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
@@ -7084,6 +7084,94 @@
 
 } // end anonymous namespace
 
+static Optional<unsigned> getAggregateSize(Instruction *InsertInst) {
+  if (auto *IE = dyn_cast<InsertElementInst>(InsertInst))
+    return IE->getType()->getNumElements();
+
+  unsigned AggregateSize = 1;
+  auto *IV = cast<InsertValueInst>(InsertInst);
+  Type *CurrentType = IV->getType();
+  do {
+    if (auto *ST = dyn_cast<StructType>(CurrentType)) {
+      for (auto *Elt : ST->elements())
+        if (Elt != ST->getElementType(0)) // check homogeneity
+          return None;
+      AggregateSize *= ST->getNumElements();
+      CurrentType = ST->getElementType(0);
+    } else if (auto *AT = dyn_cast<ArrayType>(CurrentType)) {
+      AggregateSize *= AT->getNumElements();
+      CurrentType = AT->getElementType();
+    } else if (auto *VT = dyn_cast<VectorType>(CurrentType)) {
+      AggregateSize *= VT->getNumElements();
+      return AggregateSize;
+    } else if (CurrentType->isSingleValueType()) {
+      return AggregateSize;
+    } else {
+      return None;
+    }
+  } while (true);
+}
+
+static Optional<unsigned> getOperandIndex(Instruction *InsertInst,
+                                          unsigned OperandOffset) {
+  unsigned OperandIndex = OperandOffset;
+  if (auto *IE = dyn_cast<InsertElementInst>(InsertInst)) {
+    if (auto *CI = dyn_cast<ConstantInt>(IE->getOperand(2))) {
+      auto *VT = cast<VectorType>(IE->getType());
+      OperandIndex *= VT->getNumElements();
+      OperandIndex += CI->getZExtValue();
+      return OperandIndex;
+    }
+    return None;
+  }
+
+  auto *IV = cast<InsertValueInst>(InsertInst);
+  Type *CurrentType = IV->getType();
+  for (unsigned int Index : IV->indices()) {
+    if (auto *ST = dyn_cast<StructType>(CurrentType)) {
+      OperandIndex *= ST->getNumElements();
+      CurrentType = ST->getElementType(Index);
+    } else if (auto *AT = dyn_cast<ArrayType>(CurrentType)) {
+      OperandIndex *= AT->getNumElements();
+      CurrentType = AT->getElementType();
+    } else {
+      return None;
+    }
+    OperandIndex += Index;
+  }
+  return OperandIndex;
+}
+
+static bool findBuildAggregate_rec(Instruction *LastInsertInst,
+                                   TargetTransformInfo *TTI,
+                                   SmallVectorImpl<Value *> &BuildVectorOpds,
+                                   SmallVectorImpl<Value *> &InsertElts,
+                                   unsigned OperandOffset) {
+  do {
+    Value *InsertedOperand = LastInsertInst->getOperand(1);
+    Optional<unsigned> OperandIndex =
+        getOperandIndex(LastInsertInst, OperandOffset);
+    if (!OperandIndex)
+      return false;
+    if (isa<InsertElementInst>(InsertedOperand) ||
+        isa<InsertValueInst>(InsertedOperand)) {
+      if (!findBuildAggregate_rec(cast<Instruction>(InsertedOperand), TTI,
+                                  BuildVectorOpds, InsertElts, *OperandIndex))
+        return false;
+    } else {
+      BuildVectorOpds[*OperandIndex] = InsertedOperand;
+      InsertElts[*OperandIndex] = LastInsertInst;
+    }
+    if (isa<UndefValue>(LastInsertInst->getOperand(0)))
+      return true;
+    LastInsertInst = dyn_cast<Instruction>(LastInsertInst->getOperand(0));
+  } while (LastInsertInst != nullptr &&
+           (isa<InsertValueInst>(LastInsertInst) ||
+            isa<InsertElementInst>(LastInsertInst)) &&
+           LastInsertInst->hasOneUse());
+  return false;
+}
+
 /// Recognize construction of vectors like
 ///  %ra = insertelement <4 x float> undef, float %s0, i32 0
 ///  %rb = insertelement <4 x float> %ra, float %s1, i32 1
@@ -7091,54 +7179,41 @@
 ///  %rd = insertelement <4 x float> %rc, float %s3, i32 3
 ///  starting from the last insertelement or insertvalue instruction.
 ///
-/// Also recognize aggregates like {<2 x float>, <2 x float>},
+/// Also recognize homogeneous aggregates like {<2 x float>, <2 x float>},
 /// {{float, float}, {float, float}}, [2 x {float, float}] and so on.
 /// See llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll for examples.
 ///
 /// Assume LastInsertInst is of InsertElementInst or InsertValueInst type.
 ///
 /// \return true if it matches.
-static bool findBuildAggregate(Value *LastInsertInst, TargetTransformInfo *TTI,
+static bool findBuildAggregate(Instruction *LastInsertInst,
+                               TargetTransformInfo *TTI,
                                SmallVectorImpl<Value *> &BuildVectorOpds,
                                SmallVectorImpl<Value *> &InsertElts) {
+
   assert((isa<InsertElementInst>(LastInsertInst) ||
           isa<InsertValueInst>(LastInsertInst)) &&
          "Expected insertelement or insertvalue instruction!");
-  do {
-    Value *InsertedOperand;
-    auto *IE = dyn_cast<InsertElementInst>(LastInsertInst);
-    if (IE) {
-      InsertedOperand = IE->getOperand(1);
-      LastInsertInst = IE->getOperand(0);
-    } else {
-      auto *IV = cast<InsertValueInst>(LastInsertInst);
-      InsertedOperand = IV->getInsertedValueOperand();
-      LastInsertInst = IV->getAggregateOperand();
-    }
-    if (isa<InsertElementInst>(InsertedOperand) ||
-        isa<InsertValueInst>(InsertedOperand)) {
-      SmallVector<Value *, 8> TmpBuildVectorOpds;
-      SmallVector<Value *, 8> TmpInsertElts;
-      if (!findBuildAggregate(InsertedOperand, TTI, TmpBuildVectorOpds,
-                              TmpInsertElts))
-        return false;
-      BuildVectorOpds.append(TmpBuildVectorOpds.rbegin(),
-                             TmpBuildVectorOpds.rend());
-      InsertElts.append(TmpInsertElts.rbegin(), TmpInsertElts.rend());
-    } else {
-      BuildVectorOpds.push_back(InsertedOperand);
-      InsertElts.push_back(IE);
-    }
-    if (isa<UndefValue>(LastInsertInst))
-      break;
-    if ((!isa<InsertValueInst>(LastInsertInst) &&
-         !isa<InsertElementInst>(LastInsertInst)) ||
-        !LastInsertInst->hasOneUse())
-      return false;
-  } while (true);
-  std::reverse(BuildVectorOpds.begin(), BuildVectorOpds.end());
-  std::reverse(InsertElts.begin(), InsertElts.end());
-  return true;
+
+  assert((BuildVectorOpds.empty() && InsertElts.empty()) &&
+         "Expected empty result vectors!");
+
+  Optional<unsigned> AggregateSize = getAggregateSize(LastInsertInst);
+  if (!AggregateSize)
+    return false;
+  BuildVectorOpds.resize(*AggregateSize);
+  InsertElts.resize(*AggregateSize);
+
+  if (findBuildAggregate_rec(LastInsertInst, TTI, BuildVectorOpds, InsertElts,
+                             0)) {
+    llvm::erase_if(BuildVectorOpds,
+                   [](const Value *V) { return V == nullptr; });
+    llvm::erase_if(InsertElts, [](const Value *V) { return V == nullptr; });
+    if (BuildVectorOpds.size() >= 2)
+      return true;
+  }
+
+  return false;
 }
 
 static bool PhiTypeSorterFunc(Value *V, Value *V2) {
@@ -7308,8 +7383,7 @@
 
   SmallVector<Value *, 16> BuildVectorOpds;
   SmallVector<Value *, 16> BuildVectorInsts;
-  if (!findBuildAggregate(IVI, TTI, BuildVectorOpds, BuildVectorInsts) ||
-      BuildVectorOpds.size() < 2)
+  if (!findBuildAggregate(IVI, TTI, BuildVectorOpds, BuildVectorInsts))
     return false;
 
   LLVM_DEBUG(dbgs() << "SLP: array mappable to vector: " << *IVI << "\n");
@@ -7324,7 +7398,6 @@
   SmallVector<Value *, 16> BuildVectorInsts;
   SmallVector<Value *, 16> BuildVectorOpds;
   if (!findBuildAggregate(IEI, TTI, BuildVectorOpds, BuildVectorInsts) ||
-      BuildVectorOpds.size() < 2 ||
       (llvm::all_of(BuildVectorOpds,
                     [](Value *V) { return isa<ExtractElementInst>(V); }) &&
        isShuffle(BuildVectorOpds)))
diff --git a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
--- a/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
+++ b/llvm/test/Transforms/PhaseOrdering/X86/horiz-math.ll
@@ -37,11 +37,10 @@
 
 define <4 x float> @reverse_hadd_v4f32(<4 x float> %a, <4 x float> %b) #0 {
 ; CHECK-LABEL: @reverse_hadd_v4f32(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x float> [[A:%.*]], <4 x float> [[B:%.*]], <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x float> [[A]], <4 x float> [[B]], <4 x i32> <i32 1, i32 3, i32 5, i32 7>
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x float> [[B:%.*]], <4 x float> [[A:%.*]], <4 x i32> <i32 2, i32 0, i32 6, i32 4>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x float> [[B]], <4 x float> [[A]], <4 x i32> <i32 3, i32 1, i32 7, i32 5>
 ; CHECK-NEXT:    [[TMP3:%.*]] = fadd <4 x float> [[TMP1]], [[TMP2]]
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT:    ret <4 x float> [[TMP4]]
+; CHECK-NEXT:    ret <4 x float> [[TMP3]]
 ;
   %vecext = extractelement <4 x float> %a, i32 0
   %vecext1 = extractelement <4 x float> %a, i32 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll b/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll
@@ -425,10 +425,10 @@
 ; CHECK-NEXT:    [[AB5:%.*]] = sdiv i32 [[A5]], 4
 ; CHECK-NEXT:    [[AB6:%.*]] = sdiv i32 [[A6]], 8
 ; CHECK-NEXT:    [[AB7:%.*]] = sdiv i32 [[A7]], 16
-; CHECK-NEXT:    [[R1:%.*]] = insertelement <8 x i32> undef, i32 [[AB1]], i32 1
-; CHECK-NEXT:    [[R2:%.*]] = insertelement <8 x i32> [[R1]], i32 [[AB2]], i32 2
-; CHECK-NEXT:    [[R3:%.*]] = insertelement <8 x i32> [[R2]], i32 [[AB3]], i32 3
-; CHECK-NEXT:    [[R5:%.*]] = insertelement <8 x i32> [[R3]], i32 [[AB5]], i32 5
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <8 x i32> undef, i32 [[AB1]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i32> [[TMP1]], i32 [[AB2]], i32 2
+; CHECK-NEXT:    [[R4:%.*]] = insertelement <8 x i32> [[TMP2]], i32 [[AB3]], i32 3
+; CHECK-NEXT:    [[R5:%.*]] = insertelement <8 x i32> [[R4]], i32 [[AB5]], i32 5
 ; CHECK-NEXT:    [[R6:%.*]] = insertelement <8 x i32> [[R5]], i32 [[AB6]], i32 6
 ; CHECK-NEXT:    [[R7:%.*]] = insertelement <8 x i32> [[R6]], i32 [[AB7]], i32 7
 ; CHECK-NEXT:    ret <8 x i32> [[R7]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
@@ -126,13 +126,16 @@
 ; doesn't matter
 define <4 x float> @simple_select_insert_out_of_order(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; ANY-LABEL: @simple_select_insert_out_of_order(
-; ANY-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
-; ANY-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
-; ANY-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
+; ANY-NEXT:    [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[C:%.*]], <4 x i32> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; ANY-NEXT:    [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x float> [[A:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; ANY-NEXT:    [[REORDER_SHUFFLE2:%.*]] = shufflevector <4 x float> [[B:%.*]], <4 x float> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 3>
+; ANY-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[REORDER_SHUFFLE]], zeroinitializer
+; ANY-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[REORDER_SHUFFLE1]], <4 x float> [[REORDER_SHUFFLE2]]
+; ANY-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
 ; ANY-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 2
 ; ANY-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
 ; ANY-NEXT:    [[RB:%.*]] = insertelement <4 x float> [[RA]], float [[TMP4]], i32 1
-; ANY-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 2
+; ANY-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; ANY-NEXT:    [[RC:%.*]] = insertelement <4 x float> [[RB]], float [[TMP5]], i32 0
 ; ANY-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[TMP2]], i32 3
 ; ANY-NEXT:    [[RD:%.*]] = insertelement <4 x float> [[RC]], float [[TMP6]], i32 3
@@ -447,19 +450,19 @@
 ; Make sure we handle multiple trees that feed one build vector correctly.
 define <4 x double> @multi_tree(double %w, double %x, double %y, double %z) {
 ; ANY-LABEL: @multi_tree(
-; ANY-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[W:%.*]], i32 0
-; ANY-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[X:%.*]], i32 1
-; ANY-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[Y:%.*]], i32 2
-; ANY-NEXT:    [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[Z:%.*]], i32 3
-; ANY-NEXT:    [[TMP5:%.*]] = fadd <4 x double> [[TMP4]], <double 0.000000e+00, double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>
+; ANY-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[Z:%.*]], i32 0
+; ANY-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[Y:%.*]], i32 1
+; ANY-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[X:%.*]], i32 2
+; ANY-NEXT:    [[TMP4:%.*]] = insertelement <4 x double> [[TMP3]], double [[W:%.*]], i32 3
+; ANY-NEXT:    [[TMP5:%.*]] = fadd <4 x double> [[TMP4]], <double 3.000000e+00, double 2.000000e+00, double 1.000000e+00, double 0.000000e+00>
 ; ANY-NEXT:    [[TMP6:%.*]] = fmul <4 x double> [[TMP5]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
-; ANY-NEXT:    [[TMP7:%.*]] = extractelement <4 x double> [[TMP6]], i32 0
+; ANY-NEXT:    [[TMP7:%.*]] = extractelement <4 x double> [[TMP6]], i32 3
 ; ANY-NEXT:    [[I1:%.*]] = insertelement <4 x double> undef, double [[TMP7]], i32 3
-; ANY-NEXT:    [[TMP8:%.*]] = extractelement <4 x double> [[TMP6]], i32 1
+; ANY-NEXT:    [[TMP8:%.*]] = extractelement <4 x double> [[TMP6]], i32 2
 ; ANY-NEXT:    [[I2:%.*]] = insertelement <4 x double> [[I1]], double [[TMP8]], i32 2
-; ANY-NEXT:    [[TMP9:%.*]] = extractelement <4 x double> [[TMP6]], i32 2
+; ANY-NEXT:    [[TMP9:%.*]] = extractelement <4 x double> [[TMP6]], i32 1
 ; ANY-NEXT:    [[I3:%.*]] = insertelement <4 x double> [[I2]], double [[TMP9]], i32 1
-; ANY-NEXT:    [[TMP10:%.*]] = extractelement <4 x double> [[TMP6]], i32 3
+; ANY-NEXT:    [[TMP10:%.*]] = extractelement <4 x double> [[TMP6]], i32 0
 ; ANY-NEXT:    [[I4:%.*]] = insertelement <4 x double> [[I3]], double [[TMP10]], i32 0
 ; ANY-NEXT:    ret <4 x double> [[I4]]
 ;
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll b/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll
@@ -56,7 +56,7 @@
 ; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds <4 x float>, <4 x float>* [[X]], i64 0, i64 2
 ; CHECK-NEXT:    [[TMP1:%.*]] = bitcast float* [[GEP0]] to <2 x float>*
 ; CHECK-NEXT:    [[TMP2:%.*]] = load <2 x float>, <2 x float>* [[TMP1]], align 4
-; CHECK-NEXT:    [[X2:%.*]] = load float, float* [[GEP2]]
+; CHECK-NEXT:    [[X2:%.*]] = load float, float* [[GEP2]], align 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[I0:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll b/llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/pr42022.ll
@@ -147,13 +147,13 @@
 define {%StructTy, float, float} @NonHomogeneousStruct(float *%Ptr) {
 ; CHECK-LABEL: @NonHomogeneousStruct(
 ; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds float, float* [[PTR:%.*]], i64 0
-; CHECK-NEXT:    [[L0:%.*]] = load float, float* [[GEP0]]
+; CHECK-NEXT:    [[L0:%.*]] = load float, float* [[GEP0]], align 4
 ; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds float, float* [[PTR]], i64 1
-; CHECK-NEXT:    [[L1:%.*]] = load float, float* [[GEP1]]
+; CHECK-NEXT:    [[L1:%.*]] = load float, float* [[GEP1]], align 4
 ; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds float, float* [[PTR]], i64 2
-; CHECK-NEXT:    [[L2:%.*]] = load float, float* [[GEP2]]
+; CHECK-NEXT:    [[L2:%.*]] = load float, float* [[GEP2]], align 4
 ; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr inbounds float, float* [[PTR]], i64 3
-; CHECK-NEXT:    [[L3:%.*]] = load float, float* [[GEP3]]
+; CHECK-NEXT:    [[L3:%.*]] = load float, float* [[GEP3]], align 4
 ; CHECK-NEXT:    [[FADD0:%.*]] = fadd fast float [[L0]], 1.100000e+01
 ; CHECK-NEXT:    [[FADD1:%.*]] = fadd fast float [[L1]], 1.200000e+01
 ; CHECK-NEXT:    [[FADD2:%.*]] = fadd fast float [[L2]], 1.300000e+01
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/pr44067.ll b/llvm/test/Transforms/SLPVectorizer/X86/pr44067.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/pr44067.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/pr44067.ll
@@ -8,11 +8,10 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = bitcast { { float, float } }* [[A:%.*]] to <2 x float>*
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x float>, <2 x float>* [[TMP0]], align 8
-; CHECK-NEXT:    [[REORDER_SHUFFLE:%.*]] = shufflevector <2 x float> [[TMP1]], <2 x float> undef, <2 x i32> <i32 1, i32 0>
-; CHECK-NEXT:    [[TMP2:%.*]] = fmul <2 x float> [[REORDER_SHUFFLE]], <float 2.000000e+00, float 2.000000e+00>
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul <2 x float> [[TMP1]], <float 2.000000e+00, float 2.000000e+00>
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
 ; CHECK-NEXT:    [[INS1:%.*]] = insertelement <2 x float> undef, float [[TMP3]], i32 1
-; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[INS0:%.*]] = insertelement <2 x float> [[INS1]], float [[TMP4]], i32 0
 ; CHECK-NEXT:    ret <2 x float> [[INS0]]
 ;
@@ -44,23 +43,22 @@
 ; CHECK-NEXT:    [[GEP7:%.*]] = getelementptr inbounds i16, i16* [[PTR]], i64 7
 ; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[GEP0]] to <8 x i16>*
 ; CHECK-NEXT:    [[TMP2:%.*]] = load <8 x i16>, <8 x i16>* [[TMP1]], align 2
-; CHECK-NEXT:    [[REORDER_SHUFFLE:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 7, i32 6, i32 1, i32 0, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i16> [[REORDER_SHUFFLE]], <i16 5, i16 6, i16 8, i16 7, i16 2, i16 1, i16 3, i16 4>
-; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <8 x i16> [[TMP3]], i32 4
+; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i16> [[TMP2]], <i16 1, i16 2, i16 3, i16 4, i16 5, i16 6, i16 7, i16 8>
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <8 x i16> [[TMP3]], i32 1
 ; CHECK-NEXT:    [[STRUCTIN0:%.*]] = insertvalue [[STRUCT1TY:%.*]] undef, i16 [[TMP4]], 1
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i16> [[TMP3]], i32 5
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i16> [[TMP3]], i32 0
 ; CHECK-NEXT:    [[STRUCTIN1:%.*]] = insertvalue [[STRUCT1TY]] %StructIn0, i16 [[TMP5]], 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i16> [[TMP3]], i32 6
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <8 x i16> [[TMP3]], i32 2
 ; CHECK-NEXT:    [[STRUCTIN2:%.*]] = insertvalue [[STRUCT1TY]] undef, i16 [[TMP6]], 0
-; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <8 x i16> [[TMP3]], i32 7
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <8 x i16> [[TMP3]], i32 3
 ; CHECK-NEXT:    [[STRUCTIN3:%.*]] = insertvalue [[STRUCT1TY]] %StructIn2, i16 [[TMP7]], 1
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i16> [[TMP3]], i32 0
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i16> [[TMP3]], i32 4
 ; CHECK-NEXT:    [[STRUCTIN4:%.*]] = insertvalue [[STRUCT1TY]] undef, i16 [[TMP8]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i16> [[TMP3]], i32 1
+; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i16> [[TMP3]], i32 5
 ; CHECK-NEXT:    [[STRUCTIN5:%.*]] = insertvalue [[STRUCT1TY]] %StructIn4, i16 [[TMP9]], 1
-; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <8 x i16> [[TMP3]], i32 2
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <8 x i16> [[TMP3]], i32 7
 ; CHECK-NEXT:    [[STRUCTIN6:%.*]] = insertvalue [[STRUCT1TY]] undef, i16 [[TMP10]], 1
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i16> [[TMP3]], i32 3
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i16> [[TMP3]], i32 6
 ; CHECK-NEXT:    [[STRUCTIN7:%.*]] = insertvalue [[STRUCT1TY]] %StructIn6, i16 [[TMP11]], 0
 ; CHECK-NEXT:    [[STRUCT2IN0:%.*]] = insertvalue [[STRUCT2TY:%.*]] undef, [[STRUCT1TY]] %StructIn1, 0
 ; CHECK-NEXT:    [[STRUCT2IN1:%.*]] = insertvalue [[STRUCT2TY]] %Struct2In0, [[STRUCT1TY]] %StructIn3, 1