd.f64(double, double, double) #0
; CHECK-LABEL: @constant_fold_fma_f32
; CHECK-NEXT: ret float 6.000000e+00
define float @constant_fold_fma_f32() #0 {
%x = call float @llvm.fma.f32(float 1.0, float 2.0, float 4.0) #0
ret float %x
}
; CHECK-LABEL: @constant_fold_fmuladd_f32
; CHECK-NEXT: ret float 6.000000e+00
define float @constant_fold_fmuladd_f32() #0 {
%x = call float @llvm.fmuladd.f32(float 1.0, float 2.0, float 4.0) #0
ret float %x
}
; CHECK-LABEL: @constant_fold_fma_f64
; CHECK-NEXT: ret double 6.000000e+00
define double @constant_fold_fma_f64() #0 {
%x = call double @llvm.fma.f64(double 1.0, double 2.0, double 4.0) #0
ret double %x
}
; CHECK-LABEL: @constant_fold_fmuladd_f64
; CHECK-NEXT: ret double 6.000000e+00
define double @constant_fold_fmuladd_f64() #0 {
%x = call double @llvm.fmuladd.f64(double 1.0, double 2.0, double 4.0) #0
ret double %x
}
attributes #0 = { nounwind readnone }