C++ ShuffleVectorInst类代码示例

bool InterleavedAccess::lowerInterleavedStore(
    StoreInst *SI, SmallVector<Instruction *, 32> &DeadInsts) {
  if (!SI->isSimple())
    return false;

  ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(SI->getValueOperand());
  if (!SVI || !SVI->hasOneUse())
    return false;

  // Check if the shufflevector is RE-interleave shuffle.
  unsigned Factor;
  if (!isReInterleaveMask(SVI->getShuffleMask(), Factor))
    return false;

  DEBUG(dbgs() << "IA: Found an interleaved store: " << *SI << "\n");

  // Try to create target specific intrinsics to replace the store and shuffle.
  if (!TLI->lowerInterleavedStore(SI, SVI, Factor))
    return false;

  // Already have a new target specific interleaved store. Erase the old store.
  DeadInsts.push_back(SI);
  DeadInsts.push_back(SVI);
  return true;
}

bool InterleavedAccess::lowerInterleavedLoad(
    LoadInst *LI, SmallVector<Instruction *, 32> &DeadInsts) {
  if (!LI->isSimple())
    return false;

  SmallVector<ShuffleVectorInst *, 4> Shuffles;

  // Check if all users of this load are shufflevectors.
  for (auto UI = LI->user_begin(), E = LI->user_end(); UI != E; UI++) {
    ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(*UI);
    if (!SVI || !isa<UndefValue>(SVI->getOperand(1)))
      return false;

    Shuffles.push_back(SVI);
  }

  if (Shuffles.empty())
    return false;

  unsigned Factor, Index;

  // Check if the first shufflevector is DE-interleave shuffle.
  if (!isDeInterleaveMask(Shuffles[0]->getShuffleMask(), Factor, Index))
    return false;

  // Holds the corresponding index for each DE-interleave shuffle.
  SmallVector<unsigned, 4> Indices;
  Indices.push_back(Index);

  Type *VecTy = Shuffles[0]->getType();

  // Check if other shufflevectors are also DE-interleaved of the same type
  // and factor as the first shufflevector.
  for (unsigned i = 1; i < Shuffles.size(); i++) {
    if (Shuffles[i]->getType() != VecTy)
      return false;

    if (!isDeInterleaveMaskOfFactor(Shuffles[i]->getShuffleMask(), Factor,
                                    Index))
      return false;

    Indices.push_back(Index);
  }

  DEBUG(dbgs() << "IA: Found an interleaved load: " << *LI << "\n");

  // Try to create target specific intrinsics to replace the load and shuffles.
  if (!TLI->lowerInterleavedLoad(LI, Shuffles, Indices, Factor))
    return false;

  for (auto SVI : Shuffles)
    DeadInsts.push_back(SVI);

  DeadInsts.push_back(LI);
  return true;
}

static bool isByteSwap64(ShuffleVectorInst &SI, SmallVector<int, 16>&RefMasks)
{

    RefMasks.clear();
    unsigned VWidth = cast<VectorType>(SI.getType())->getNumElements();
    VectorType *LHS = cast<VectorType>(SI.getOperand(0)->getType());
    VectorType *RHS = cast<VectorType>(SI.getOperand(1)->getType());

    IntegerType *IT = dyn_cast<IntegerType>(LHS->getElementType());
    //When Element Type is not IntegerType or the Result's element number
    //can't be divided by 8, return false
    //TODO:Need to check all masks are all constants.
    if (IT == nullptr
        || ! IT->isIntegerTy(8)
        || VWidth % 8 != 0) {
        return false;
    }

    SmallVector<int, 16> Masks(SI.getShuffleMask());
    bool isByteSwap = true;

    for (unsigned i = 0; i < VWidth / 8; ++i) {
        unsigned base = Masks[i * 8];
        if (base % 8 != 7) {
            isByteSwap = false;
            break;
        }

        for (unsigned j = 1; j < 8; ++j) {
            if (base - Masks[i * 8 + j] != j) {
                isByteSwap = false;
                break;
            }
        }

        if (isByteSwap) {
            RefMasks.push_back(base / 8);
        } else {
            break;
        }
    }

    if (!isByteSwap) {
        RefMasks.clear();
    }

    return isByteSwap;
}

bool Scalarizer::visitShuffleVectorInst(ShuffleVectorInst &SVI) {
  VectorType *VT = dyn_cast<VectorType>(SVI.getType());
  if (!VT)
    return false;

  unsigned NumElems = VT->getNumElements();
  Scatterer Op0 = scatter(&SVI, SVI.getOperand(0));
  Scatterer Op1 = scatter(&SVI, SVI.getOperand(1));
  ValueVector Res;
  Res.resize(NumElems);

  for (unsigned I = 0; I < NumElems; ++I) {
    int Selector = SVI.getMaskValue(I);
    if (Selector < 0)
      Res[I] = UndefValue::get(VT->getElementType());
    else if (unsigned(Selector) < Op0.size())
      Res[I] = Op0[Selector];
    else
      Res[I] = Op1[Selector - Op0.size()];
  }
  gather(&SVI, Res);
  return true;
}

// Returns true if the shuffle is extracting a contiguous range of values from
// LHS, for example:
//                 +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
//   Input:        |AA|BB|CC|DD|EE|FF|GG|HH|II|JJ|KK|LL|MM|NN|OO|PP|
//   Shuffles to:  |EE|FF|GG|HH|
//                 +--+--+--+--+
static bool isShuffleExtractingFromLHS(ShuffleVectorInst &SVI,
                                       SmallVector<int, 16> &Mask) {
  unsigned LHSElems =
      cast<VectorType>(SVI.getOperand(0)->getType())->getNumElements();
  unsigned MaskElems = Mask.size();
  unsigned BegIdx = Mask.front();
  unsigned EndIdx = Mask.back();
  if (BegIdx > EndIdx || EndIdx >= LHSElems || EndIdx - BegIdx != MaskElems - 1)
    return false;
  for (unsigned I = 0; I != MaskElems; ++I)
    if (static_cast<unsigned>(Mask[I]) != BegIdx + I)
      return false;
  return true;
}

Instruction *InstCombiner::visitShuffleVectorInst(ShuffleVectorInst &SVI) {
  Value *LHS = SVI.getOperand(0);
  Value *RHS = SVI.getOperand(1);
  SmallVector<int, 16> 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 = cast<VectorType>(SVI.getType())->getNumElements();

  APInt UndefElts(VWidth, 0);
  APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
  if (Value *V = SimplifyDemandedVectorElts(&SVI, AllOnesEltMask, UndefElts)) {
    if (V != &SVI)
      return ReplaceInstUsesWith(SVI, V);
    LHS = SVI.getOperand(0);
    RHS = SVI.getOperand(1);
    MadeChange = true;
  }

  unsigned LHSWidth = cast<VectorType>(LHS->getType())->getNumElements();

  // 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) {
      // shuffle(undef,undef,mask) -> undef.
      Value* result = (VWidth == LHSWidth)
                      ? LHS : UndefValue::get(SVI.getType());
      return ReplaceInstUsesWith(SVI, result);
    }

    // Remap any references to RHS to use LHS.
    std::vector<Constant*> Elts;
    for (unsigned i = 0, e = LHSWidth; i != VWidth; ++i) {
      if (Mask[i] < 0)
        Elts.push_back(UndefValue::get(Type::getInt32Ty(SVI.getContext())));
      else {
        if ((Mask[i] >= (int)e && isa<UndefValue>(RHS)) ||
            (Mask[i] <  (int)e && isa<UndefValue>(LHS))) {
          Mask[i] = -1;     // 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;
  }

  if (VWidth == LHSWidth) {
    // Analyze the shuffle, are the LHS or RHS and identity shuffles?
    bool isLHSID = true, isRHSID = true;

    for (unsigned i = 0, e = Mask.size(); i != e; ++i) {
      if (Mask[i] < 0) continue;  // Ignore undef values.
      // Is this an identity shuffle of the LHS value?
      isLHSID &= (Mask[i] == (int)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);
  }

  // If the LHS is a shufflevector itself, see if we can combine it with this
  // one without producing an unusual shuffle.
  // Cases that might be simplified:
  // 1.
  // x1=shuffle(v1,v2,mask1)
  //  x=shuffle(x1,undef,mask)
  //        ==>
  //  x=shuffle(v1,undef,newMask)
  // newMask[i] = (mask[i] < x1.size()) ? mask1[mask[i]] : -1
  // 2.
  // x1=shuffle(v1,undef,mask1)
  //  x=shuffle(x1,x2,mask)
  // where v1.size() == mask1.size()
  //        ==>
  //  x=shuffle(v1,x2,newMask)
  // newMask[i] = (mask[i] < x1.size()) ? mask1[mask[i]] : mask[i]
  // 3.
  // x2=shuffle(v2,undef,mask2)
  //  x=shuffle(x1,x2,mask)
  // where v2.size() == mask2.size()
  //        ==>
  //  x=shuffle(x1,v2,newMask)
//.........这里部分代码省略.........

static ReductionKind matchPairwiseReductionAtLevel(Instruction *I,
                                                   unsigned Level,
                                                   unsigned NumLevels) {
  // Match one level of pairwise operations.
  // %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef,
  //       <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef>
  // %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef,
  //       <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
  // %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
  if (!I)
    return RK_None;

  assert(I->getType()->isVectorTy() && "Expecting a vector type");

  Optional<ReductionData> RD = getReductionData(I);
  if (!RD)
    return RK_None;

  ShuffleVectorInst *LS = dyn_cast<ShuffleVectorInst>(RD->LHS);
  if (!LS && Level)
    return RK_None;
  ShuffleVectorInst *RS = dyn_cast<ShuffleVectorInst>(RD->RHS);
  if (!RS && Level)
    return RK_None;

  // On level 0 we can omit one shufflevector instruction.
  if (!Level && !RS && !LS)
    return RK_None;

  // Shuffle inputs must match.
  Value *NextLevelOpL = LS ? LS->getOperand(0) : nullptr;
  Value *NextLevelOpR = RS ? RS->getOperand(0) : nullptr;
  Value *NextLevelOp = nullptr;
  if (NextLevelOpR && NextLevelOpL) {
    // If we have two shuffles their operands must match.
    if (NextLevelOpL != NextLevelOpR)
      return RK_None;

    NextLevelOp = NextLevelOpL;
  } else if (Level == 0 && (NextLevelOpR || NextLevelOpL)) {
    // On the first level we can omit the shufflevector <0, undef,...>. So the
    // input to the other shufflevector <1, undef> must match with one of the
    // inputs to the current binary operation.
    // Example:
    //  %NextLevelOpL = shufflevector %R, <1, undef ...>
    //  %BinOp        = fadd          %NextLevelOpL, %R
    if (NextLevelOpL && NextLevelOpL != RD->RHS)
      return RK_None;
    else if (NextLevelOpR && NextLevelOpR != RD->LHS)
      return RK_None;

    NextLevelOp = NextLevelOpL ? RD->RHS : RD->LHS;
  } else
    return RK_None;

  // Check that the next levels binary operation exists and matches with the
  // current one.
  if (Level + 1 != NumLevels) {
    Optional<ReductionData> NextLevelRD =
        getReductionData(cast<Instruction>(NextLevelOp));
    if (!NextLevelRD || !RD->hasSameData(*NextLevelRD))
      return RK_None;
  }

  // Shuffle mask for pairwise operation must match.
  if (matchPairwiseShuffleMask(LS, /*IsLeft=*/true, Level)) {
    if (!matchPairwiseShuffleMask(RS, /*IsLeft=*/false, Level))
      return RK_None;
  } else if (matchPairwiseShuffleMask(RS, /*IsLeft=*/true, Level)) {
    if (!matchPairwiseShuffleMask(LS, /*IsLeft=*/false, Level))
      return RK_None;
  } else {
    return RK_None;
  }

  if (++Level == NumLevels)
    return RD->Kind;

  // Match next level.
  return matchPairwiseReductionAtLevel(cast<Instruction>(NextLevelOp), Level,
                                       NumLevels);
}

bool InterleavedAccess::lowerInterleavedLoad(
    LoadInst *LI, SmallVector<Instruction *, 32> &DeadInsts) {
  if (!LI->isSimple())
    return false;

  SmallVector<ShuffleVectorInst *, 4> Shuffles;
  SmallVector<ExtractElementInst *, 4> Extracts;

  // Check if all users of this load are shufflevectors. If we encounter any
  // users that are extractelement instructions, we save them to later check if
  // they can be modifed to extract from one of the shufflevectors instead of
  // the load.
  for (auto UI = LI->user_begin(), E = LI->user_end(); UI != E; UI++) {
    auto *Extract = dyn_cast<ExtractElementInst>(*UI);
    if (Extract && isa<ConstantInt>(Extract->getIndexOperand())) {
      Extracts.push_back(Extract);
      continue;
    }
    ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(*UI);
    if (!SVI || !isa<UndefValue>(SVI->getOperand(1)))
      return false;

    Shuffles.push_back(SVI);
  }

  if (Shuffles.empty())
    return false;

  unsigned Factor, Index;

  // Check if the first shufflevector is DE-interleave shuffle.
  if (!isDeInterleaveMask(Shuffles[0]->getShuffleMask(), Factor, Index,
                          MaxFactor))
    return false;

  // Holds the corresponding index for each DE-interleave shuffle.
  SmallVector<unsigned, 4> Indices;
  Indices.push_back(Index);

  Type *VecTy = Shuffles[0]->getType();

  // Check if other shufflevectors are also DE-interleaved of the same type
  // and factor as the first shufflevector.
  for (unsigned i = 1; i < Shuffles.size(); i++) {
    if (Shuffles[i]->getType() != VecTy)
      return false;

    if (!isDeInterleaveMaskOfFactor(Shuffles[i]->getShuffleMask(), Factor,
                                    Index))
      return false;

    Indices.push_back(Index);
  }

  // Try and modify users of the load that are extractelement instructions to
  // use the shufflevector instructions instead of the load.
  if (!tryReplaceExtracts(Extracts, Shuffles))
    return false;

  LLVM_DEBUG(dbgs() << "IA: Found an interleaved load: " << *LI << "\n");

  // Try to create target specific intrinsics to replace the load and shuffles.
  if (!TLI->lowerInterleavedLoad(LI, Shuffles, Indices, Factor))
    return false;

  for (auto SVI : Shuffles)
    DeadInsts.push_back(SVI);

  DeadInsts.push_back(LI);
  return true;
}

Instruction *InstCombiner::visitShuffleVectorInst(ShuffleVectorInst &SVI) {
  Value *LHS = SVI.getOperand(0);
  Value *RHS = SVI.getOperand(1);
  SmallVector<int, 16> Mask = SVI.getShuffleMask();
  Type *Int32Ty = Type::getInt32Ty(SVI.getContext());

  bool MadeChange = false;

  // Undefined shuffle mask -> undefined value.
  if (isa<UndefValue>(SVI.getOperand(2)))
    return replaceInstUsesWith(SVI, UndefValue::get(SVI.getType()));

  unsigned VWidth = cast<VectorType>(SVI.getType())->getNumElements();

  APInt UndefElts(VWidth, 0);
  APInt AllOnesEltMask(APInt::getAllOnesValue(VWidth));
  if (Value *V = SimplifyDemandedVectorElts(&SVI, AllOnesEltMask, UndefElts)) {
    if (V != &SVI)
      return replaceInstUsesWith(SVI, V);
    LHS = SVI.getOperand(0);
    RHS = SVI.getOperand(1);
    MadeChange = true;
  }

  unsigned LHSWidth = cast<VectorType>(LHS->getType())->getNumElements();

  // 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) {
      // shuffle(undef,undef,mask) -> undef.
      Value *Result = (VWidth == LHSWidth)
                      ? LHS : UndefValue::get(SVI.getType());
      return replaceInstUsesWith(SVI, Result);
    }

    // Remap any references to RHS to use LHS.
    SmallVector<Constant*, 16> Elts;
    for (unsigned i = 0, e = LHSWidth; i != VWidth; ++i) {
      if (Mask[i] < 0) {
        Elts.push_back(UndefValue::get(Int32Ty));
        continue;
      }

      if ((Mask[i] >= (int)e && isa<UndefValue>(RHS)) ||
          (Mask[i] <  (int)e && isa<UndefValue>(LHS))) {
        Mask[i] = -1;     // Turn into undef.
        Elts.push_back(UndefValue::get(Int32Ty));
      } else {
        Mask[i] = Mask[i] % e;  // Force to LHS.
        Elts.push_back(ConstantInt::get(Int32Ty, 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;
  }

  if (VWidth == LHSWidth) {
    // Analyze the shuffle, are the LHS or RHS and identity shuffles?
    bool isLHSID, isRHSID;
    recognizeIdentityMask(Mask, isLHSID, isRHSID);

    // Eliminate identity shuffles.
    if (isLHSID) return replaceInstUsesWith(SVI, LHS);
    if (isRHSID) return replaceInstUsesWith(SVI, RHS);
  }

  if (isa<UndefValue>(RHS) && CanEvaluateShuffled(LHS, Mask)) {
    Value *V = EvaluateInDifferentElementOrder(LHS, Mask);
    return replaceInstUsesWith(SVI, V);
  }

  // SROA generates shuffle+bitcast when the extracted sub-vector is bitcast to
  // a non-vector type. We can instead bitcast the original vector followed by
  // an extract of the desired element:
  //
  //   %sroa = shufflevector <16 x i8> %in, <16 x i8> undef,
  //                         <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  //   %1 = bitcast <4 x i8> %sroa to i32
  // Becomes:
  //   %bc = bitcast <16 x i8> %in to <4 x i32>
  //   %ext = extractelement <4 x i32> %bc, i32 0
  //
  // If the shuffle is extracting a contiguous range of values from the input
  // vector then each use which is a bitcast of the extracted size can be
  // replaced. This will work if the vector types are compatible, and the begin
  // index is aligned to a value in the casted vector type. If the begin index
  // isn't aligned then we can shuffle the original vector (keeping the same
  // vector type) before extracting.
  //
  // This code will bail out if the target type is fundamentally incompatible
  // with vectors of the source type.
  //
  // Example of <16 x i8>, target type i32:
  // Index range [4,8):         v-----------v Will work.
  //                +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
//.........这里部分代码省略.........