[SLPVectorizer]Migrate getEntryCost to return InstructionCost

[CarolineConcatto]

Summary

This patch also changes:

the return type of getGatherCost and
the signature of the debug function dumpTreeCosts

to use InstructionCost.

This patch is part of a series of patches to use InstructionCost instead of
unsigned/int for the cost model functions.

See this thread for context:
http://lists.llvm.org/pipermail/llvm-dev/2020-November/146408.html

See this patch for the introduction of the type:
https://reviews.llvm.org/D91174

Depends on D93049

[sdesmalen]

This change is purely mechanical. LGTM

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

 #include "llvm/Pass.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/DOTGraphTraits.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/GraphWriter.h"
+#include "llvm/Support/InstructionCost.h"
 #include "llvm/Support/KnownBits.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/Utils/InjectTLIMappings.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
 #include "llvm/Transforms/Vectorize.h"
 #include <algorithm>
 #include <cassert>
#endif
 
   ~BoUpSLP();
 
 private:
   /// Checks if all users of \p I are the part of the vectorization tree.
   bool areAllUsersVectorized(Instruction *I) const;
 
   /// \returns the cost of the vectorizable entry.
-  int getEntryCost(TreeEntry *E);
+  InstructionCost getEntryCost(TreeEntry *E);
 
   /// This is the recursive part of buildTree.
   void buildTree_rec(ArrayRef<Value *> Roots, unsigned Depth,
                      const EdgeInfo &EI);
 
   /// \returns true if the ExtractElement/ExtractValue instructions in \p VL can
   /// be vectorized to use the original vector (or aggregate "bitcast" to a
   /// vector) and sets \p CurrentOrder to the identity permutation; otherwise
   /// returns false, setting \p CurrentOrder to either an empty vector or a
   /// non-identity permutation that allows to reuse extract instructions.
   bool canReuseExtract(ArrayRef<Value *> VL, Value *OpValue,
                        SmallVectorImpl<unsigned> &CurrentOrder) const;
 
   /// Vectorize a single entry in the tree.
   Value *vectorizeTree(TreeEntry *E);
 
   /// Vectorize a single entry in the tree, starting in \p VL.
   Value *vectorizeTree(ArrayRef<Value *> VL);
 
   /// \returns the scalarization cost for this type. Scalarization in this
   /// context means the creation of vectors from a group of scalars.
-  int getGatherCost(FixedVectorType *Ty,
-                    const DenseSet<unsigned> &ShuffledIndices) const;
+  InstructionCost
+  getGatherCost(FixedVectorType *Ty,
 
   /// \returns the scalarization cost for this list of values. Assuming that
   /// this subtree gets vectorized, we may need to extract the values from the
   /// roots. This method calculates the cost of extracting the values.
-  int getGatherCost(ArrayRef<Value *> VL) const;
+  InstructionCost getGatherCost(ArrayRef<Value *> VL) const;
 
   /// Set the Builder insert point to one after the last instruction in
   /// the bundle
   void setInsertPointAfterBundle(TreeEntry *E);
 
   /// \returns a vector from a collection of scalars in \p VL.
   Value *gather(ArrayRef<Value *> VL);
 
LLVM_DUMP_METHOD void dump() const {
       for (const auto &EInfo : UserTreeIndices)
         dbgs() << EInfo << ", ";
       dbgs() << "\n";
     }
 #endif
   };
 
 #ifndef NDEBUG
-  void dumpTreeCosts(TreeEntry *E, int ReuseShuffleCost, int VecCost,
-                     int ScalarCost) const {
+  void dumpTreeCosts(TreeEntry *E, InstructionCost ReuseShuffleCost,
+                     InstructionCost VecCost,
+                     InstructionCost ScalarCost) const {
     dbgs() << "SLP: Calculated costs for Tree:\n"; E->dump();
     dbgs() << "SLP: Costs:\n";
     dbgs() << "SLP:     ReuseShuffleCost = " << ReuseShuffleCost << "\n";
     dbgs() << "SLP:     VectorCost = " << VecCost << "\n";
     dbgs() << "SLP:     ScalarCost = " << ScalarCost << "\n";
     dbgs() << "SLP:     ReuseShuffleCost + VecCost - ScalarCost = " <<
                ReuseShuffleCost + VecCost - ScalarCost << "\n";
   }
if (!CI->isNoBuiltin() && VecFunc) {
 
     // If the corresponding vector call is cheaper, return its cost.
     LibCost = TTI->getCallInstrCost(nullptr, VecTy, VecTys,
                                     TTI::TCK_RecipThroughput);
   }
   return {IntrinsicCost, LibCost};
 }
 
-int BoUpSLP::getEntryCost(TreeEntry *E) {
+InstructionCost BoUpSLP::getEntryCost(TreeEntry *E) {
   ArrayRef<Value*> VL = E->Scalars;
 
   Type *ScalarTy = VL[0]->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
     ScalarTy = SI->getValueOperand()->getType();
   else if (CmpInst *CI = dyn_cast<CmpInst>(VL[0]))
     ScalarTy = CI->getOperand(0)->getType();
   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());
 
   unsigned ReuseShuffleNumbers = E->ReuseShuffleIndices.size();
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
-  int ReuseShuffleCost = 0;
+  InstructionCost ReuseShuffleCost = 0;
   if (NeedToShuffleReuses) {
     ReuseShuffleCost =
         TTI->getShuffleCost(TargetTransformInfo::SK_PermuteSingleSrc, VecTy);
   }
   if (E->State == TreeEntry::NeedToGather) {
     if (allConstant(VL))
       return 0;
     if (isSplat(VL)) {
       return ReuseShuffleCost +
              TTI->getShuffleCost(TargetTransformInfo::SK_Broadcast, VecTy, 0);
     }
     if (E->getOpcode() == Instruction::ExtractElement &&
         allSameType(VL) && allSameBlock(VL)) {
       Optional<TargetTransformInfo::ShuffleKind> ShuffleKind = isShuffle(VL);
       if (ShuffleKind.hasValue()) {
-        int Cost = TTI->getShuffleCost(ShuffleKind.getValue(), VecTy);
+        InstructionCost Cost =
+            TTI->getShuffleCost(ShuffleKind.getValue(), VecTy);
         for (auto *V : VL) {
           // If all users of instruction are going to be vectorized and this
           // instruction itself is not going to be vectorized, consider this
           // instruction as dead and remove its cost from the final cost of the
           // vectorized tree.
           if (areAllUsersVectorized(cast<Instruction>(V)) &&
               !ScalarToTreeEntry.count(V)) {
             auto *IO = cast<ConstantInt>(
InstructionCost BoUpSLP::getEntryCost(TreeEntry *E) {
   unsigned ShuffleOrOp =
       E->isAltShuffle() ? (unsigned)Instruction::ShuffleVector : E->getOpcode();
   switch (ShuffleOrOp) {
     case Instruction::PHI:
       return 0;
 
     case Instruction::ExtractValue:
     case Instruction::ExtractElement: {
-      int DeadCost = 0;
+      InstructionCost DeadCost = 0;
       if (NeedToShuffleReuses) {
         unsigned Idx = 0;
         for (unsigned I : E->ReuseShuffleIndices) {
           if (ShuffleOrOp == Instruction::ExtractElement) {
             auto *IO = cast<ConstantInt>(
                 cast<ExtractElementInst>(VL[I])->getIndexOperand());
             Idx = IO->getZExtValue();
             ReuseShuffleCost -= TTI->getVectorInstrCost(
switch (ShuffleOrOp) {
     case Instruction::PtrToInt:
     case Instruction::IntToPtr:
     case Instruction::SIToFP:
     case Instruction::UIToFP:
     case Instruction::Trunc:
     case Instruction::FPTrunc:
     case Instruction::BitCast: {
       Type *SrcTy = VL0->getOperand(0)->getType();
-      int ScalarEltCost =
+      InstructionCost ScalarEltCost =
           TTI->getCastInstrCost(E->getOpcode(), ScalarTy, SrcTy,
                                 TTI::getCastContextHint(VL0), CostKind, VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
 
       // Calculate the cost of this instruction.
-      int ScalarCost = VL.size() * ScalarEltCost;
+      InstructionCost ScalarCost = VL.size() * ScalarEltCost;
 
       auto *SrcVecTy = FixedVectorType::get(SrcTy, VL.size());
-      int VecCost = 0;
+      InstructionCost VecCost = 0;
       // Check if the values are candidates to demote.
       if (!MinBWs.count(VL0) || VecTy != SrcVecTy) {
         VecCost =
             ReuseShuffleCost +
             TTI->getCastInstrCost(E->getOpcode(), VecTy, SrcVecTy,
                                   TTI::getCastContextHint(VL0), CostKind, VL0);
       }
       LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost));
       return VecCost - ScalarCost;
     }
     case Instruction::FCmp:
     case Instruction::ICmp:
     case Instruction::Select: {
       // Calculate the cost of this instruction.
-      int ScalarEltCost =
+      InstructionCost ScalarEltCost =
           TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy, Builder.getInt1Ty(),
                                   CmpInst::BAD_ICMP_PREDICATE, CostKind, VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
       auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
-      int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
+      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;
       for (auto *V : VL) {
         CmpInst::Predicate CurrentPred;
         auto MatchCmp = m_Cmp(CurrentPred, m_Value(), m_Value());
         if ((!match(V, m_Select(MatchCmp, m_Value(), m_Value())) &&
              !match(V, MatchCmp)) ||
             (!First && VecPred != CurrentPred)) {
           VecPred = CmpInst::BAD_ICMP_PREDICATE;
           break;
         }
         First = false;
         VecPred = CurrentPred;
       }
 
-      int VecCost = TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
-                                            VecPred, CostKind, VL0);
+      InstructionCost VecCost = TTI->getCmpSelInstrCost(
+          E->getOpcode(), VecTy, MaskTy, VecPred, CostKind, VL0);
       // Check if it is possible and profitable to use min/max for selects in
       // VL.
       //
       auto IntrinsicAndUse = canConvertToMinOrMaxIntrinsic(VL);
       if (IntrinsicAndUse.first != Intrinsic::not_intrinsic) {
         IntrinsicCostAttributes CostAttrs(IntrinsicAndUse.first, VecTy,
                                           {VecTy, VecTy});
-        int IntrinsicCost = TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
+        InstructionCost IntrinsicCost =
+            TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
         // If the selects are the only uses of the compares, they will be dead
         // and we can adjust the cost by removing their cost.
         if (IntrinsicAndUse.second)
           IntrinsicCost -=
               TTI->getCmpSelInstrCost(Instruction::ICmp, VecTy, MaskTy,
                                       CmpInst::BAD_ICMP_PREDICATE, CostKind);
         VecCost = std::min(VecCost, IntrinsicCost);
       }
case Instruction::Xor: {
           CInt0 = CInt;
           continue;
         }
         if (CInt0 != CInt)
           Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
       }
 
       SmallVector<const Value *, 4> Operands(VL0->operand_values());
-      int ScalarEltCost = TTI->getArithmeticInstrCost(
-          E->getOpcode(), ScalarTy, CostKind, Op1VK, Op2VK, Op1VP, Op2VP,
-          Operands, VL0);
+      InstructionCost ScalarEltCost =
+          TTI->getArithmeticInstrCost(E->getOpcode(), ScalarTy, CostKind, Op1VK,
+                                      Op2VK, Op1VP, Op2VP, Operands, VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
-      int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
-      int VecCost = TTI->getArithmeticInstrCost(
-          E->getOpcode(), VecTy, CostKind, Op1VK, Op2VK, Op1VP, Op2VP,
-          Operands, VL0);
+      InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
+      InstructionCost VecCost =
+          TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind, Op1VK,
+                                      Op2VK, Op1VP, Op2VP, Operands, VL0);
       LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost));
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::GetElementPtr: {
       TargetTransformInfo::OperandValueKind Op1VK =
           TargetTransformInfo::OK_AnyValue;
       TargetTransformInfo::OperandValueKind Op2VK =
           TargetTransformInfo::OK_UniformConstantValue;
 
-      int ScalarEltCost =
-          TTI->getArithmeticInstrCost(Instruction::Add, ScalarTy, CostKind,
-                                      Op1VK, Op2VK);
+      InstructionCost ScalarEltCost = TTI->getArithmeticInstrCost(
+          Instruction::Add, ScalarTy, CostKind, Op1VK, Op2VK);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
-      int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
-      int VecCost =
-          TTI->getArithmeticInstrCost(Instruction::Add, VecTy, CostKind,
-                                      Op1VK, Op2VK);
+      InstructionCost ScalarCost = VecTy->getNumElements() * ScalarEltCost;
+      InstructionCost VecCost = TTI->getArithmeticInstrCost(
+          Instruction::Add, VecTy, CostKind, Op1VK, Op2VK);
       LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecCost, ScalarCost));
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::Load: {
       // Cost of wide load - cost of scalar loads.
       Align alignment = cast<LoadInst>(VL0)->getAlign();
-      int ScalarEltCost =
-          TTI->getMemoryOpCost(Instruction::Load, ScalarTy, alignment, 0,
-                               CostKind, VL0);
+      InstructionCost ScalarEltCost = TTI->getMemoryOpCost(
+          Instruction::Load, ScalarTy, alignment, 0, CostKind, VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
-      int ScalarLdCost = VecTy->getNumElements() * ScalarEltCost;
-      int VecLdCost;
+      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");
         VecLdCost = TTI->getGatherScatterOpCost(
             Instruction::Load, VecTy, cast<LoadInst>(VL0)->getPointerOperand(),
             /*VariableMask=*/false, alignment, CostKind, VL0);
       }
       if (!NeedToShuffleReuses && !E->ReorderIndices.empty())
         VecLdCost += TTI->getShuffleCost(
             TargetTransformInfo::SK_PermuteSingleSrc, VecTy);
       LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecLdCost, ScalarLdCost));
       return ReuseShuffleCost + VecLdCost - ScalarLdCost;
     }
     case Instruction::Store: {
       // We know that we can merge the stores. Calculate the cost.
       bool IsReorder = !E->ReorderIndices.empty();
       auto *SI =
           cast<StoreInst>(IsReorder ? VL[E->ReorderIndices.front()] : VL0);
       Align Alignment = SI->getAlign();
-      int ScalarEltCost =
-          TTI->getMemoryOpCost(Instruction::Store, ScalarTy, Alignment, 0,
-                               CostKind, VL0);
-      int ScalarStCost = VecTy->getNumElements() * ScalarEltCost;
-      int VecStCost = TTI->getMemoryOpCost(Instruction::Store,
-                                           VecTy, Alignment, 0, CostKind, VL0);
+      InstructionCost ScalarEltCost = TTI->getMemoryOpCost(
+          Instruction::Store, ScalarTy, Alignment, 0, CostKind, VL0);
+      InstructionCost ScalarStCost = VecTy->getNumElements() * ScalarEltCost;
+      InstructionCost VecStCost = TTI->getMemoryOpCost(
+          Instruction::Store, VecTy, Alignment, 0, CostKind, VL0);
       if (IsReorder)
         VecStCost += TTI->getShuffleCost(
             TargetTransformInfo::SK_PermuteSingleSrc, VecTy);
       LLVM_DEBUG(dumpTreeCosts(E, ReuseShuffleCost, VecStCost, ScalarStCost));
       return VecStCost - ScalarStCost;
     }
     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, ElementCount::getFixed(1), 1);
-      int ScalarEltCost = TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
+      InstructionCost ScalarEltCost =
+          TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
-      int ScalarCallCost = VecTy->getNumElements() * ScalarEltCost;
+      InstructionCost ScalarCallCost = VecTy->getNumElements() * ScalarEltCost;
 
       auto VecCallCosts = getVectorCallCosts(CI, VecTy, TTI, TLI);
-      int VecCallCost = std::min(VecCallCosts.first, VecCallCosts.second);
+      InstructionCost VecCallCost =
+          std::min(VecCallCosts.first, VecCallCosts.second);
 
       LLVM_DEBUG(dbgs() << "SLP: Call cost " << VecCallCost - ScalarCallCost
                         << " (" << VecCallCost << "-" << ScalarCallCost << ")"
                         << " for " << *CI << "\n");
 
       return ReuseShuffleCost + VecCallCost - ScalarCallCost;
     }
     case Instruction::ShuffleVector: {
       assert(E->isAltShuffle() &&
              ((Instruction::isBinaryOp(E->getOpcode()) &&
                Instruction::isBinaryOp(E->getAltOpcode())) ||
               (Instruction::isCast(E->getOpcode()) &&
                Instruction::isCast(E->getAltOpcode()))) &&
              "Invalid Shuffle Vector Operand");
-      int ScalarCost = 0;
+      InstructionCost ScalarCost = 0;
       if (NeedToShuffleReuses) {
         for (unsigned Idx : E->ReuseShuffleIndices) {
           Instruction *I = cast<Instruction>(VL[Idx]);
           InstructionCost Cost = TTI->getInstructionCost(I, CostKind);
           assert(Cost.isValid() && "Invalid instruction cost");
           ReuseShuffleCost -= *(Cost.getValue());
         }
         for (Value *V : VL) {
           Instruction *I = cast<Instruction>(V);
           InstructionCost Cost = TTI->getInstructionCost(I, CostKind);
           assert(Cost.isValid() && "Invalid instruction cost");
           ReuseShuffleCost += *(Cost.getValue());
         }
       }
       for (Value *V : VL) {
         Instruction *I = cast<Instruction>(V);
         assert(E->isOpcodeOrAlt(I) && "Unexpected main/alternate opcode");
         InstructionCost Cost = TTI->getInstructionCost(I, CostKind);
         assert(Cost.isValid() && "Invalid instruction cost");
         ScalarCost += *(Cost.getValue());
       }
       // VecCost is equal to sum of the cost of creating 2 vectors
       // and the cost of creating shuffle.
-      int VecCost = 0;
+      InstructionCost VecCost = 0;
       if (Instruction::isBinaryOp(E->getOpcode())) {
         VecCost = TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind);
         VecCost += TTI->getArithmeticInstrCost(E->getAltOpcode(), VecTy,
                                                CostKind);
       } else {
         Type *Src0SclTy = E->getMainOp()->getOperand(0)->getType();
         Type *Src1SclTy = E->getAltOp()->getOperand(0)->getType();
         auto *Src0Ty = FixedVectorType::get(Src0SclTy, VL.size());
#ifndef NDEBUG
   LLVM_DEBUG(dbgs() << Str);
   if (ViewSLPTree)
     ViewGraph(this, "SLP" + F->getName(), false, Str);
 #endif
 
   return Cost;
 }
 
-int BoUpSLP::getGatherCost(FixedVectorType *Ty,
-                           const DenseSet<unsigned> &ShuffledIndices) const {
+InstructionCost
+BoUpSLP::getGatherCost(FixedVectorType *Ty,
   unsigned NumElts = Ty->getNumElements();
   APInt DemandedElts = APInt::getNullValue(NumElts);
   for (unsigned I = 0; I < NumElts; ++I)
     if (!ShuffledIndices.count(I))
       DemandedElts.setBit(I);
-  int Cost = TTI->getScalarizationOverhead(Ty, DemandedElts, /*Insert*/ true,
-                                           /*Extract*/ false);
+  InstructionCost Cost =
+      TTI->getScalarizationOverhead(Ty, DemandedElts, /*Insert*/ true,
   if (!ShuffledIndices.empty())
     Cost += TTI->getShuffleCost(TargetTransformInfo::SK_PermuteSingleSrc, Ty);
   return Cost;
 }
 
-int BoUpSLP::getGatherCost(ArrayRef<Value *> VL) const {
+InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL) const {
   // Find the type of the operands in VL.
   Type *ScalarTy = VL[0]->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
     ScalarTy = SI->getValueOperand()->getType();
   auto *VecTy = FixedVectorType::get(ScalarTy, VL.size());
   // Find the cost of inserting/extracting values from the vector.
   // Check if the same elements are inserted several times and count them as
   // shuffle candidates.