[SLP][NFC]Introduce TreeEntry::getVectorFactor member function, NFC.

[ABataev]

Summary

Added TreeEntry::getVectorFactor to get the final vectotization factor
to simplify the code.

[vporpo]

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

1683

"Final" is a bit ambiguous, could you explain a bit more in the comment what this refers to? My understanding is that this refers to the VF used when we generated code, and it may differ from Scalars.size() if this node contains scalars that repeat.

[ABataev]

Address comments.

[vporpo]

LGTM

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

bool isSame(ArrayRef<Value *> VL) const {
           ::addMask(Mask, ReuseShuffleIndices);
           return IsSame(Scalars, Mask);
         }
         return false;
       }
       return IsSame(Scalars, ReuseShuffleIndices);
     }
 
+    /// \return Final vectorization factor for the node. Defined by the total
+    /// number of vectorized scalars, including those, used several times in the
+    /// entry and counted in the \a ReuseShuffleIndices, if any.
+    unsigned getVectorFactor() const {
+      if (!ReuseShuffleIndices.empty())
+        return ReuseShuffleIndices.size();
+      return Scalars.size();
+    };
+
     /// A vector of scalars.
     ValueList Scalars;
 
     /// The Scalars are vectorized into this value. It is initialized to Null.
     Value *VectorizedValue = nullptr;
 
     /// Do we need to gather this sequence or vectorize it
     /// (either with vector instruction or with scatter/gather
InstructionCost BoUpSLP::getEntryCost(const TreeEntry *E,
   auto *VecTy = FixedVectorType::get(ScalarTy, VL.size());
   TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
 
   // If we have computed a smaller type for the expression, update VecTy so
   // that the costs will be accurate.
   if (MinBWs.count(VL[0]))
     VecTy = FixedVectorType::get(
         IntegerType::get(F->getContext(), MinBWs[VL[0]].first), VL.size());
-  auto *FinalVecTy = VecTy;
+  unsigned EntryVF = E->getVectorFactor();
+  auto *FinalVecTy = FixedVectorType::get(VecTy->getElementType(), EntryVF);
 
-  unsigned ReuseShuffleNumbers = E->ReuseShuffleIndices.size();
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
-  if (NeedToShuffleReuses)
-    FinalVecTy =
-        FixedVectorType::get(VecTy->getElementType(), ReuseShuffleNumbers);
   // FIXME: it tries to fix a problem with MSVC buildbots.
   TargetTransformInfo &TTIRef = *TTI;
   auto &&AdjustExtractsCost = [this, &TTIRef, CostKind, VL, VecTy,
                                VectorizedVals](InstructionCost &Cost,
                                                bool IsGather) {
     DenseMap<Value *, int> ExtractVectorsTys;
     for (auto *V : VL) {
       // If all users of instruction are going to be vectorized and this
case Instruction::ExtractElement: {
                                                   EE->getVectorOperandType(),
                                                   *getExtractIndex(EE));
           } else {
             CommonCost -= TTI->getVectorInstrCost(Instruction::ExtractElement,
                                                   VecTy, Idx);
             ++Idx;
           }
         }
-        Idx = ReuseShuffleNumbers;
+        Idx = EntryVF;
         for (Value *V : VL) {
           if (ShuffleOrOp == Instruction::ExtractElement) {
             auto *EE = cast<ExtractElementInst>(V);
             CommonCost += TTI->getVectorInstrCost(Instruction::ExtractElement,
                                                   EE->getVectorOperandType(),
                                                   *getExtractIndex(EE));
           } else {
             --Idx;
switch (ShuffleOrOp) {
     case Instruction::Trunc:
     case Instruction::FPTrunc:
     case Instruction::BitCast: {
       Type *SrcTy = VL0->getOperand(0)->getType();
       InstructionCost ScalarEltCost =
           TTI->getCastInstrCost(E->getOpcode(), ScalarTy, SrcTy,
                                 TTI::getCastContextHint(VL0), CostKind, VL0);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
 
       // Calculate the cost of this instruction.
       InstructionCost ScalarCost = VL.size() * ScalarEltCost;
 
       auto *SrcVecTy = FixedVectorType::get(SrcTy, VL.size());
       InstructionCost VecCost = 0;
       // Check if the values are candidates to demote.
       if (!MinBWs.count(VL0) || VecTy != SrcVecTy) {
         VecCost = CommonCost + TTI->getCastInstrCost(
                                    E->getOpcode(), VecTy, SrcVecTy,
                                    TTI::getCastContextHint(VL0), CostKind, VL0);
       }
       LLVM_DEBUG(dumpTreeCosts(E, CommonCost, VecCost, ScalarCost));
       return VecCost - ScalarCost;
     }
     case Instruction::FCmp:
     case Instruction::ICmp:
     case Instruction::Select: {
       // Calculate the cost of this instruction.
       InstructionCost ScalarEltCost =
           TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy, Builder.getInt1Ty(),
                                   CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
       auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
       InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
 
       // Check if all entries in VL are either compares or selects with compares
       // as condition that have the same predicates.
       CmpInst::Predicate VecPred = CmpInst::BAD_ICMP_PREDICATE;
       bool First = true;
case Instruction::Xor: {
           Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
       }
 
       SmallVector<const Value *, 4> Operands(VL0->operand_values());
       InstructionCost ScalarEltCost =
           TTI->getArithmeticInstrCost(E->getOpcode(), ScalarTy, CostKind, Op1VK,
                                       Op2VK, Op1VP, Op2VP, Operands, VL0);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
       InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
       InstructionCost VecCost =
           TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind, Op1VK,
                                       Op2VK, Op1VP, Op2VP, Operands, VL0);
       LLVM_DEBUG(dumpTreeCosts(E, CommonCost, VecCost, ScalarCost));
       return CommonCost + VecCost - ScalarCost;
     }
     case Instruction::GetElementPtr: {
       TargetTransformInfo::OperandValueKind Op1VK =
           TargetTransformInfo::OK_AnyValue;
       TargetTransformInfo::OperandValueKind Op2VK =
           TargetTransformInfo::OK_UniformConstantValue;
 
       InstructionCost ScalarEltCost = TTI->getArithmeticInstrCost(
           Instruction::Add, ScalarTy, CostKind, Op1VK, Op2VK);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
       InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
       InstructionCost VecCost = TTI->getArithmeticInstrCost(
           Instruction::Add, VecTy, CostKind, Op1VK, Op2VK);
       LLVM_DEBUG(dumpTreeCosts(E, CommonCost, VecCost, ScalarCost));
       return CommonCost + VecCost - ScalarCost;
     }
     case Instruction::Load: {
       // Cost of wide load - cost of scalar loads.
       Align Alignment = cast<LoadInst>(VL0)->getAlign();
       InstructionCost ScalarEltCost = TTI->getMemoryOpCost(
           Instruction::Load, ScalarTy, Alignment, 0, CostKind, VL0);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
       InstructionCost ScalarLdCost = VecTy->getNumElements() * ScalarEltCost;
       InstructionCost VecLdCost;
       if (E->State == TreeEntry::Vectorize) {
         VecLdCost = TTI->getMemoryOpCost(Instruction::Load, VecTy, Alignment, 0,
                                          CostKind, VL0);
       } else {
         assert(E->State == TreeEntry::ScatterVectorize && "Unknown EntryState");
case Instruction::Call: {
       CallInst *CI = cast<CallInst>(VL0);
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
 
       // Calculate the cost of the scalar and vector calls.
       IntrinsicCostAttributes CostAttrs(ID, *CI, 1);
       InstructionCost ScalarEltCost =
           TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
       if (NeedToShuffleReuses) {
-        CommonCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
+        CommonCost -= (EntryVF - VL.size()) * ScalarEltCost;
       }
       InstructionCost ScalarCallCost = VecTy->getNumElements() * ScalarEltCost;
 
       auto VecCallCosts = getVectorCallCosts(CI, VecTy, TTI, TLI);
       InstructionCost VecCallCost =
           std::min(VecCallCosts.first, VecCallCosts.second);
 
       LLVM_DEBUG(dbgs() << "SLP: Call cost " << VecCallCost - ScalarCallCost
bool BoUpSLP::isFullyVectorizableTinyTree(bool ForReduction) const {
   };
 
   // We only handle trees of heights 1 and 2.
   if (VectorizableTree.size() == 1 &&
       (VectorizableTree[0]->State == TreeEntry::Vectorize ||
        (ForReduction &&
         AreVectorizableGathers(VectorizableTree[0].get(),
                                VectorizableTree[0]->Scalars.size()) &&
-        (VectorizableTree[0]->Scalars.size() > 2 ||
-         VectorizableTree[0]->ReuseShuffleIndices.size() > 2))))
+        VectorizableTree[0]->getVectorFactor() > 2)))
     return true;
 
   if (VectorizableTree.size() != 2)
     return false;
 
   // Handle splat and all-constants stores. Also try to vectorize tiny trees
   // with the second gather nodes if they have less scalar operands rather than
   // the initial tree element (may be profitable to shuffle the second gather)
if (It != UsedTEs.front().end()) {
       std::iota(Mask.begin(), Mask.end(), 0);
       return TargetTransformInfo::SK_PermuteSingleSrc;
     }
     // No perfect match, just shuffle, so choose the first tree node.
     Entries.push_back(*UsedTEs.front().begin());
   } else {
     // Try to find nodes with the same vector factor.
     assert(UsedTEs.size() == 2 && "Expected at max 2 permuted entries.");
-    // FIXME: Shall be replaced by GetVF function once non-power-2 patch is
-    // landed.
-    auto &&GetVF = [](const TreeEntry *TE) {
-      if (!TE->ReuseShuffleIndices.empty())
-        return TE->ReuseShuffleIndices.size();
-      return TE->Scalars.size();
-    };
     DenseMap<int, const TreeEntry *> VFToTE;
     for (const TreeEntry *TE : UsedTEs.front())
-      VFToTE.try_emplace(GetVF(TE), TE);
+      VFToTE.try_emplace(TE->getVectorFactor(), TE);
     for (const TreeEntry *TE : UsedTEs.back()) {
-      auto It = VFToTE.find(GetVF(TE));
+      auto It = VFToTE.find(TE->getVectorFactor());
       if (It != VFToTE.end()) {
         VF = It->first;
         Entries.push_back(It->second);
         Entries.push_back(TE);
         break;
       }
     }
     // No 2 source vectors with the same vector factor - give up and do regular
Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
   IRBuilder<>::InsertPointGuard Guard(Builder);
 
   if (E->VectorizedValue) {
     LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n");
     return E->VectorizedValue;
   }
 
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
-  unsigned VF = E->Scalars.size();
-  if (NeedToShuffleReuses)
-    VF = E->ReuseShuffleIndices.size();
+  unsigned VF = E->getVectorFactor();
   ShuffleInstructionBuilder ShuffleBuilder(Builder, VF);
   if (E->State == TreeEntry::NeedToGather) {
     if (E->getMainOp())
       setInsertPointAfterBundle(E);
     Value *Vec;
     SmallVector<int> Mask;
     SmallVector<const TreeEntry *> Entries;
     Optional<TargetTransformInfo::ShuffleKind> Shuffle =