6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-06-13 22:24:07 +00:00
Code Issues Projects Releases Wiki Activity

Cost model support for lowered math builtins.

Browse Source 
We make the cost for calling libm functions extremely high as emitting the
calls is expensive and causes spills (on x86) so performance suffers. We still
vectorize important calls like ceilf and friends on SSE4.1. and fabs.

Differential Revision: http://llvm-reviews.chandlerc.com/D466

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176287 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Benjamin Kramer
2013-02-28 19:09:33 +00:00
parent 279706e90e
commit 8611d4449a
3 changed files with 110 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
lib/CodeGen/BasicTargetTransformInfo.cpp
View File

@ -379,22 +379,77 @@ unsigned BasicTTI::getMemoryOpCost(unsigned Opcode, Type *Src,
return LT.first;
}
unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID, Type *RetTy,
unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<Type *> Tys) const {
// assume that we need to scalarize this intrinsic.
unsigned ScalarizationCost = 0;
unsigned ScalarCalls = 1;
if (RetTy->isVectorTy()) {
ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
}
for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
if (Tys[i]->isVectorTy()) {
ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
unsigned ISD = 0;
switch (IID) {
default: {
// Assume that we need to scalarize this intrinsic.
unsigned ScalarizationCost = 0;
unsigned ScalarCalls = 1;
if (RetTy->isVectorTy()) {
ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
}
for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
if (Tys[i]->isVectorTy()) {
ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
}
}
return ScalarCalls + ScalarizationCost;
}
return ScalarCalls + ScalarizationCost;
// Look for intrinsics that can be lowered directly or turned into a scalar
// intrinsic call.
case Intrinsic::sqrt: ISD = ISD::FSQRT; break;
case Intrinsic::sin: ISD = ISD::FSIN; break;
case Intrinsic::cos: ISD = ISD::FCOS; break;
case Intrinsic::exp: ISD = ISD::FEXP; break;
case Intrinsic::exp2: ISD = ISD::FEXP2; break;
case Intrinsic::log: ISD = ISD::FLOG; break;
case Intrinsic::log10: ISD = ISD::FLOG10; break;
case Intrinsic::log2: ISD = ISD::FLOG2; break;
case Intrinsic::fabs: ISD = ISD::FABS; break;
case Intrinsic::floor: ISD = ISD::FFLOOR; break;
case Intrinsic::ceil: ISD = ISD::FCEIL; break;
case Intrinsic::trunc: ISD = ISD::FTRUNC; break;
case Intrinsic::rint: ISD = ISD::FRINT; break;
case Intrinsic::pow: ISD = ISD::FPOW; break;
case Intrinsic::fma: ISD = ISD::FMA; break;
case Intrinsic::fmuladd: ISD = ISD::FMA; break; // FIXME: mul + add?
}
std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(RetTy);
if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
// The operation is legal. Assume it costs 1.
// If the type is split to multiple registers, assume that thre is some
// overhead to this.
// TODO: Once we have extract/insert subvector cost we need to use them.
if (LT.first > 1)
return LT.first * 2;
return LT.first * 1;
}
if (!TLI->isOperationExpand(ISD, LT.second)) {
// If the operation is custom lowered then assume
// thare the code is twice as expensive.
return LT.first * 2;
}
// Else, assume that we need to scalarize this intrinsic. For math builtins
// this will emit a costly libcall, adding call overhead and spills. Make it
// very expensive.
if (RetTy->isVectorTy()) {
unsigned Num = RetTy->getVectorNumElements();
unsigned Cost = TopTTI->getIntrinsicInstrCost(IID, RetTy->getScalarType(),
Tys);
return 10 * Cost * Num;
}
// This is going to be turned into a library call, make it expensive.
return 10;
}
unsigned BasicTTI::getNumberOfParts(Type *Tp) const {