diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -2433,7 +2433,8 @@
 
   /// \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,
@@ -6793,6 +6794,7 @@
   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) {
@@ -6923,8 +6925,10 @@
 
 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;
@@ -6936,7 +6940,6 @@
     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))
@@ -7061,8 +7064,9 @@
   }
 };
 
-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();
@@ -7089,7 +7093,8 @@
       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());
@@ -8223,6 +8228,7 @@
 
   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) {
@@ -8238,7 +8244,7 @@
       }
     }
 
-    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]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle-inseltpoison.ll
@@ -3,9 +3,13 @@
 
 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
@@ -110,15 +114,18 @@
 
 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
@@ -138,15 +145,18 @@
 ; 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
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/blending-shuffle.ll
@@ -3,9 +3,13 @@
 
 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
@@ -110,15 +114,18 @@
 
 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
@@ -138,15 +145,18 @@
 ; 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
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle-inseltpoison.ll
@@ -3,9 +3,13 @@
 
 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
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/extract-shuffle.ll
@@ -3,9 +3,13 @@
 
 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