[SLP]Fix the cost for the extractelements, used in several nodes.

[ABataev]

Summary

Currently the compiler calculates the compensation cost for the
extractelements, removed during vectorization. But if the extractelement
instruction is used in several nodes, we can calculate the compensation
for them several times.

[RKSimon]

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll

12

This doesn't look faster imo

[ABataev]

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll

12

It will be fixed after D148801, I hope. Let me commit it and see if it is so

[ABataev]

Rebase

[ABataev]

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll

12

TTI reports that the cost of vector mul is 4, when the scalar cost is 2 (1x2).
llvm-mca reports different numbers - 8 for scalar muls and 1 for vector mul.
https://godbolt.org/z/azqaMKabr

[RKSimon]

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll

12

Thanks for catching that - I'll get it updated

[vporpo]

Thanks for looking into this @ABataev .

[RKSimon]

@ABataev Please can you rebase against rG4060042384209c9e7077b7024a73c70ef0be0b91 ?

[ABataev]

Rebase

[RKSimon]

LGTM

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

private:
 
   /// Return information about the vector formed for the specified index
   /// of a vector of (the same) instruction.
   TargetTransformInfo::OperandValueInfo getOperandInfo(ArrayRef<Value *> VL,
                                                        unsigned OpIdx);
 
   /// \returns the cost of the vectorizable entry.
   InstructionCost getEntryCost(const TreeEntry *E,
-                               ArrayRef<Value *> VectorizedVals);
+                               ArrayRef<Value *> VectorizedVals,
+                               SmallPtrSetImpl<Value *> &CheckedExtracts);
 
   /// 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

 class BoUpSLP::ShuffleCostEstimator : public BaseShuffleAnalysis {
   bool IsFinalized = false;
   SmallVector<int> CommonMask;
   SmallVector<Value *, 2> InVectors;
   const TargetTransformInfo &TTI;
   InstructionCost Cost = 0;
   ArrayRef<Value *> VectorizedVals;
   BoUpSLP &R;
+  SmallPtrSetImpl<Value *> &CheckedExtracts;
   constexpr static TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
 
   InstructionCost getBuildVectorCost(ArrayRef<Value *> VL, Value *Root) {
     if ((!Root && allConstant(VL)) || all_of(VL, UndefValue::classof))
       return TTI::TCC_Free;
     auto *VecTy = FixedVectorType::get(VL.front()->getType(), VL.size());
     InstructionCost GatherCost = 0;
     SmallVector<Value *> Gathers(VL.begin(), VL.end());
InstructionCost getBuildVectorCost(ArrayRef<Value *> VL, Value *Root) {
     return GatherCost +
            (all_of(Gathers, UndefValue::classof)
                 ? TTI::TCC_Free
                 : R.getGatherCost(Gathers, !Root && VL.equals(Gathers)));
   };
 
 public:
   ShuffleCostEstimator(TargetTransformInfo &TTI,
-                       ArrayRef<Value *> VectorizedVals, BoUpSLP &R)
-      : TTI(TTI), VectorizedVals(VectorizedVals), R(R) {}
+                       ArrayRef<Value *> VectorizedVals, BoUpSLP &R,
+                       SmallPtrSetImpl<Value *> &CheckedExtracts)
+      : TTI(TTI), VectorizedVals(VectorizedVals), R(R),
+        CheckedExtracts(CheckedExtracts) {}
   Value *adjustExtracts(const TreeEntry *E, ArrayRef<int> Mask) {
     if (Mask.empty())
       return nullptr;
     Value *VecBase = nullptr;
     ArrayRef<Value *> VL = E->Scalars;
     auto *VecTy = FixedVectorType::get(VL.front()->getType(), VL.size());
     // If the resulting type is scalarized, do not adjust the cost.
     unsigned VecNumParts = TTI.getNumberOfParts(VecTy);
     if (VecNumParts == VecTy->getNumElements())
       return nullptr;
     DenseMap<Value *, int> ExtractVectorsTys;
-    SmallPtrSet<Value *, 4> CheckedExtracts;
     for (auto [I, V] : enumerate(VL)) {
       // Ignore non-extractelement scalars.
       if (isa<UndefValue>(V) || (!Mask.empty() && Mask[I] == UndefMaskElem))
         continue;
       // 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.
public:
   }
 
   ~ShuffleCostEstimator() {
     assert((IsFinalized || CommonMask.empty()) &&
            "Shuffle construction must be finalized.");
   }
 };
 
-InstructionCost BoUpSLP::getEntryCost(const TreeEntry *E,
-                                      ArrayRef<Value *> VectorizedVals) {
+InstructionCost
+BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
+                      SmallPtrSetImpl<Value *> &CheckedExtracts) {
   ArrayRef<Value *> VL = E->Scalars;
 
   Type *ScalarTy = VL[0]->getType();
   if (auto *SI = dyn_cast<StoreInst>(VL[0]))
     ScalarTy = SI->getValueOperand()->getType();
   else if (auto *CI = dyn_cast<CmpInst>(VL[0]))
     ScalarTy = CI->getOperand(0)->getType();
   else if (auto *IE = dyn_cast<InsertElementInst>(VL[0]))
BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
   auto *FinalVecTy = FixedVectorType::get(VecTy->getElementType(), EntryVF);
 
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
   if (E->State == TreeEntry::NeedToGather) {
     if (allConstant(VL))
       return 0;
     if (isa<InsertElementInst>(VL[0]))
       return InstructionCost::getInvalid();
-    ShuffleCostEstimator Estimator(*TTI, VectorizedVals, *this);
+    ShuffleCostEstimator Estimator(*TTI, VectorizedVals, *this,
+                                   CheckedExtracts);
     unsigned VF = E->getVectorFactor();
     SmallVector<int> ReuseShuffleIndicies(E->ReuseShuffleIndices.begin(),
                                           E->ReuseShuffleIndices.end());
     SmallVector<Value *> GatheredScalars(E->Scalars.begin(), E->Scalars.end());
     // Build a mask out of the reorder indices and reorder scalars per this
     // mask.
     SmallVector<int> ReorderMask;
     inversePermutation(E->ReorderIndices, ReorderMask);
for (Value *V : EntryPtr->Scalars)
             EntryPtr.get());
   }
   InstructionCost Cost = 0;
   LLVM_DEBUG(dbgs() << "SLP: Calculating cost for tree of size "
                     << VectorizableTree.size() << ".\n");
 
   unsigned BundleWidth = VectorizableTree[0]->Scalars.size();
 
+  SmallPtrSet<Value *, 4> CheckedExtracts;
   for (unsigned I = 0, E = VectorizableTree.size(); I < E; ++I) {
     TreeEntry &TE = *VectorizableTree[I];
     if (TE.State == TreeEntry::NeedToGather) {
       if (const TreeEntry *E = getTreeEntry(TE.getMainOp());
           E && E->getVectorFactor() == TE.getVectorFactor() &&
           E->isSame(TE.Scalars)) {
         // Some gather nodes might be absolutely the same as some vectorizable
         // nodes after reordering, need to handle it.
         LLVM_DEBUG(dbgs() << "SLP: Adding cost 0 for bundle that starts with "
                           << *TE.Scalars[0] << ".\n"
                           << "SLP: Current total cost = " << Cost << "\n");
         continue;
       }
     }
 
-    InstructionCost C = getEntryCost(&TE, VectorizedVals);
+    InstructionCost C = getEntryCost(&TE, VectorizedVals, CheckedExtracts);
     Cost += C;
     LLVM_DEBUG(dbgs() << "SLP: Adding cost " << C
                       << " for bundle that starts with " << *TE.Scalars[0]
                       << ".\n"
                       << "SLP: Current total cost = " << Cost << "\n");
   }
 
   SmallPtrSet<Value *, 16> ExtractCostCalculated;

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=slp-vectorizer,instcombine -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 | FileCheck %s
 
 define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-LABEL: @g(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
-; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i64 1
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
+; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x i8> poison, i8 [[X0X0]], i64 0
+; CHECK-NEXT:    [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i64 1
+; CHECK-NEXT:    ret <2 x i8> [[INS2]]
 ;
   %x0 = extractelement <2 x i8> %x, i32 0
   %y1 = extractelement <2 x i8> %y, i32 1
   %x0x0 = mul i8 %x0, %x0
   %y1y1 = mul i8 %y1, %y1
   %ins1 = insertelement <2 x i8> poison, i8 %x0x0, i32 0
   %ins2 = insertelement <2 x i8> %ins1, i8 %y1y1, i32 1
   ret <2 x i8> %ins2
;
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %y1y1, %y2y2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }
 
 define i8 @k(<4 x i8> %x) {
 ; CHECK-LABEL: @k(
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <2 x i32> <i32 3, i32 2>
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i64 1
-; CHECK-NEXT:    [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
-; CHECK-NEXT:    ret i8 [[TMP8]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i64 3
+; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i64 1
+; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i64 2
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
+; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
+; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret i8 [[TMP3]]
 ;
   %x0 = extractelement <4 x i8> %x, i32 0
   %x3 = extractelement <4 x i8> %x, i32 3
   %x1 = extractelement <4 x i8> %x, i32 1
   %x2 = extractelement <4 x i8> %x, i32 2
   %x0x0 = mul i8 %x0, %x0
   %x3x3 = mul i8 %x3, %x3
   %x1x1 = mul i8 %x1, %x1
   %x2x2 = mul i8 %x2, %x2
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %x1x1, %x2x2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }
 
 define i8 @k_bb(<4 x i8> %x) {
 ; CHECK-LABEL: @k_bb(
 ; CHECK-NEXT:    br label [[BB1:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <2 x i32> <i32 3, i32 2>
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i64 1
-; CHECK-NEXT:    [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
-; CHECK-NEXT:    ret i8 [[TMP8]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i64 3
+; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i64 1
+; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i64 2
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
+; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
+; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret i8 [[TMP3]]
 ;
   %x0 = extractelement <4 x i8> %x, i32 0
   br label %bb1
 bb1:
   %x3 = extractelement <4 x i8> %x, i32 3
   %x1 = extractelement <4 x i8> %x, i32 1
   %x2 = extractelement <4 x i8> %x, i32 2
   %x0x0 = mul i8 %x0, %x0
   %x3x3 = mul i8 %x3, %x3
   %x1x1 = mul i8 %x1, %x1
   %x2x2 = mul i8 %x2, %x2
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %x1x1, %x2x2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }

llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=slp-vectorizer,instcombine -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 | FileCheck %s
 
 define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-LABEL: @g(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
-; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i64 1
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
+; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i64 0
+; CHECK-NEXT:    [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i64 1
+; CHECK-NEXT:    ret <2 x i8> [[INS2]]
 ;
   %x0 = extractelement <2 x i8> %x, i32 0
   %y1 = extractelement <2 x i8> %y, i32 1
   %x0x0 = mul i8 %x0, %x0
   %y1y1 = mul i8 %y1, %y1
   %ins1 = insertelement <2 x i8> undef, i8 %x0x0, i32 0
   %ins2 = insertelement <2 x i8> %ins1, i8 %y1y1, i32 1
   ret <2 x i8> %ins2
;
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %y1y1, %y2y2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }
 
 define i8 @k(<4 x i8> %x) {
 ; CHECK-LABEL: @k(
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <2 x i32> <i32 3, i32 2>
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i64 1
-; CHECK-NEXT:    [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
-; CHECK-NEXT:    ret i8 [[TMP8]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i64 3
+; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i64 1
+; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i64 2
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
+; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
+; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret i8 [[TMP3]]
 ;
   %x0 = extractelement <4 x i8> %x, i32 0
   %x3 = extractelement <4 x i8> %x, i32 3
   %x1 = extractelement <4 x i8> %x, i32 1
   %x2 = extractelement <4 x i8> %x, i32 2
   %x0x0 = mul i8 %x0, %x0
   %x3x3 = mul i8 %x3, %x3
   %x1x1 = mul i8 %x1, %x1
   %x2x2 = mul i8 %x2, %x2
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %x1x1, %x2x2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }
 
 define i8 @k_bb(<4 x i8> %x) {
 ; CHECK-LABEL: @k_bb(
 ; CHECK-NEXT:    br label [[BB1:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <4 x i8> [[X:%.*]], [[X]]
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> poison, <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i8> [[X]], [[X]]
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <2 x i32> <i32 3, i32 2>
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i8> [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x i8> [[TMP5]], i64 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <2 x i8> [[TMP5]], i64 1
-; CHECK-NEXT:    [[TMP8:%.*]] = sdiv i8 [[TMP6]], [[TMP7]]
-; CHECK-NEXT:    ret i8 [[TMP8]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <4 x i8> [[X:%.*]], i64 0
+; CHECK-NEXT:    [[X3:%.*]] = extractelement <4 x i8> [[X]], i64 3
+; CHECK-NEXT:    [[X1:%.*]] = extractelement <4 x i8> [[X]], i64 1
+; CHECK-NEXT:    [[X2:%.*]] = extractelement <4 x i8> [[X]], i64 2
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[X3X3:%.*]] = mul i8 [[X3]], [[X3]]
+; CHECK-NEXT:    [[X1X1:%.*]] = mul i8 [[X1]], [[X1]]
+; CHECK-NEXT:    [[X2X2:%.*]] = mul i8 [[X2]], [[X2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i8 [[X0X0]], [[X3X3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = add i8 [[X1X1]], [[X2X2]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sdiv i8 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    ret i8 [[TMP3]]
 ;
   %x0 = extractelement <4 x i8> %x, i32 0
   br label %bb1
 bb1:
   %x3 = extractelement <4 x i8> %x, i32 3
   %x1 = extractelement <4 x i8> %x, i32 1
   %x2 = extractelement <4 x i8> %x, i32 2
   %x0x0 = mul i8 %x0, %x0
   %x3x3 = mul i8 %x3, %x3
   %x1x1 = mul i8 %x1, %x1
   %x2x2 = mul i8 %x2, %x2
   %1 = add i8 %x0x0, %x3x3
   %2 = add i8 %x1x1, %x2x2
   %3 = sdiv i8 %1, %2
   ret i8 %3
 }

llvm/test/Transforms/SLPVectorizer/X86/buildvector-float-and-extract-lane1.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
 ; RUN: opt -passes=slp-vectorizer -mtriple=-x86_64-grtev4-linux-gnu -S -mcpu=corei7-avx -pass-remarks-output=%t < %s | FileCheck %s
 ; RUN: FileCheck --input-file=%t --check-prefix=YAML %s
 
 ; Building a vector of a float (lane 0) and an extract from lane 1 (lane 1)
 ; should have a cost of +1 because we need an extra instruction to combine
 ; both into a single vector.
 ; So this code should not be vectorized.
 
 ; YAML: --- !Passed
 ; YAML: Pass:            slp-vectorizer
 ; YAML: Name:            VectorizedList
 ; YAML: Function:        test
 ; YAML: Args:
 ; YAML:   - String:          'SLP vectorized with cost '
-; YAML:   - Cost:            '-2'
+; YAML:   - Cost:            '-1'
 ; YAML:   - String:          ' and with tree size '
 ; YAML:   - TreeSize:        '3'
 ; YAML: ...
 define void @test(<4 x float> %vec, float %a, float %b, ptr %ptr) {
 ; CHECK-LABEL: define void @test
 ; CHECK-SAME: (<4 x float> [[VEC:%.*]], float [[A:%.*]], float [[B:%.*]], ptr [[PTR:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:    [[FADD:%.*]] = fadd float [[A]], [[B]]
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x float> [[VEC]], <4 x float> poison, <2 x i32> <i32 undef, i32 1>

llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 -slp-schedule-budget=1 | FileCheck %s
 
 define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-LABEL: @g(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
-; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
+; CHECK-NEXT:    [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
+; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x i8> poison, i8 [[X0X0]], i32 0
+; CHECK-NEXT:    [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
+; CHECK-NEXT:    ret <2 x i8> [[INS2]]
 ;
   %x0 = extractelement <2 x i8> %x, i32 0
   %y1 = extractelement <2 x i8> %y, i32 1
   %x0x0 = mul i8 %x0, %x0
   %y1y1 = mul i8 %y1, %y1
   %ins1 = insertelement <2 x i8> poison, i8 %x0x0, i32 0
   %ins2 = insertelement <2 x i8> %ins1, i8 %y1y1, i32 1
   ret <2 x i8> %ins2
 }
 

llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=slp-vectorizer -S -o - -mtriple=x86_64-unknown-linux -mcpu=bdver2 -slp-schedule-budget=1 | FileCheck %s
 
 define <2 x i8> @g(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-LABEL: @g(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = mul <2 x i8> [[TMP1]], [[TMP1]]
-; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x i8> [[X:%.*]], i32 0
+; CHECK-NEXT:    [[Y1:%.*]] = extractelement <2 x i8> [[Y:%.*]], i32 1
+; CHECK-NEXT:    [[X0X0:%.*]] = mul i8 [[X0]], [[X0]]
+; CHECK-NEXT:    [[Y1Y1:%.*]] = mul i8 [[Y1]], [[Y1]]
+; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x i8> undef, i8 [[X0X0]], i32 0
+; CHECK-NEXT:    [[INS2:%.*]] = insertelement <2 x i8> [[INS1]], i8 [[Y1Y1]], i32 1
+; CHECK-NEXT:    ret <2 x i8> [[INS2]]
 ;
   %x0 = extractelement <2 x i8> %x, i32 0
   %y1 = extractelement <2 x i8> %y, i32 1
   %x0x0 = mul i8 %x0, %x0
   %y1y1 = mul i8 %y1, %y1
   %ins1 = insertelement <2 x i8> undef, i8 %x0x0, i32 0
   %ins2 = insertelement <2 x i8> %ins1, i8 %y1y1, i32 1
   ret <2 x i8> %ins2
 }