diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index e45fcb2b5c790c..893fef4095b27c 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5443,6 +5443,22 @@ BoUpSLP::getReorderingData(const TreeEntry &TE, bool TopToBottom) {
     if (!TE.ReorderIndices.empty())
       return TE.ReorderIndices;
 
+    SmallVector<Instruction *> UserBVHead(TE.Scalars.size());
+    for (auto [I, V] : zip(UserBVHead, TE.Scalars)) {
+      if (!V->hasNUsesOrMore(1))
+        continue;
+      auto *II = dyn_cast<InsertElementInst>(*V->user_begin());
+      if (!II)
+        continue;
+      Instruction *BVHead = nullptr;
+      BasicBlock *BB = II->getParent();
+      while (II && II->hasOneUse() && II->getParent() == BB) {
+        BVHead = II;
+        II = dyn_cast<InsertElementInst>(II->getOperand(0));
+      }
+      I = BVHead;
+    }
+
     auto PHICompare = [&](unsigned I1, unsigned I2) {
       Value *V1 = TE.Scalars[I1];
       Value *V2 = TE.Scalars[I2];
@@ -5454,21 +5470,60 @@ BoUpSLP::getReorderingData(const TreeEntry &TE, bool TopToBottom) {
         return false;
       auto *FirstUserOfPhi1 = cast<Instruction>(*V1->user_begin());
       auto *FirstUserOfPhi2 = cast<Instruction>(*V2->user_begin());
-      if (auto *IE1 = dyn_cast<InsertElementInst>(FirstUserOfPhi1))
-        if (auto *IE2 = dyn_cast<InsertElementInst>(FirstUserOfPhi2)) {
-          if (!areTwoInsertFromSameBuildVector(
-                  IE1, IE2,
-                  [](InsertElementInst *II) { return II->getOperand(0); }))
-            return I1 < I2;
+      if (FirstUserOfPhi1->getParent() != FirstUserOfPhi2->getParent())
+        return DT->dominates(FirstUserOfPhi1->getParent(),
+                             FirstUserOfPhi2->getParent());
+      auto *IE1 = dyn_cast<InsertElementInst>(FirstUserOfPhi1);
+      auto *IE2 = dyn_cast<InsertElementInst>(FirstUserOfPhi2);
+      auto *EE1 = dyn_cast<ExtractElementInst>(FirstUserOfPhi1);
+      auto *EE2 = dyn_cast<ExtractElementInst>(FirstUserOfPhi2);
+      if (IE1 && !IE2)
+        return true;
+      if (!IE1 && IE2)
+        return false;
+      if (IE1 && IE2) {
+        if (UserBVHead[I1] && !UserBVHead[I2])
+          return true;
+        if (!UserBVHead[I1])
+          return false;
+        if (UserBVHead[I1] == UserBVHead[I2])
           return getElementIndex(IE1) < getElementIndex(IE2);
-        }
-      if (auto *EE1 = dyn_cast<ExtractElementInst>(FirstUserOfPhi1))
-        if (auto *EE2 = dyn_cast<ExtractElementInst>(FirstUserOfPhi2)) {
-          if (EE1->getOperand(0) != EE2->getOperand(0))
-            return I1 < I2;
+        if (UserBVHead[I1]->getParent() != UserBVHead[I2]->getParent())
+          return DT->dominates(UserBVHead[I1]->getParent(),
+                               UserBVHead[I2]->getParent());
+        return UserBVHead[I1]->comesBefore(UserBVHead[I2]);
+      }
+      if (EE1 && !EE2)
+        return true;
+      if (!EE1 && EE2)
+        return false;
+      if (EE1 && EE2) {
+        if (EE1->getOperand(0) == EE2->getOperand(0))
           return getElementIndex(EE1) < getElementIndex(EE2);
+        auto *I1 = dyn_cast<Instruction>(EE1->getOperand(0));
+        if (I1 && !I2)
+          return true;
+        if (!I1 && I2)
+          return false;
+        auto *I2 = dyn_cast<Instruction>(EE2->getOperand(0));
+        if (I1 && I2) {
+          if (I1->getParent() != I2->getParent())
+            return DT->dominates(I1->getParent(), I2->getParent());
+          return I1->comesBefore(I2);
         }
-      return I1 < I2;
+        auto *P1 = dyn_cast<Argument>(EE1->getOperand(0));
+        auto *P2 = dyn_cast<Argument>(EE2->getOperand(0));
+        if (P1 && !P2)
+          return true;
+        if (!P1 && P2)
+          return false;
+        if (P1 && P2)
+          return P1->getArgNo() < P2->getArgNo();
+        // TODO: add analysis for other value kinds.
+        return EE1->getOperand(0)->getValueID() <
+               EE2->getOperand(0)->getValueID();
+      }
+      return false;
     };
     DenseMap<unsigned, unsigned> PhiToId;
     SmallVector<unsigned> Phis(TE.Scalars.size());
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/reused-scalar-repeated-in-node.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/reused-scalar-repeated-in-node.ll
index dbc4f3d59d4f9b..d6073ea4bbbae6 100644
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/reused-scalar-repeated-in-node.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/reused-scalar-repeated-in-node.ll
@@ -33,40 +33,40 @@ define void @test() {
 ; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x float> [[TMP6]], float [[I68]], i32 6
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x float> [[TMP7]], float [[I66]], i32 7
 ; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x float> [[TMP8]], float [[I72]], i32 13
-; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x float> [[TMP9]], float [[I69]], i32 14
-; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x float> [[TMP10]], float [[I67]], i32 15
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x float> [[TMP9]], float [[I67]], i32 14
+; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x float> [[TMP10]], float [[I69]], i32 15
 ; CHECK-NEXT:    br i1 poison, label %[[BB167:.*]], label %[[BB77:.*]]
 ; CHECK:       [[BB77]]:
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <16 x float> [[TMP11]], <16 x float> poison, <8 x i32> <i32 poison, i32 5, i32 6, i32 7, i32 15, i32 15, i32 14, i32 15>
+; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <16 x float> [[TMP11]], <16 x float> poison, <8 x i32> <i32 poison, i32 5, i32 6, i32 7, i32 14, i32 14, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <2 x float> [[TMP0]], <2 x float> poison, <16 x i32> <i32 poison, i32 poison, i32 1, i32 0, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 1, i32 poison, i32 poison>
 ; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <2 x float> [[TMP0]], <2 x float> poison, <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 poison, i32 poison>
 ; CHECK-NEXT:    br label %[[BB78:.*]]
 ; CHECK:       [[BB78]]:
 ; CHECK-NEXT:    [[TMP15:%.*]] = phi <8 x float> [ [[TMP12]], %[[BB77]] ], [ [[TMP30:%.*]], %[[BB78]] ]
 ; CHECK-NEXT:    [[TMP16:%.*]] = phi <2 x float> [ poison, %[[BB77]] ], [ [[TMP31:%.*]], %[[BB78]] ]
-; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 0, i32 3, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 2, i32 7, i32 2, i32 3, i32 0, i32 6, i32 7, i32 7>
+; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 0, i32 3, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 2, i32 6, i32 2, i32 3, i32 0, i32 7, i32 6, i32 6>
 ; CHECK-NEXT:    [[TMP18:%.*]] = fmul fast <16 x float> [[TMP17]], [[TMP13]]
-; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 1, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 1, i32 7, i32 6, i32 6>
+; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 1, i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 1, i32 6, i32 7, i32 7>
 ; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <16 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-NEXT:    [[TMP21:%.*]] = shufflevector <16 x float> [[TMP19]], <16 x float> [[TMP20]], <16 x i32> <i32 0, i32 17, i32 2, i32 16, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP22:%.*]] = shufflevector <8 x float> [[TMP15]], <8 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <16 x float> [[TMP21]], <16 x float> [[TMP22]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 17, i32 6, i32 7, i32 8, i32 22, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <16 x float> [[TMP21]], <16 x float> [[TMP22]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 17, i32 6, i32 7, i32 8, i32 23, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <16 x float> [[TMP23]], <16 x float> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 1, i32 5, i32 3, i32 1, i32 3, i32 9, i32 3, i32 1, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP25:%.*]] = call <16 x float> @llvm.vector.insert.v16f32.v2f32(<16 x float> [[TMP14]], <2 x float> [[TMP0]], i64 2)
 ; CHECK-NEXT:    [[TMP26:%.*]] = fmul fast <16 x float> [[TMP24]], [[TMP25]]
 ; CHECK-NEXT:    [[TMP27:%.*]] = fadd fast <16 x float> [[TMP26]], [[TMP18]]
 ; CHECK-NEXT:    [[TMP28:%.*]] = fadd fast <16 x float> [[TMP27]], poison
 ; CHECK-NEXT:    [[TMP29:%.*]] = fadd fast <16 x float> [[TMP28]], poison
-; CHECK-NEXT:    [[TMP30]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <8 x i32> <i32 12, i32 5, i32 6, i32 7, i32 15, i32 15, i32 14, i32 15>
+; CHECK-NEXT:    [[TMP30]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <8 x i32> <i32 12, i32 5, i32 6, i32 7, i32 14, i32 14, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP31]] = shufflevector <16 x float> [[TMP29]], <16 x float> poison, <2 x i32> <i32 10, i32 11>
 ; CHECK-NEXT:    br i1 poison, label %[[BB78]], label %[[BB167]]
 ; CHECK:       [[BB167]]:
 ; CHECK-NEXT:    [[TMP32:%.*]] = phi <16 x float> [ [[TMP11]], %[[BB64]] ], [ [[TMP29]], %[[BB78]] ]
-; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <16 x float> [[TMP32]], i32 15
+; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <16 x float> [[TMP32]], i32 14
 ; CHECK-NEXT:    store float [[TMP33]], ptr poison, align 1
 ; CHECK-NEXT:    [[TMP34:%.*]] = extractelement <16 x float> [[TMP32]], i32 13
 ; CHECK-NEXT:    store float [[TMP34]], ptr poison, align 1
-; CHECK-NEXT:    [[TMP35:%.*]] = extractelement <16 x float> [[TMP32]], i32 14
+; CHECK-NEXT:    [[TMP35:%.*]] = extractelement <16 x float> [[TMP32]], i32 15
 ; CHECK-NEXT:    br i1 poison, label %[[BB186:.*]], label %[[BB184:.*]]
 ; CHECK:       [[BB184]]:
 ; CHECK-NEXT:    br label %[[BB185:.*]]
diff --git a/llvm/test/Transforms/SLPVectorizer/root-trunc-extract-reuse.ll b/llvm/test/Transforms/SLPVectorizer/root-trunc-extract-reuse.ll
index 34c068478c5f5e..d4b737a6bc4211 100644
--- a/llvm/test/Transforms/SLPVectorizer/root-trunc-extract-reuse.ll
+++ b/llvm/test/Transforms/SLPVectorizer/root-trunc-extract-reuse.ll
@@ -10,9 +10,9 @@ define i1 @test() {
 ; CHECK-NEXT:    br label [[ELSE]]
 ; CHECK:       else:
 ; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i32> [ zeroinitializer, [[THEN]] ], [ zeroinitializer, [[ENTRY:%.*]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <2 x i32> [[TMP0]], i32 1
 ; CHECK-NEXT:    [[BF_CAST162:%.*]] = and i32 [[TMP1]], 0
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x i32> zeroinitializer, <2 x i32> [[TMP0]], <2 x i32> <i32 3, i32 1>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x i32> zeroinitializer, <2 x i32> [[TMP0]], <2 x i32> <i32 2, i32 1>
 ; CHECK-NEXT:    [[T13:%.*]] = and <2 x i32> [[TMP2]], zeroinitializer
 ; CHECK-NEXT:    br label [[ELSE1:%.*]]
 ; CHECK:       else1: