maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp

621 lines
25 KiB
C++
Raw Blame History

//===- InstCombineVectorOps.cpp -------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements instcombine for ExtractElement, InsertElement and
// ShuffleVector.
//
//===----------------------------------------------------------------------===//
#include "InstCombine.h"
using namespace llvm;
/// CheapToScalarize - Return true if the value is cheaper to scalarize than it
/// is to leave as a vector operation.
static bool CheapToScalarize(Value *V, bool isConstant) {
if (isa<ConstantAggregateZero>(V))
return true;
if (ConstantVector *C = dyn_cast<ConstantVector>(V)) {
if (isConstant) return true;
// If all elts are the same, we can extract.
Constant *Op0 = C->getOperand(0);
for (unsigned i = 1; i < C->getNumOperands(); ++i)
if (C->getOperand(i) != Op0)
return false;
return true;
}
Instruction *I = dyn_cast<Instruction>(V);
if (!I) return false;
// Insert element gets simplified to the inserted element or is deleted if
// this is constant idx extract element and its a constant idx insertelt.
if (I->getOpcode() == Instruction::InsertElement && isConstant &&
isa<ConstantInt>(I->getOperand(2)))
return true;
if (I->getOpcode() == Instruction::Load && I->hasOneUse())
return true;
if (BinaryOperator *BO = dyn_cast<BinaryOperator>(I))
if (BO->hasOneUse() &&
(CheapToScalarize(BO->getOperand(0), isConstant) ||
CheapToScalarize(BO->getOperand(1), isConstant)))
return true;
if (CmpInst *CI = dyn_cast<CmpInst>(I))
if (CI->hasOneUse() &&
(CheapToScalarize(CI->getOperand(0), isConstant) ||
CheapToScalarize(CI->getOperand(1), isConstant)))
return true;
return false;
}
/// Read and decode a shufflevector mask.
///
/// It turns undef elements into values that are larger than the number of
/// elements in the input.
static std::vector<unsigned> getShuffleMask(const ShuffleVectorInst *SVI) {
unsigned NElts = SVI->getType()->getNumElements();
if (isa<ConstantAggregateZero>(SVI->getOperand(2)))
return std::vector<unsigned>(NElts, 0);
if (isa<UndefValue>(SVI->getOperand(2)))
return std::vector<unsigned>(NElts, 2*NElts);
std::vector<unsigned> Result;
const ConstantVector *CP = cast<ConstantVector>(SVI->getOperand(2));
for (User::const_op_iterator i = CP->op_begin(), e = CP->op_end(); i!=e; ++i)
if (isa<UndefValue>(*i))
Result.push_back(NElts*2); // undef -> 8
else
Result.push_back(cast<ConstantInt>(*i)->getZExtValue());
return Result;
}
/// FindScalarElement - Given a vector and an element number, see if the scalar
/// value is already around as a register, for example if it were inserted then
/// extracted from the vector.
static Value *FindScalarElement(Value *V, unsigned EltNo) {
assert(V->getType()->isVectorTy() && "Not looking at a vector?");
const VectorType *PTy = cast<VectorType>(V->getType());
unsigned Width = PTy->getNumElements();
if (EltNo >= Width) // Out of range access.
return UndefValue::get(PTy->getElementType());
if (isa<UndefValue>(V))
return UndefValue::get(PTy->getElementType());
if (isa<ConstantAggregateZero>(V))
return Constant::getNullValue(PTy->getElementType());
if (ConstantVector *CP = dyn_cast<ConstantVector>(V))
return CP->getOperand(EltNo);
if (InsertElementInst *III = dyn_cast<InsertElementInst>(V)) {
// If this is an insert to a variable element, we don't know what it is.
if (!isa<ConstantInt>(III->getOperand(2)))
return 0;
unsigned IIElt = cast<ConstantInt>(III->getOperand(2))->getZExtValue();
// If this is an insert to the element we are looking for, return the
// inserted value.
if (EltNo == IIElt)
return III->getOperand(1);
// Otherwise, the insertelement doesn't modify the value, recurse on its
// vector input.
return FindScalarElement(III->getOperand(0), EltNo);
}
if (ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(V)) {
unsigned LHSWidth =
cast<VectorType>(SVI->getOperand(0)->getType())->getNumElements();
unsigned InEl = getShuffleMask(SVI)[EltNo];
if (InEl < LHSWidth)
return FindScalarElement(SVI->getOperand(0), InEl);
else if (InEl < LHSWidth*2)
return FindScalarElement(SVI->getOperand(1), InEl - LHSWidth);
else
return UndefValue::get(PTy->getElementType());
}
// Otherwise, we don't know.
return 0;
}
Instruction *InstCombiner::visitExtractElementInst(ExtractElementInst &EI) {
// If vector val is undef, replace extract with scalar undef.
if (isa<UndefValue>(EI.getOperand(0)))
return ReplaceInstUsesWith(EI, UndefValue::get(EI.getType()));
// If vector val is constant 0, replace extract with scalar 0.
if (isa<ConstantAggregateZero>(EI.getOperand(0)))
return ReplaceInstUsesWith(EI, Constant::getNullValue(EI.getType()));
if (ConstantVector *C = dyn_cast<ConstantVector>(EI.getOperand(0))) {
// If vector val is constant with all elements the same, replace EI with
// that element. When the elements are not identical, we cannot replace yet
// (we do that below, but only when the index is constant).
Constant *op0 = C->getOperand(0);
for (unsigned i = 1; i != C->getNumOperands(); ++i)
if (C->getOperand(i) != op0) {
op0 = 0;
break;
}
if (op0)
return ReplaceInstUsesWith(EI, op0);
}
// If extracting a specified index from the vector, see if we can recursively
// find a previously computed scalar that was inserted into the vector.
if (ConstantInt *IdxC = dyn_cast<ConstantInt>(EI.getOperand(1))) {
unsigned IndexVal = IdxC->getZExtValue();
unsigned VectorWidth = EI.getVectorOperandType()->getNumElements();
// If this is extracting an invalid index, turn this into undef, to avoid
// crashing the code below.
if (IndexVal >= VectorWidth)
return ReplaceInstUsesWith(EI, UndefValue::get(EI.getType()));
// This instruction only demands the single element from the input vector.
// If the input vector has a single use, simplify it based on this use
// property.
if (EI.getOperand(0)->hasOneUse() && VectorWidth != 1) {
APInt UndefElts(VectorWidth, 0);
APInt DemandedMask(VectorWidth, 0);
DemandedMask.set(IndexVal);
if (Value *V = SimplifyDemandedVectorElts(EI.getOperand(0),
DemandedMask, UndefElts)) {
EI.setOperand(0, V);
return &EI;
}
}
if (Value *Elt = FindScalarElement(EI.getOperand(0), IndexVal))
return ReplaceInstUsesWith(EI, Elt);
// If the this extractelement is directly using a bitcast from a vector of
// the same number of elements, see if we can find the source element from
// it. In this case, we will end up needing to bitcast the scalars.
if (BitCastInst *BCI = dyn_cast<BitCastInst>(EI.getOperand(0))) {
if (const VectorType *VT =
dyn_cast<VectorType>(BCI->getOperand(0)->getType()))
if (VT->getNumElements() == VectorWidth)
if (Value *Elt = FindScalarElement(BCI->getOperand(0), IndexVal))
return new BitCastInst(Elt, EI.getType());
}
}
if (Instruction *I = dyn_cast<Instruction>(EI.getOperand(0))) {
// Push extractelement into predecessor operation if legal and
// profitable to do so
if (BinaryOperator *BO = dyn_cast<BinaryOperator>(I)) {
if (I->hasOneUse() &&
CheapToScalarize(BO, isa<ConstantInt>(EI.getOperand(1)))) {
Value *newEI0 =
Builder->CreateExtractElement(BO->getOperand(0), EI.getOperand(1),
EI.getName()+".lhs");
Value *newEI1 =
Builder->CreateExtractElement(BO->getOperand(1), EI.getOperand(1),
EI.getName()+".rhs");
return BinaryOperator::Create(BO->getOpcode(), newEI0, newEI1);
}
} else if (InsertElementInst *IE = dyn_cast<InsertElementInst>(I)) {
// Extracting the inserted element?
if (IE->getOperand(2) == EI.getOperand(1))
return ReplaceInstUsesWith(EI, IE->getOperand(1));
// If the inserted and extracted elements are constants, they must not
// be the same value, extract from the pre-inserted value instead.
if (isa<Constant>(IE->getOperand(2)) && isa<Constant>(EI.getOperand(1))) {
Worklist.AddValue(EI.getOperand(0));
EI.setOperand(0, IE->getOperand(0));
return &EI;
}
} else if (ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(I)) {
// If this is extracting an element from a shufflevector, figure out where
// it came from and extract from the appropriate input element instead.
if (ConstantInt *Elt = dyn_cast<ConstantInt>(EI.getOperand(1))) {
unsigned SrcIdx = getShuffleMask(SVI)[Elt->getZExtValue()];
Value *Src;
unsigned LHSWidth =
cast<VectorType>(SVI->getOperand(0)->getType())->getNumElements();
if (SrcIdx < LHSWidth)
Src = SVI->getOperand(0);
else if (SrcIdx < LHSWidth*2) {
SrcIdx -= LHSWidth;
Src = SVI->getOperand(1);
} else {
return ReplaceInstUsesWith(EI, UndefValue::get(EI.getType()));
}
return ExtractElementInst::Create(Src,
ConstantInt::get(Type::getInt32Ty(EI.getContext()),
SrcIdx, false));
}
}
// FIXME: Canonicalize extractelement(bitcast) -> bitcast(extractelement)
}
return 0;
}
/// CollectSingleShuffleElements - If V is a shuffle of values that ONLY returns
/// elements from either LHS or RHS, return the shuffle mask and true.
/// Otherwise, return false.
static bool CollectSingleShuffleElements(Value *V, Value *LHS, Value *RHS,
std::vector<Constant*> &Mask) {
assert(V->getType() == LHS->getType() && V->getType() == RHS->getType() &&
"Invalid CollectSingleShuffleElements");
unsigned NumElts = cast<VectorType>(V->getType())->getNumElements();
if (isa<UndefValue>(V)) {
Mask.assign(NumElts, UndefValue::get(Type::getInt32Ty(V->getContext())));
return true;
}
if (V == LHS) {
for (unsigned i = 0; i != NumElts; ++i)
Mask.push_back(ConstantInt::get(Type::getInt32Ty(V->getContext()), i));
return true;
}
if (V == RHS) {
for (unsigned i = 0; i != NumElts; ++i)
Mask.push_back(ConstantInt::get(Type::getInt32Ty(V->getContext()),
i+NumElts));
return true;
}
if (InsertElementInst *IEI = dyn_cast<InsertElementInst>(V)) {
// If this is an insert of an extract from some other vector, include it.
Value *VecOp = IEI->getOperand(0);
Value *ScalarOp = IEI->getOperand(1);
Value *IdxOp = IEI->getOperand(2);
if (!isa<ConstantInt>(IdxOp))
return false;
unsigned InsertedIdx = cast<ConstantInt>(IdxOp)->getZExtValue();
if (isa<UndefValue>(ScalarOp)) { // inserting undef into vector.
// Okay, we can handle this if the vector we are insertinting into is
// transitively ok.
if (CollectSingleShuffleElements(VecOp, LHS, RHS, Mask)) {
// If so, update the mask to reflect the inserted undef.
Mask[InsertedIdx] = UndefValue::get(Type::getInt32Ty(V->getContext()));
return true;
}
} else if (ExtractElementInst *EI = dyn_cast<ExtractElementInst>(ScalarOp)){
if (isa<ConstantInt>(EI->getOperand(1)) &&
EI->getOperand(0)->getType() == V->getType()) {
unsigned ExtractedIdx =
cast<ConstantInt>(EI->getOperand(1))->getZExtValue();
// This must be extracting from either LHS or RHS.
if (EI->getOperand(0) == LHS || EI->getOperand(0) == RHS) {
// Okay, we can handle this if the vector we are insertinting into is
// transitively ok.
if (CollectSingleShuffleElements(VecOp, LHS, RHS, Mask)) {
// If so, update the mask to reflect the inserted value.
if (EI->getOperand(0) == LHS) {
Mask[InsertedIdx % NumElts] =
ConstantInt::get(Type::getInt32Ty(V->getContext()),
ExtractedIdx);
} else {
assert(EI->getOperand(0) == RHS);
Mask[InsertedIdx % NumElts] =
ConstantInt::get(Type::getInt32Ty(V->getContext()),
ExtractedIdx+NumElts);
}
return true;
}
}
}
}
}
// TODO: Handle shufflevector here!
return false;
}
/// CollectShuffleElements - We are building a shuffle of V, using RHS as the
/// RHS of the shuffle instruction, if it is not null. Return a shuffle mask
/// that computes V and the LHS value of the shuffle.
static Value *CollectShuffleElements(Value *V, std::vector<Constant*> &Mask,
Value *&RHS) {
assert(V->getType()->isVectorTy() &&
(RHS == 0 || V->getType() == RHS->getType()) &&
"Invalid shuffle!");
unsigned NumElts = cast<VectorType>(V->getType())->getNumElements();
if (isa<UndefValue>(V)) {
Mask.assign(NumElts, UndefValue::get(Type::getInt32Ty(V->getContext())));
return V;
} else if (isa<ConstantAggregateZero>(V)) {
Mask.assign(NumElts, ConstantInt::get(Type::getInt32Ty(V->getContext()),0));
return V;
} else if (InsertElementInst *IEI = dyn_cast<InsertElementInst>(V)) {
// If this is an insert of an extract from some other vector, include it.
Value *VecOp = IEI->getOperand(0);
Value *ScalarOp = IEI->getOperand(1);
Value *IdxOp = IEI->getOperand(2);
if (ExtractElementInst *EI = dyn_cast<ExtractElementInst>(ScalarOp)) {
if (isa<ConstantInt>(EI->getOperand(1)) && isa<ConstantInt>(IdxOp) &&
EI->getOperand(0)->getType() == V->getType()) {
unsigned ExtractedIdx =
cast<ConstantInt>(EI->getOperand(1))->getZExtValue();
unsigned InsertedIdx = cast<ConstantInt>(IdxOp)->getZExtValue();
// Either the extracted from or inserted into vector must be RHSVec,
// otherwise we'd end up with a shuffle of three inputs.
if (EI->getOperand(0) == RHS || RHS == 0) {
RHS = EI->getOperand(0);
Value *V = CollectShuffleElements(VecOp, Mask, RHS);
Mask[InsertedIdx % NumElts] =
ConstantInt::get(Type::getInt32Ty(V->getContext()),
NumElts+ExtractedIdx);
return V;
}
if (VecOp == RHS) {
Value *V = CollectShuffleElements(EI->getOperand(0), Mask, RHS);
// Everything but the extracted element is replaced with the RHS.
for (unsigned i = 0; i != NumElts; ++i) {
if (i != InsertedIdx)
Mask[i] = ConstantInt::get(Type::getInt32Ty(V->getContext()),
NumElts+i);
}
return V;
}
// If this insertelement is a chain that comes from exactly these two
// vectors, return the vector and the effective shuffle.
if (CollectSingleShuffleElements(IEI, EI->getOperand(0), RHS, Mask))
return EI->getOperand(0);
}
}
}
// TODO: Handle shufflevector here!
// Otherwise, can't do anything fancy. Return an identity vector.
for (unsigned i = 0; i != NumElts; ++i)
Mask.push_back(ConstantInt::get(Type::getInt32Ty(V->getContext()), i));
return V;
}
Instruction *InstCombiner::visitInsertElementInst(InsertElementInst &IE) {
Value *VecOp = IE.getOperand(0);
Value *ScalarOp = IE.getOperand(1);
Value *IdxOp = IE.getOperand(2);
// Inserting an undef or into an undefined place, remove this.
if (isa<UndefValue>(ScalarOp) || isa<UndefValue>(IdxOp))
ReplaceInstUsesWith(IE, VecOp);
// If the inserted element was extracted from some other vector, and if the
// indexes are constant, try to turn this into a shufflevector operation.
if (ExtractElementInst *EI = dyn_cast<ExtractElementInst>(ScalarOp)) {
if (isa<ConstantInt>(EI->getOperand(1)) && isa<ConstantInt>(IdxOp) &&
EI->getOperand(0)->getType() == IE.getType()) {
unsigned NumVectorElts = IE.getType()->getNumElements();
unsigned ExtractedIdx =
cast<ConstantInt>(EI->getOperand(1))->getZExtValue();
unsigned InsertedIdx = cast<ConstantInt>(IdxOp)->getZExtValue();
if (ExtractedIdx >= NumVectorElts) // Out of range extract.
return ReplaceInstUsesWith(IE, VecOp);
if (InsertedIdx >= NumVectorElts) // Out of range insert.
return ReplaceInstUsesWith(IE, UndefValue::get(IE.getType()));
// If we are extracting a value from a vector, then inserting it right
// back into the same place, just use the input vector.
if (EI->getOperand(0) == VecOp && ExtractedIdx == InsertedIdx)
return ReplaceInstUsesWith(IE, VecOp);
// If this insertelement isn't used by some other insertelement, turn it
// (and any insertelements it points to), into one big shuffle.
if (!IE.hasOneUse() || !isa<InsertElementInst>(IE.use_back())) {
std::vector<Constant*> Mask;
Value *RHS = 0;
Value *LHS = CollectShuffleElements(&IE, Mask, RHS);
if (RHS == 0) RHS = UndefValue::get(LHS->getType());
// We now have a shuffle of LHS, RHS, Mask.
return new ShuffleVectorInst(LHS, RHS,
ConstantVector::get(Mask));
}
}
}
unsigned VWidth = cast<VectorType>(VecOp->getType())->getNumElements();
APInt UndefElts(VWidth, 0);
APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
if (SimplifyDemandedVectorElts(&IE, AllOnesEltMask, UndefElts))
return &IE;
return 0;
}
Instruction *InstCombiner::visitShuffleVectorInst(ShuffleVectorInst &SVI) {
Value *LHS = SVI.getOperand(0);
Value *RHS = SVI.getOperand(1);
std::vector<unsigned> Mask = getShuffleMask(&SVI);
bool MadeChange = false;
// Undefined shuffle mask -> undefined value.
if (isa<UndefValue>(SVI.getOperand(2)))
return ReplaceInstUsesWith(SVI, UndefValue::get(SVI.getType()));
unsigned VWidth = Mask.size();
unsigned LHSWidth = cast<VectorType>(LHS->getType())->getNumElements();
APInt UndefElts(VWidth, 0);
APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
if (SimplifyDemandedVectorElts(&SVI, AllOnesEltMask, UndefElts)) {
LHS = SVI.getOperand(0);
RHS = SVI.getOperand(1);
MadeChange = true;
}
// Canonicalize shuffle(x ,x,mask) -> shuffle(x, undef,mask')
// Canonicalize shuffle(undef,x,mask) -> shuffle(x, undef,mask').
if (LHS == RHS || isa<UndefValue>(LHS)) {
if (isa<UndefValue>(LHS) && LHS == RHS)
return ReplaceInstUsesWith(SVI, UndefValue::get(SVI.getType()));
// Remap any references to RHS to use LHS.
std::vector<Constant*> Elts;
for (unsigned i = 0, e = LHSWidth; i != VWidth; ++i) {
if (Mask[i] >= 2*e)
Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
else {
if ((Mask[i] >= e && isa<UndefValue>(RHS)) ||
(Mask[i] < e && isa<UndefValue>(LHS))) {
Mask[i] = 2*e; // Turn into undef.
Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
} else {
Mask[i] = Mask[i] % e; // Force to LHS.
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
Mask[i]));
}
}
}
SVI.setOperand(0, SVI.getOperand(1));
SVI.setOperand(1, UndefValue::get(RHS->getType()));
SVI.setOperand(2, ConstantVector::get(Elts));
LHS = SVI.getOperand(0);
RHS = SVI.getOperand(1);
MadeChange = true;
}
// Analyze the shuffle, are the LHS or RHS and identity shuffles?
if (VWidth == LHSWidth) {
bool isLHSID = true, isRHSID = true;
for (unsigned i = 0, e = Mask.size(); i != e; ++i) {
if (Mask[i] >= e*2) continue; // Ignore undef values.
// Is this an identity shuffle of the LHS value?
isLHSID &= (Mask[i] == i);
// Is this an identity shuffle of the RHS value?
isRHSID &= (Mask[i]-e == i);
}
// Eliminate identity shuffles.
if (isLHSID) return ReplaceInstUsesWith(SVI, LHS);
if (isRHSID) return ReplaceInstUsesWith(SVI, RHS);
}
// Check for a handful of important shuffle(shuffle()) combinations.
ShuffleVectorInst *LSVI = dyn_cast<ShuffleVectorInst>(LHS);
if (!LSVI)
return MadeChange ? &SVI : 0;
LHS = LSVI->getOperand(0);
std::vector<unsigned> LHSMask = getShuffleMask(LSVI);
unsigned LHSInNElts = cast<VectorType>(LHS->getType())->getNumElements();
// If the LHS is an identity shuffle, or if SVI + LHS form a full unpack
// operation, merge the LHS and SVI shuffles. This allows llvm to emit
// efficient code for matrix transposes written with generic vector ops.
bool isLHSLoExtract = true, isLHSHiExtract = true;
bool isUnpackLo = isPowerOf2_32(VWidth);
bool isUnpackHi = isPowerOf2_32(VWidth);
for (unsigned i = 0, e = LHSMask.size(); i != e; ++i) {
if (LHSMask[i] >= LHSInNElts*2) continue; // Ignore undef values;
isLHSLoExtract &= (LHSMask[i] == i);
isLHSHiExtract &= (LHSMask[i] == i+(LHSInNElts/2));
isUnpackLo &= (LHSMask[i] == (i/2));
isUnpackHi &= (LHSMask[i] == (i/2) + (e/2));
}
for (unsigned i = 0, e = Mask.size(); i != e && (isUnpackLo || isUnpackHi);
i += 2) {
isUnpackLo &= (Mask[i] == i) && (Mask[i+1] == (i/2)+e);
isUnpackHi &= (Mask[i] == i) && (Mask[i+1] == (i/2)+e+(e/2));
}
if ((isLHSLoExtract || isLHSHiExtract || isUnpackLo || isUnpackHi) &&
(isa<UndefValue>(RHS) || (LHSWidth == LHSInNElts))) {
std::vector<Constant*> Elts;
for (unsigned i = 0, e = VWidth; i != e; ++i) {
if (Mask[i] >= 2*LHSWidth)
Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
else if (Mask[i] >= e)
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
Mask[i]));
else
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
LHSMask[Mask[i]]));
}
if (isa<UndefValue>(RHS))
RHS = UndefValue::get(LHS->getType());
return new ShuffleVectorInst(LHS, RHS, ConstantVector::get(Elts));
}
// If rhs is shuffle + identity, propagate.
if (ShuffleVectorInst *RSVI = dyn_cast<ShuffleVectorInst>(RHS)) {
std::vector<unsigned> RHSMask = getShuffleMask(RSVI);
unsigned RHSInNElts =
cast<VectorType>(RSVI->getOperand(0)->getType())->getNumElements();
// If rhs is identity, propagate
bool isRHSLoExtract = true, isRHSHiExtract = true;
for (unsigned i = 0, e = RHSMask.size(); i != e; ++i) {
if (RHSMask[i] >= RHSInNElts*2) continue; // Ignore undef values;
isRHSLoExtract &= (RHSMask[i] == i);
isRHSHiExtract &= (RHSMask[i] == i+(RHSInNElts/2));
}
if ((isRHSLoExtract || isRHSHiExtract) && (LHSWidth == RHSInNElts)) {
std::vector<Constant*> Elts;
for (unsigned i = 0, e = VWidth; i != e; ++i) {
if (Mask[i] >= 2*LHSWidth)
Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
else if (Mask[i] < LHSWidth)
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
Mask[i]));
else
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
RHSMask[Mask[i]-LHSWidth]+LHSWidth));
}
SVI.setOperand(1, RSVI->getOperand(0));
SVI.setOperand(2, ConstantVector::get(Elts));
return &SVI;
}
}
// Be extremely conservative when merging shufflevector instructions. It is
// difficult for the code generator to recognize a merged shuffle, which
// usually leads to worse code from merging a shuffle.
if (!isa<UndefValue>(RHS))
return MadeChange ? &SVI : 0;
// If the merged shuffle mask is one of the two input shuffle masks, which
// just removes one instruction. This should handle splat(splat) -> splat.
if (LHSMask.size() == Mask.size()) {
std::vector<unsigned> NewMask;
for (unsigned i = 0, e = Mask.size(); i != e; ++i)
if (Mask[i] >= e)
NewMask.push_back(2*e);
else
NewMask.push_back(LHSMask[Mask[i]]);
// If the result mask is equal to the src shuffle or this shuffle mask,
// do the replacement.
if (NewMask == LHSMask || NewMask == Mask) {
std::vector<Constant*> Elts;
for (unsigned i = 0, e = NewMask.size(); i != e; ++i) {
if (NewMask[i] >= LHSInNElts*2) {
Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
} else {
Elts.push_back(ConstantInt::get(Type::getInt32Ty(SVI.getContext()),
NewMask[i]));
}
}
return new ShuffleVectorInst(LHS, LSVI->getOperand(1),
ConstantVector::get(Elts));
}
}
return MadeChange ? &SVI : 0;
}
Reference in New Issue View Git Blame Copy Permalink