[SLP] Refactoring of HorizontalReduction class, NFC.

[ABataev]

Summary

Removed data members ReduxWidth and MinVecRegSize + some C++11 improvements.

[ABataev]

This comment was removed by ABataev.

[ABataev]

Accepted this patch accidentally

[mkuper]

LGTM

llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp

 ///     +
 ///     |
 ///   *p =
 ///
 class HorizontalReduction {
   SmallVector<Value *, 16> ReductionOps;
   SmallVector<Value *, 32> ReducedVals;
 
-  BinaryOperator *ReductionRoot;
+  BinaryOperator *ReductionRoot = nullptr;
   // After successfull horizontal reduction vectorization attempt for PHI node
   // vectorizer tries to update root binary op by combining vectorized tree and
   // the ReductionPHI node. But during vectorization this ReductionPHI can be
   // vectorized itself and replaced by the undef value, while the instruction
   // itself is marked for deletion. This 'marked for deletion' PHI node then can
   // be used in new binary operation, causing "Use still stuck around after Def
   // is destroyed" crash upon PHI node deletion.
   WeakVH ReductionPHI;
 
   /// The opcode of the reduction.
-  Instruction::BinaryOps ReductionOpcode;
+  Instruction::BinaryOps ReductionOpcode = Instruction::BinaryOpsEnd;
   /// The opcode of the values we perform a reduction on.
-  unsigned ReducedValueOpcode;
+  unsigned ReducedValueOpcode = 0;
   /// Should we model this reduction as a pairwise reduction tree or a tree that
   /// splits the vector in halves and adds those halves.
-  bool IsPairwiseReduction;
+  bool IsPairwiseReduction = false;
 
 public:
-  /// The width of one full horizontal reduction operation.
-  unsigned ReduxWidth;
-
-  /// Minimal width of available vector registers. It's used to determine
-  /// ReduxWidth.
-  unsigned MinVecRegSize;
-
-  HorizontalReduction(unsigned MinVecRegSize)
-      : ReductionRoot(nullptr), ReductionOpcode(Instruction::BinaryOpsEnd),
-        ReducedValueOpcode(0), IsPairwiseReduction(false), ReduxWidth(0),
-        MinVecRegSize(MinVecRegSize) {}
+  HorizontalReduction() = default;
 
   /// \brief Try to find a reduction tree.
   bool matchAssociativeReduction(PHINode *Phi, BinaryOperator *B) {
     assert((!Phi || is_contained(Phi->operands(), B)) &&
            "Thi phi needs to use the binary operator");
 
     // We could have a initial reductions that is not an add.
     //  r *= v1 + v2 + v3 + v4
bool matchAssociativeReduction(PHINode *Phi, BinaryOperator *B) {
 
     if (!B)
       return false;
 
     Type *Ty = B->getType();
     if (!isValidElementType(Ty))
       return false;
 
-    const DataLayout &DL = B->getModule()->getDataLayout();
     ReductionOpcode = B->getOpcode();
     ReducedValueOpcode = 0;
-    // FIXME: Register size should be a parameter to this function, so we can
-    // try different vectorization factors.
-    ReduxWidth = MinVecRegSize / DL.getTypeSizeInBits(Ty);
     ReductionRoot = B;
     ReductionPHI = Phi;
 
-    if (ReduxWidth < 4)
-      return false;
-
     // We currently only support adds.
     if (ReductionOpcode != Instruction::Add &&
         ReductionOpcode != Instruction::FAdd)
       return false;
 
     // Post order traverse the reduction tree starting at B. We only handle true
     // trees containing only binary operators or selects.
     SmallVector<std::pair<Instruction *, unsigned>, 32> Stack;
public:
   }
 
   /// \brief Attempt to vectorize the tree found by
   /// matchAssociativeReduction.
   bool tryToReduce(BoUpSLP &V, TargetTransformInfo *TTI) {
     if (ReducedVals.empty())
       return false;
 
+    // If there is a sufficient number of reduction values, reduce
+    // to a nearby power-of-2. Can safely generate oversized
+    // vectors and rely on the backend to split them to legal sizes.
     unsigned NumReducedVals = ReducedVals.size();
-    if (NumReducedVals < ReduxWidth)
+    if (NumReducedVals < 4)
       return false;
 
+    unsigned ReduxWidth = PowerOf2Floor(NumReducedVals);
+
     Value *VectorizedTree = nullptr;
     IRBuilder<> Builder(ReductionRoot);
     FastMathFlags Unsafe;
     Unsafe.setUnsafeAlgebra();
     Builder.setFastMathFlags(Unsafe);
     unsigned i = 0;
 
     for (; i < NumReducedVals - ReduxWidth + 1; i += ReduxWidth) {
       auto VL = makeArrayRef(&ReducedVals[i], ReduxWidth);
       V.buildTree(VL, ReductionOps);
       if (V.shouldReorder()) {
         SmallVector<Value *, 8> Reversed(VL.rbegin(), VL.rend());
         V.buildTree(Reversed, ReductionOps);
       }
       if (V.isTreeTinyAndNotFullyVectorizable())
         continue;
 
       V.computeMinimumValueSizes();
 
       // Estimate cost.
-      int Cost = V.getTreeCost() + getReductionCost(TTI, ReducedVals[i]);
+      int Cost =
+          V.getTreeCost() + getReductionCost(TTI, ReducedVals[i], ReduxWidth);
       if (Cost >= -SLPCostThreshold)
         break;
 
       DEBUG(dbgs() << "SLP: Vectorizing horizontal reduction at cost:" << Cost
                    << ". (HorRdx)\n");
 
       // Vectorize a tree.
       DebugLoc Loc = cast<Instruction>(ReducedVals[i])->getDebugLoc();
       Value *VectorizedRoot = V.vectorizeTree();
 
       // Emit a reduction.
-      Value *ReducedSubTree = emitReduction(VectorizedRoot, Builder);
+      Value *ReducedSubTree =
+          emitReduction(VectorizedRoot, Builder, ReduxWidth);
       if (VectorizedTree) {
         Builder.SetCurrentDebugLocation(Loc);
         VectorizedTree = Builder.CreateBinOp(ReductionOpcode, VectorizedTree,
                                              ReducedSubTree, "bin.rdx");
       } else
         VectorizedTree = ReducedSubTree;
     }
 
public:
   }
 
   unsigned numReductionValues() const {
     return ReducedVals.size();
   }
 
 private:
   /// \brief Calculate the cost of a reduction.
-  int getReductionCost(TargetTransformInfo *TTI, Value *FirstReducedVal) {
+  int getReductionCost(TargetTransformInfo *TTI, Value *FirstReducedVal,
+                       unsigned ReduxWidth) {
     Type *ScalarTy = FirstReducedVal->getType();
     Type *VecTy = VectorType::get(ScalarTy, ReduxWidth);
 
     int PairwiseRdxCost = TTI->getReductionCost(ReductionOpcode, VecTy, true);
     int SplittingRdxCost = TTI->getReductionCost(ReductionOpcode, VecTy, false);
 
     IsPairwiseReduction = PairwiseRdxCost < SplittingRdxCost;
     int VecReduxCost = IsPairwiseReduction ? PairwiseRdxCost : SplittingRdxCost;
 
     int ScalarReduxCost =
         (ReduxWidth - 1) *
         TTI->getArithmeticInstrCost(ReductionOpcode, ScalarTy);
 
     DEBUG(dbgs() << "SLP: Adding cost " << VecReduxCost - ScalarReduxCost
                  << " for reduction that starts with " << *FirstReducedVal
                  << " (It is a "
                  << (IsPairwiseReduction ? "pairwise" : "splitting")
                  << " reduction)\n");
 
     return VecReduxCost - ScalarReduxCost;
   }
 
   /// \brief Emit a horizontal reduction of the vectorized value.
-  Value *emitReduction(Value *VectorizedValue, IRBuilder<> &Builder) {
+  Value *emitReduction(Value *VectorizedValue, IRBuilder<> &Builder,
+                       unsigned ReduxWidth) {
     assert(VectorizedValue && "Need to have a vectorized tree node");
     assert(isPowerOf2_32(ReduxWidth) &&
            "We only handle power-of-two reductions for now");
 
     Value *TmpVec = VectorizedValue;
     for (unsigned i = ReduxWidth / 2; i != 0; i >>= 1) {
       if (IsPairwiseReduction) {
         Value *LeftMask =
while (!Stack.empty()) {
     auto *Inst = dyn_cast<Instruction>(V);
     if (!Inst || isa<PHINode>(Inst)) {
       Stack.pop_back();
       continue;
     }
     if (Stack.back().isInitial()) {
       Stack.back().clearInitial();
       if (auto *BI = dyn_cast<BinaryOperator>(Inst)) {
-        HorizontalReduction HorRdx(R.getMinVecRegSize());
+        HorizontalReduction HorRdx;
         if (HorRdx.matchAssociativeReduction(P, BI)) {
-          // If there is a sufficient number of reduction values, reduce
-          // to a nearby power-of-2. Can safely generate oversized
-          // vectors and rely on the backend to split them to legal sizes.
-          HorRdx.ReduxWidth =
-              std::max((uint64_t)4, PowerOf2Floor(HorRdx.numReductionValues()));
-
           if (HorRdx.tryToReduce(R, TTI)) {
             Res = true;
             P = nullptr;
             continue;
           }
         }
         if (P) {
           Inst = dyn_cast<Instruction>(BI->getOperand(0));