6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-06-15 05:24:01 +00:00
Code Issues Projects Releases Wiki Activity

Handle sqrt() shrinking in SimplifyLibCalls like any other call

Browse Source 
This patch removes a chunk of special case logic for folding 
(float)sqrt((double)x) -> sqrtf(x)
in InstCombineCasts and handles it in the mainstream path of SimplifyLibCalls.

No functional change intended, but I loosened the restriction on the existing
sqrt testcases to allow for this optimization even without unsafe-fp-math because
that's the existing behavior.

I also added a missing test case for not shrinking the llvm.sqrt.f64 intrinsic
in case the result is used as a double.

Differential Revision: http://reviews.llvm.org/D5919



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220514 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel
2014-10-23 21:52:45 +00:00
parent 4d529076b6
commit d2153694e0
3 changed files with 33 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
lib/Transforms/Utils/SimplifyLibCalls.cpp
View File

@ -1058,7 +1058,16 @@ Value *LibCallSimplifier::optimizeUnaryDoubleFP(CallInst *CI, IRBuilder<> &B,
// floor((double)floatval) -> (double)floorf(floatval)
Value *V = Cast->getOperand(0);
V = EmitUnaryFloatFnCall(V, Callee->getName(), B, Callee->getAttributes());
if (Callee->isIntrinsic()) {
Module *M = CI->getParent()->getParent()->getParent();
Intrinsic::ID IID = (Intrinsic::ID) Callee->getIntrinsicID();
Function *F = Intrinsic::getDeclaration(M, IID, B.getFloatTy());
V = B.CreateCall(F, V);
} else {
// The call is a library call rather than an intrinsic.
V = EmitUnaryFloatFnCall(V, Callee->getName(), B, Callee->getAttributes());
}
return B.CreateFPExt(V, B.getDoubleTy());
}
@ -1086,6 +1095,7 @@ Value *LibCallSimplifier::optimizeBinaryDoubleFP(CallInst *CI, IRBuilder<> &B) {
Value *V = nullptr;
Value *V1 = Cast1->getOperand(0);
Value *V2 = Cast2->getOperand(0);
// TODO: Handle intrinsics in the same way as in optimizeUnaryDoubleFP().
V = EmitBinaryFloatFnCall(V1, V2, Callee->getName(), B,
Callee->getAttributes());
return B.CreateFPExt(V, B.getDoubleTy());
@ -1267,10 +1277,9 @@ Value *LibCallSimplifier::optimizeSqrt(CallInst *CI, IRBuilder<> &B) {
Function *Callee = CI->getCalledFunction();
Value *Ret = nullptr;
if (UnsafeFPShrink && Callee->getName() == "sqrt" &&
TLI->has(LibFunc::sqrtf)) {
if (TLI->has(LibFunc::sqrtf) && (Callee->getName() == "sqrt" ||
Callee->getIntrinsicID() == Intrinsic::sqrt))
Ret = optimizeUnaryDoubleFP(CI, B, true);
}
// FIXME: For finer-grain optimization, we need intrinsics to have the same
// fast-math flag decorations that are applied to FP instructions. For now,
@ -2010,7 +2019,7 @@ Value *LibCallSimplifier::optimizeCall(CallInst *CI) {
UnsafeFPShrink = true;
}
// Next check for intrinsics.
// First, check for intrinsics.
if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI)) {
if (!isCallingConvC)
return nullptr;