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
@@ -5536,10 +5536,15 @@
 }
 
 unsigned BoUpSLP::getVectorElementSize(Value *V) {
-  // If V is a store, just return the width of the stored value without
-  // traversing the expression tree. This is the common case.
-  if (auto *Store = dyn_cast<StoreInst>(V))
-    return DL->getTypeSizeInBits(Store->getValueOperand()->getType());
+  // If V is a store, just return the width of the stored value (or value
+  // truncated just before storing) without traversing the expression tree.
+  // This is the common case.
+  if (auto *Store = dyn_cast<StoreInst>(V)) {
+    if (auto *Trunc = dyn_cast<TruncInst>(Store->getValueOperand()))
+      return DL->getTypeSizeInBits(Trunc->getSrcTy());
+    else
+      return DL->getTypeSizeInBits(Store->getValueOperand()->getType());
+  }
 
   auto E = InstrElementSize.find(V);
   if (E != InstrElementSize.end())
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-after-bundle.ll
@@ -22,132 +22,304 @@
 }
 
 define void @bar(i8* noalias nocapture readonly %a, i8* noalias nocapture readonly %b, i8* noalias nocapture readonly %c, i8* noalias nocapture readonly %d, i8* noalias nocapture %e, i32 %w) local_unnamed_addr #1 {
-; CHECK-LABEL: @bar(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <16 x i32> undef, i32 [[W:%.*]], i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <16 x i32> [[TMP0]], i32 [[W]], i32 1
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i32> [[TMP1]], i32 [[W]], i32 2
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i32> [[TMP2]], i32 [[W]], i32 3
-; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i32> [[TMP3]], i32 [[W]], i32 4
-; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i32> [[TMP4]], i32 [[W]], i32 5
-; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i32> [[TMP5]], i32 [[W]], i32 6
-; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i32> [[TMP6]], i32 [[W]], i32 7
-; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i32> [[TMP7]], i32 [[W]], i32 8
-; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i32> [[TMP8]], i32 [[W]], i32 9
-; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i32> [[TMP9]], i32 [[W]], i32 10
-; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i32> [[TMP10]], i32 [[W]], i32 11
-; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <16 x i32> [[TMP11]], i32 [[W]], i32 12
-; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x i32> [[TMP12]], i32 [[W]], i32 13
-; CHECK-NEXT:    [[TMP14:%.*]] = insertelement <16 x i32> [[TMP13]], i32 [[W]], i32 14
-; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <16 x i32> [[TMP14]], i32 [[W]], i32 15
-; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
-; CHECK:       for.body:
-; CHECK-NEXT:    [[I_0356:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[A_ADDR_0355:%.*]] = phi i8* [ [[A:%.*]], [[ENTRY]] ], [ [[ADD_PTR:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[E_ADDR_0354:%.*]] = phi i8* [ [[E:%.*]], [[ENTRY]] ], [ [[ADD_PTR192:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[D_ADDR_0353:%.*]] = phi i8* [ [[D:%.*]], [[ENTRY]] ], [ [[ADD_PTR191:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[C_ADDR_0352:%.*]] = phi i8* [ [[C:%.*]], [[ENTRY]] ], [ [[ADD_PTR190:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[B_ADDR_0351:%.*]] = phi i8* [ [[B:%.*]], [[ENTRY]] ], [ [[ADD_PTR189:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 1
-; CHECK-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 1
-; CHECK-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 1
-; CHECK-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 1
-; CHECK-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 1
-; CHECK-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX28:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 2
-; CHECK-NEXT:    [[ARRAYIDX33:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 3
-; CHECK-NEXT:    [[ARRAYIDX35:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 3
-; CHECK-NEXT:    [[ARRAYIDX37:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 3
-; CHECK-NEXT:    [[ARRAYIDX40:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 3
-; CHECK-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 3
-; CHECK-NEXT:    [[ARRAYIDX45:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX47:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX49:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX52:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX56:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 4
-; CHECK-NEXT:    [[ARRAYIDX57:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 5
-; CHECK-NEXT:    [[ARRAYIDX59:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 5
-; CHECK-NEXT:    [[ARRAYIDX61:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 5
-; CHECK-NEXT:    [[ARRAYIDX64:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 5
-; CHECK-NEXT:    [[ARRAYIDX68:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 5
-; CHECK-NEXT:    [[ARRAYIDX69:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX71:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX73:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX76:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX80:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 6
-; CHECK-NEXT:    [[ARRAYIDX81:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 7
-; CHECK-NEXT:    [[ARRAYIDX83:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 7
-; CHECK-NEXT:    [[ARRAYIDX85:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 7
-; CHECK-NEXT:    [[ARRAYIDX88:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 7
-; CHECK-NEXT:    [[ARRAYIDX92:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 7
-; CHECK-NEXT:    [[ARRAYIDX93:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 8
-; CHECK-NEXT:    [[ARRAYIDX95:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 8
-; CHECK-NEXT:    [[ARRAYIDX97:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 8
-; CHECK-NEXT:    [[ARRAYIDX100:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 8
-; CHECK-NEXT:    [[ARRAYIDX104:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 8
-; CHECK-NEXT:    [[ARRAYIDX105:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 9
-; CHECK-NEXT:    [[ARRAYIDX107:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 9
-; CHECK-NEXT:    [[ARRAYIDX109:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 9
-; CHECK-NEXT:    [[ARRAYIDX112:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 9
-; CHECK-NEXT:    [[ARRAYIDX116:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 9
-; CHECK-NEXT:    [[ARRAYIDX117:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 10
-; CHECK-NEXT:    [[ARRAYIDX119:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 10
-; CHECK-NEXT:    [[ARRAYIDX121:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 10
-; CHECK-NEXT:    [[ARRAYIDX124:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 10
-; CHECK-NEXT:    [[ARRAYIDX128:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 10
-; CHECK-NEXT:    [[ARRAYIDX129:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 11
-; CHECK-NEXT:    [[ARRAYIDX131:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 11
-; CHECK-NEXT:    [[ARRAYIDX133:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 11
-; CHECK-NEXT:    [[ARRAYIDX136:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 11
-; CHECK-NEXT:    [[ARRAYIDX140:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 11
-; CHECK-NEXT:    [[ARRAYIDX141:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 12
-; CHECK-NEXT:    [[ARRAYIDX143:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 12
-; CHECK-NEXT:    [[ARRAYIDX145:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 12
-; CHECK-NEXT:    [[ARRAYIDX148:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 12
-; CHECK-NEXT:    [[ARRAYIDX152:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 12
-; CHECK-NEXT:    [[ARRAYIDX153:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 13
-; CHECK-NEXT:    [[ARRAYIDX155:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 13
-; CHECK-NEXT:    [[ARRAYIDX157:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 13
-; CHECK-NEXT:    [[ARRAYIDX160:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 13
-; CHECK-NEXT:    [[ARRAYIDX164:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 13
-; CHECK-NEXT:    [[ARRAYIDX165:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 14
-; CHECK-NEXT:    [[ARRAYIDX167:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 14
-; CHECK-NEXT:    [[ARRAYIDX169:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 14
-; CHECK-NEXT:    [[ARRAYIDX172:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 14
-; CHECK-NEXT:    [[ARRAYIDX176:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 14
-; CHECK-NEXT:    [[ARRAYIDX177:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 15
-; CHECK-NEXT:    [[TMP16:%.*]] = bitcast i8* [[C_ADDR_0352]] to <16 x i8>*
-; CHECK-NEXT:    [[TMP17:%.*]] = load <16 x i8>, <16 x i8>* [[TMP16]], align 1
-; CHECK-NEXT:    [[ARRAYIDX179:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 15
-; CHECK-NEXT:    [[TMP18:%.*]] = bitcast i8* [[D_ADDR_0353]] to <16 x i8>*
-; CHECK-NEXT:    [[TMP19:%.*]] = load <16 x i8>, <16 x i8>* [[TMP18]], align 1
-; CHECK-NEXT:    [[ARRAYIDX181:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 15
-; CHECK-NEXT:    [[TMP20:%.*]] = bitcast i8* [[A_ADDR_0355]] to <16 x i8>*
-; CHECK-NEXT:    [[TMP21:%.*]] = load <16 x i8>, <16 x i8>* [[TMP20]], align 1
-; CHECK-NEXT:    [[ARRAYIDX184:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 15
-; CHECK-NEXT:    [[TMP22:%.*]] = bitcast i8* [[B_ADDR_0351]] to <16 x i8>*
-; CHECK-NEXT:    [[TMP23:%.*]] = load <16 x i8>, <16 x i8>* [[TMP22]], align 1
-; CHECK-NEXT:    [[TMP24:%.*]] = icmp ult <16 x i8> [[TMP17]], [[TMP19]]
-; CHECK-NEXT:    [[TMP25:%.*]] = select <16 x i1> [[TMP24]], <16 x i8> [[TMP23]], <16 x i8> [[TMP21]]
-; CHECK-NEXT:    [[TMP26:%.*]] = zext <16 x i8> [[TMP25]] to <16 x i32>
-; CHECK-NEXT:    [[TMP27:%.*]] = mul <16 x i32> [[TMP26]], [[TMP15]]
-; CHECK-NEXT:    [[TMP28:%.*]] = trunc <16 x i32> [[TMP27]] to <16 x i8>
-; CHECK-NEXT:    [[ARRAYIDX188:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 15
-; CHECK-NEXT:    [[TMP29:%.*]] = bitcast i8* [[E_ADDR_0354]] to <16 x i8>*
-; CHECK-NEXT:    store <16 x i8> [[TMP28]], <16 x i8>* [[TMP29]], align 1
-; CHECK-NEXT:    [[INC]] = add nuw nsw i32 [[I_0356]], 1
-; CHECK-NEXT:    [[ADD_PTR]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 16
-; CHECK-NEXT:    [[ADD_PTR189]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 16
-; CHECK-NEXT:    [[ADD_PTR190]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 16
-; CHECK-NEXT:    [[ADD_PTR191]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 16
-; CHECK-NEXT:    [[ADD_PTR192]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 16
-; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 8
-; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
-; CHECK:       for.end:
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @bar(
+; SSE-NEXT:  entry:
+; SSE-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> undef, i32 [[W:%.*]], i32 0
+; SSE-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[W]], i32 1
+; SSE-NEXT:    [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[W]], i32 2
+; SSE-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[W]], i32 3
+; SSE-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> undef, i32 [[W]], i32 0
+; SSE-NEXT:    [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[W]], i32 1
+; SSE-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[W]], i32 2
+; SSE-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> [[TMP6]], i32 [[W]], i32 3
+; SSE-NEXT:    [[TMP8:%.*]] = insertelement <4 x i32> undef, i32 [[W]], i32 0
+; SSE-NEXT:    [[TMP9:%.*]] = insertelement <4 x i32> [[TMP8]], i32 [[W]], i32 1
+; SSE-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[W]], i32 2
+; SSE-NEXT:    [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[W]], i32 3
+; SSE-NEXT:    [[TMP12:%.*]] = insertelement <4 x i32> undef, i32 [[W]], i32 0
+; SSE-NEXT:    [[TMP13:%.*]] = insertelement <4 x i32> [[TMP12]], i32 [[W]], i32 1
+; SSE-NEXT:    [[TMP14:%.*]] = insertelement <4 x i32> [[TMP13]], i32 [[W]], i32 2
+; SSE-NEXT:    [[TMP15:%.*]] = insertelement <4 x i32> [[TMP14]], i32 [[W]], i32 3
+; SSE-NEXT:    br label [[FOR_BODY:%.*]]
+; SSE:       for.body:
+; SSE-NEXT:    [[I_0356:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[A_ADDR_0355:%.*]] = phi i8* [ [[A:%.*]], [[ENTRY]] ], [ [[ADD_PTR:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[E_ADDR_0354:%.*]] = phi i8* [ [[E:%.*]], [[ENTRY]] ], [ [[ADD_PTR192:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[D_ADDR_0353:%.*]] = phi i8* [ [[D:%.*]], [[ENTRY]] ], [ [[ADD_PTR191:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[C_ADDR_0352:%.*]] = phi i8* [ [[C:%.*]], [[ENTRY]] ], [ [[ADD_PTR190:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[B_ADDR_0351:%.*]] = phi i8* [ [[B:%.*]], [[ENTRY]] ], [ [[ADD_PTR189:%.*]], [[FOR_BODY]] ]
+; SSE-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 1
+; SSE-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 1
+; SSE-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 1
+; SSE-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 1
+; SSE-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 1
+; SSE-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 2
+; SSE-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 2
+; SSE-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 2
+; SSE-NEXT:    [[ARRAYIDX28:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 2
+; SSE-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 2
+; SSE-NEXT:    [[ARRAYIDX33:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 3
+; SSE-NEXT:    [[TMP16:%.*]] = bitcast i8* [[C_ADDR_0352]] to <4 x i8>*
+; SSE-NEXT:    [[TMP17:%.*]] = load <4 x i8>, <4 x i8>* [[TMP16]], align 1
+; SSE-NEXT:    [[ARRAYIDX35:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 3
+; SSE-NEXT:    [[TMP18:%.*]] = bitcast i8* [[D_ADDR_0353]] to <4 x i8>*
+; SSE-NEXT:    [[TMP19:%.*]] = load <4 x i8>, <4 x i8>* [[TMP18]], align 1
+; SSE-NEXT:    [[ARRAYIDX37:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 3
+; SSE-NEXT:    [[TMP20:%.*]] = bitcast i8* [[A_ADDR_0355]] to <4 x i8>*
+; SSE-NEXT:    [[TMP21:%.*]] = load <4 x i8>, <4 x i8>* [[TMP20]], align 1
+; SSE-NEXT:    [[ARRAYIDX40:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 3
+; SSE-NEXT:    [[TMP22:%.*]] = bitcast i8* [[B_ADDR_0351]] to <4 x i8>*
+; SSE-NEXT:    [[TMP23:%.*]] = load <4 x i8>, <4 x i8>* [[TMP22]], align 1
+; SSE-NEXT:    [[TMP24:%.*]] = icmp ult <4 x i8> [[TMP17]], [[TMP19]]
+; SSE-NEXT:    [[TMP25:%.*]] = select <4 x i1> [[TMP24]], <4 x i8> [[TMP23]], <4 x i8> [[TMP21]]
+; SSE-NEXT:    [[TMP26:%.*]] = zext <4 x i8> [[TMP25]] to <4 x i32>
+; SSE-NEXT:    [[TMP27:%.*]] = mul <4 x i32> [[TMP26]], [[TMP3]]
+; SSE-NEXT:    [[TMP28:%.*]] = trunc <4 x i32> [[TMP27]] to <4 x i8>
+; SSE-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 3
+; SSE-NEXT:    [[TMP29:%.*]] = bitcast i8* [[E_ADDR_0354]] to <4 x i8>*
+; SSE-NEXT:    store <4 x i8> [[TMP28]], <4 x i8>* [[TMP29]], align 1
+; SSE-NEXT:    [[ARRAYIDX45:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 4
+; SSE-NEXT:    [[ARRAYIDX47:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 4
+; SSE-NEXT:    [[ARRAYIDX49:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 4
+; SSE-NEXT:    [[ARRAYIDX52:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 4
+; SSE-NEXT:    [[ARRAYIDX56:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 4
+; SSE-NEXT:    [[ARRAYIDX57:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 5
+; SSE-NEXT:    [[ARRAYIDX59:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 5
+; SSE-NEXT:    [[ARRAYIDX61:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 5
+; SSE-NEXT:    [[ARRAYIDX64:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 5
+; SSE-NEXT:    [[ARRAYIDX68:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 5
+; SSE-NEXT:    [[ARRAYIDX69:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 6
+; SSE-NEXT:    [[ARRAYIDX71:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 6
+; SSE-NEXT:    [[ARRAYIDX73:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 6
+; SSE-NEXT:    [[ARRAYIDX76:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 6
+; SSE-NEXT:    [[ARRAYIDX80:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 6
+; SSE-NEXT:    [[ARRAYIDX81:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 7
+; SSE-NEXT:    [[TMP30:%.*]] = bitcast i8* [[ARRAYIDX45]] to <4 x i8>*
+; SSE-NEXT:    [[TMP31:%.*]] = load <4 x i8>, <4 x i8>* [[TMP30]], align 1
+; SSE-NEXT:    [[ARRAYIDX83:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 7
+; SSE-NEXT:    [[TMP32:%.*]] = bitcast i8* [[ARRAYIDX47]] to <4 x i8>*
+; SSE-NEXT:    [[TMP33:%.*]] = load <4 x i8>, <4 x i8>* [[TMP32]], align 1
+; SSE-NEXT:    [[ARRAYIDX85:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 7
+; SSE-NEXT:    [[TMP34:%.*]] = bitcast i8* [[ARRAYIDX49]] to <4 x i8>*
+; SSE-NEXT:    [[TMP35:%.*]] = load <4 x i8>, <4 x i8>* [[TMP34]], align 1
+; SSE-NEXT:    [[ARRAYIDX88:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 7
+; SSE-NEXT:    [[TMP36:%.*]] = bitcast i8* [[ARRAYIDX52]] to <4 x i8>*
+; SSE-NEXT:    [[TMP37:%.*]] = load <4 x i8>, <4 x i8>* [[TMP36]], align 1
+; SSE-NEXT:    [[TMP38:%.*]] = icmp ult <4 x i8> [[TMP31]], [[TMP33]]
+; SSE-NEXT:    [[TMP39:%.*]] = select <4 x i1> [[TMP38]], <4 x i8> [[TMP37]], <4 x i8> [[TMP35]]
+; SSE-NEXT:    [[TMP40:%.*]] = zext <4 x i8> [[TMP39]] to <4 x i32>
+; SSE-NEXT:    [[TMP41:%.*]] = mul <4 x i32> [[TMP40]], [[TMP7]]
+; SSE-NEXT:    [[TMP42:%.*]] = trunc <4 x i32> [[TMP41]] to <4 x i8>
+; SSE-NEXT:    [[ARRAYIDX92:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 7
+; SSE-NEXT:    [[TMP43:%.*]] = bitcast i8* [[ARRAYIDX56]] to <4 x i8>*
+; SSE-NEXT:    store <4 x i8> [[TMP42]], <4 x i8>* [[TMP43]], align 1
+; SSE-NEXT:    [[ARRAYIDX93:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 8
+; SSE-NEXT:    [[ARRAYIDX95:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 8
+; SSE-NEXT:    [[ARRAYIDX97:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 8
+; SSE-NEXT:    [[ARRAYIDX100:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 8
+; SSE-NEXT:    [[ARRAYIDX104:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 8
+; SSE-NEXT:    [[ARRAYIDX105:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 9
+; SSE-NEXT:    [[ARRAYIDX107:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 9
+; SSE-NEXT:    [[ARRAYIDX109:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 9
+; SSE-NEXT:    [[ARRAYIDX112:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 9
+; SSE-NEXT:    [[ARRAYIDX116:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 9
+; SSE-NEXT:    [[ARRAYIDX117:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 10
+; SSE-NEXT:    [[ARRAYIDX119:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 10
+; SSE-NEXT:    [[ARRAYIDX121:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 10
+; SSE-NEXT:    [[ARRAYIDX124:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 10
+; SSE-NEXT:    [[ARRAYIDX128:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 10
+; SSE-NEXT:    [[ARRAYIDX129:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 11
+; SSE-NEXT:    [[TMP44:%.*]] = bitcast i8* [[ARRAYIDX93]] to <4 x i8>*
+; SSE-NEXT:    [[TMP45:%.*]] = load <4 x i8>, <4 x i8>* [[TMP44]], align 1
+; SSE-NEXT:    [[ARRAYIDX131:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 11
+; SSE-NEXT:    [[TMP46:%.*]] = bitcast i8* [[ARRAYIDX95]] to <4 x i8>*
+; SSE-NEXT:    [[TMP47:%.*]] = load <4 x i8>, <4 x i8>* [[TMP46]], align 1
+; SSE-NEXT:    [[ARRAYIDX133:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 11
+; SSE-NEXT:    [[TMP48:%.*]] = bitcast i8* [[ARRAYIDX97]] to <4 x i8>*
+; SSE-NEXT:    [[TMP49:%.*]] = load <4 x i8>, <4 x i8>* [[TMP48]], align 1
+; SSE-NEXT:    [[ARRAYIDX136:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 11
+; SSE-NEXT:    [[TMP50:%.*]] = bitcast i8* [[ARRAYIDX100]] to <4 x i8>*
+; SSE-NEXT:    [[TMP51:%.*]] = load <4 x i8>, <4 x i8>* [[TMP50]], align 1
+; SSE-NEXT:    [[TMP52:%.*]] = icmp ult <4 x i8> [[TMP45]], [[TMP47]]
+; SSE-NEXT:    [[TMP53:%.*]] = select <4 x i1> [[TMP52]], <4 x i8> [[TMP51]], <4 x i8> [[TMP49]]
+; SSE-NEXT:    [[TMP54:%.*]] = zext <4 x i8> [[TMP53]] to <4 x i32>
+; SSE-NEXT:    [[TMP55:%.*]] = mul <4 x i32> [[TMP54]], [[TMP11]]
+; SSE-NEXT:    [[TMP56:%.*]] = trunc <4 x i32> [[TMP55]] to <4 x i8>
+; SSE-NEXT:    [[ARRAYIDX140:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 11
+; SSE-NEXT:    [[TMP57:%.*]] = bitcast i8* [[ARRAYIDX104]] to <4 x i8>*
+; SSE-NEXT:    store <4 x i8> [[TMP56]], <4 x i8>* [[TMP57]], align 1
+; SSE-NEXT:    [[ARRAYIDX141:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 12
+; SSE-NEXT:    [[ARRAYIDX143:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 12
+; SSE-NEXT:    [[ARRAYIDX145:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 12
+; SSE-NEXT:    [[ARRAYIDX148:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 12
+; SSE-NEXT:    [[ARRAYIDX152:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 12
+; SSE-NEXT:    [[ARRAYIDX153:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 13
+; SSE-NEXT:    [[ARRAYIDX155:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 13
+; SSE-NEXT:    [[ARRAYIDX157:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 13
+; SSE-NEXT:    [[ARRAYIDX160:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 13
+; SSE-NEXT:    [[ARRAYIDX164:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 13
+; SSE-NEXT:    [[ARRAYIDX165:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 14
+; SSE-NEXT:    [[ARRAYIDX167:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 14
+; SSE-NEXT:    [[ARRAYIDX169:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 14
+; SSE-NEXT:    [[ARRAYIDX172:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 14
+; SSE-NEXT:    [[ARRAYIDX176:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 14
+; SSE-NEXT:    [[ARRAYIDX177:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 15
+; SSE-NEXT:    [[TMP58:%.*]] = bitcast i8* [[ARRAYIDX141]] to <4 x i8>*
+; SSE-NEXT:    [[TMP59:%.*]] = load <4 x i8>, <4 x i8>* [[TMP58]], align 1
+; SSE-NEXT:    [[ARRAYIDX179:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 15
+; SSE-NEXT:    [[TMP60:%.*]] = bitcast i8* [[ARRAYIDX143]] to <4 x i8>*
+; SSE-NEXT:    [[TMP61:%.*]] = load <4 x i8>, <4 x i8>* [[TMP60]], align 1
+; SSE-NEXT:    [[ARRAYIDX181:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 15
+; SSE-NEXT:    [[TMP62:%.*]] = bitcast i8* [[ARRAYIDX145]] to <4 x i8>*
+; SSE-NEXT:    [[TMP63:%.*]] = load <4 x i8>, <4 x i8>* [[TMP62]], align 1
+; SSE-NEXT:    [[ARRAYIDX184:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 15
+; SSE-NEXT:    [[TMP64:%.*]] = bitcast i8* [[ARRAYIDX148]] to <4 x i8>*
+; SSE-NEXT:    [[TMP65:%.*]] = load <4 x i8>, <4 x i8>* [[TMP64]], align 1
+; SSE-NEXT:    [[TMP66:%.*]] = icmp ult <4 x i8> [[TMP59]], [[TMP61]]
+; SSE-NEXT:    [[TMP67:%.*]] = select <4 x i1> [[TMP66]], <4 x i8> [[TMP65]], <4 x i8> [[TMP63]]
+; SSE-NEXT:    [[TMP68:%.*]] = zext <4 x i8> [[TMP67]] to <4 x i32>
+; SSE-NEXT:    [[TMP69:%.*]] = mul <4 x i32> [[TMP68]], [[TMP15]]
+; SSE-NEXT:    [[TMP70:%.*]] = trunc <4 x i32> [[TMP69]] to <4 x i8>
+; SSE-NEXT:    [[ARRAYIDX188:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 15
+; SSE-NEXT:    [[TMP71:%.*]] = bitcast i8* [[ARRAYIDX152]] to <4 x i8>*
+; SSE-NEXT:    store <4 x i8> [[TMP70]], <4 x i8>* [[TMP71]], align 1
+; SSE-NEXT:    [[INC]] = add nuw nsw i32 [[I_0356]], 1
+; SSE-NEXT:    [[ADD_PTR]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 16
+; SSE-NEXT:    [[ADD_PTR189]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 16
+; SSE-NEXT:    [[ADD_PTR190]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 16
+; SSE-NEXT:    [[ADD_PTR191]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 16
+; SSE-NEXT:    [[ADD_PTR192]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 16
+; SSE-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 8
+; SSE-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; SSE:       for.end:
+; SSE-NEXT:    ret void
+;
+; AVX512-LABEL: @bar(
+; AVX512-NEXT:  entry:
+; AVX512-NEXT:    [[TMP0:%.*]] = insertelement <16 x i32> undef, i32 [[W:%.*]], i32 0
+; AVX512-NEXT:    [[TMP1:%.*]] = insertelement <16 x i32> [[TMP0]], i32 [[W]], i32 1
+; AVX512-NEXT:    [[TMP2:%.*]] = insertelement <16 x i32> [[TMP1]], i32 [[W]], i32 2
+; AVX512-NEXT:    [[TMP3:%.*]] = insertelement <16 x i32> [[TMP2]], i32 [[W]], i32 3
+; AVX512-NEXT:    [[TMP4:%.*]] = insertelement <16 x i32> [[TMP3]], i32 [[W]], i32 4
+; AVX512-NEXT:    [[TMP5:%.*]] = insertelement <16 x i32> [[TMP4]], i32 [[W]], i32 5
+; AVX512-NEXT:    [[TMP6:%.*]] = insertelement <16 x i32> [[TMP5]], i32 [[W]], i32 6
+; AVX512-NEXT:    [[TMP7:%.*]] = insertelement <16 x i32> [[TMP6]], i32 [[W]], i32 7
+; AVX512-NEXT:    [[TMP8:%.*]] = insertelement <16 x i32> [[TMP7]], i32 [[W]], i32 8
+; AVX512-NEXT:    [[TMP9:%.*]] = insertelement <16 x i32> [[TMP8]], i32 [[W]], i32 9
+; AVX512-NEXT:    [[TMP10:%.*]] = insertelement <16 x i32> [[TMP9]], i32 [[W]], i32 10
+; AVX512-NEXT:    [[TMP11:%.*]] = insertelement <16 x i32> [[TMP10]], i32 [[W]], i32 11
+; AVX512-NEXT:    [[TMP12:%.*]] = insertelement <16 x i32> [[TMP11]], i32 [[W]], i32 12
+; AVX512-NEXT:    [[TMP13:%.*]] = insertelement <16 x i32> [[TMP12]], i32 [[W]], i32 13
+; AVX512-NEXT:    [[TMP14:%.*]] = insertelement <16 x i32> [[TMP13]], i32 [[W]], i32 14
+; AVX512-NEXT:    [[TMP15:%.*]] = insertelement <16 x i32> [[TMP14]], i32 [[W]], i32 15
+; AVX512-NEXT:    br label [[FOR_BODY:%.*]]
+; AVX512:       for.body:
+; AVX512-NEXT:    [[I_0356:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[A_ADDR_0355:%.*]] = phi i8* [ [[A:%.*]], [[ENTRY]] ], [ [[ADD_PTR:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[E_ADDR_0354:%.*]] = phi i8* [ [[E:%.*]], [[ENTRY]] ], [ [[ADD_PTR192:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[D_ADDR_0353:%.*]] = phi i8* [ [[D:%.*]], [[ENTRY]] ], [ [[ADD_PTR191:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[C_ADDR_0352:%.*]] = phi i8* [ [[C:%.*]], [[ENTRY]] ], [ [[ADD_PTR190:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[B_ADDR_0351:%.*]] = phi i8* [ [[B:%.*]], [[ENTRY]] ], [ [[ADD_PTR189:%.*]], [[FOR_BODY]] ]
+; AVX512-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 1
+; AVX512-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 1
+; AVX512-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 1
+; AVX512-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 1
+; AVX512-NEXT:    [[ARRAYIDX20:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 1
+; AVX512-NEXT:    [[ARRAYIDX21:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 2
+; AVX512-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 2
+; AVX512-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 2
+; AVX512-NEXT:    [[ARRAYIDX28:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 2
+; AVX512-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 2
+; AVX512-NEXT:    [[ARRAYIDX33:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 3
+; AVX512-NEXT:    [[ARRAYIDX35:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 3
+; AVX512-NEXT:    [[ARRAYIDX37:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 3
+; AVX512-NEXT:    [[ARRAYIDX40:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 3
+; AVX512-NEXT:    [[ARRAYIDX44:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 3
+; AVX512-NEXT:    [[ARRAYIDX45:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 4
+; AVX512-NEXT:    [[ARRAYIDX47:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 4
+; AVX512-NEXT:    [[ARRAYIDX49:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 4
+; AVX512-NEXT:    [[ARRAYIDX52:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 4
+; AVX512-NEXT:    [[ARRAYIDX56:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 4
+; AVX512-NEXT:    [[ARRAYIDX57:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 5
+; AVX512-NEXT:    [[ARRAYIDX59:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 5
+; AVX512-NEXT:    [[ARRAYIDX61:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 5
+; AVX512-NEXT:    [[ARRAYIDX64:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 5
+; AVX512-NEXT:    [[ARRAYIDX68:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 5
+; AVX512-NEXT:    [[ARRAYIDX69:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 6
+; AVX512-NEXT:    [[ARRAYIDX71:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 6
+; AVX512-NEXT:    [[ARRAYIDX73:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 6
+; AVX512-NEXT:    [[ARRAYIDX76:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 6
+; AVX512-NEXT:    [[ARRAYIDX80:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 6
+; AVX512-NEXT:    [[ARRAYIDX81:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 7
+; AVX512-NEXT:    [[ARRAYIDX83:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 7
+; AVX512-NEXT:    [[ARRAYIDX85:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 7
+; AVX512-NEXT:    [[ARRAYIDX88:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 7
+; AVX512-NEXT:    [[ARRAYIDX92:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 7
+; AVX512-NEXT:    [[ARRAYIDX93:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 8
+; AVX512-NEXT:    [[ARRAYIDX95:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 8
+; AVX512-NEXT:    [[ARRAYIDX97:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 8
+; AVX512-NEXT:    [[ARRAYIDX100:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 8
+; AVX512-NEXT:    [[ARRAYIDX104:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 8
+; AVX512-NEXT:    [[ARRAYIDX105:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 9
+; AVX512-NEXT:    [[ARRAYIDX107:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 9
+; AVX512-NEXT:    [[ARRAYIDX109:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 9
+; AVX512-NEXT:    [[ARRAYIDX112:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 9
+; AVX512-NEXT:    [[ARRAYIDX116:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 9
+; AVX512-NEXT:    [[ARRAYIDX117:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 10
+; AVX512-NEXT:    [[ARRAYIDX119:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 10
+; AVX512-NEXT:    [[ARRAYIDX121:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 10
+; AVX512-NEXT:    [[ARRAYIDX124:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 10
+; AVX512-NEXT:    [[ARRAYIDX128:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 10
+; AVX512-NEXT:    [[ARRAYIDX129:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 11
+; AVX512-NEXT:    [[ARRAYIDX131:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 11
+; AVX512-NEXT:    [[ARRAYIDX133:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 11
+; AVX512-NEXT:    [[ARRAYIDX136:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 11
+; AVX512-NEXT:    [[ARRAYIDX140:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 11
+; AVX512-NEXT:    [[ARRAYIDX141:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 12
+; AVX512-NEXT:    [[ARRAYIDX143:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 12
+; AVX512-NEXT:    [[ARRAYIDX145:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 12
+; AVX512-NEXT:    [[ARRAYIDX148:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 12
+; AVX512-NEXT:    [[ARRAYIDX152:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 12
+; AVX512-NEXT:    [[ARRAYIDX153:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 13
+; AVX512-NEXT:    [[ARRAYIDX155:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 13
+; AVX512-NEXT:    [[ARRAYIDX157:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 13
+; AVX512-NEXT:    [[ARRAYIDX160:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 13
+; AVX512-NEXT:    [[ARRAYIDX164:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 13
+; AVX512-NEXT:    [[ARRAYIDX165:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 14
+; AVX512-NEXT:    [[ARRAYIDX167:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 14
+; AVX512-NEXT:    [[ARRAYIDX169:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 14
+; AVX512-NEXT:    [[ARRAYIDX172:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 14
+; AVX512-NEXT:    [[ARRAYIDX176:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 14
+; AVX512-NEXT:    [[ARRAYIDX177:%.*]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 15
+; AVX512-NEXT:    [[TMP16:%.*]] = bitcast i8* [[C_ADDR_0352]] to <16 x i8>*
+; AVX512-NEXT:    [[TMP17:%.*]] = load <16 x i8>, <16 x i8>* [[TMP16]], align 1
+; AVX512-NEXT:    [[ARRAYIDX179:%.*]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 15
+; AVX512-NEXT:    [[TMP18:%.*]] = bitcast i8* [[D_ADDR_0353]] to <16 x i8>*
+; AVX512-NEXT:    [[TMP19:%.*]] = load <16 x i8>, <16 x i8>* [[TMP18]], align 1
+; AVX512-NEXT:    [[ARRAYIDX181:%.*]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 15
+; AVX512-NEXT:    [[TMP20:%.*]] = bitcast i8* [[A_ADDR_0355]] to <16 x i8>*
+; AVX512-NEXT:    [[TMP21:%.*]] = load <16 x i8>, <16 x i8>* [[TMP20]], align 1
+; AVX512-NEXT:    [[ARRAYIDX184:%.*]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 15
+; AVX512-NEXT:    [[TMP22:%.*]] = bitcast i8* [[B_ADDR_0351]] to <16 x i8>*
+; AVX512-NEXT:    [[TMP23:%.*]] = load <16 x i8>, <16 x i8>* [[TMP22]], align 1
+; AVX512-NEXT:    [[TMP24:%.*]] = icmp ult <16 x i8> [[TMP17]], [[TMP19]]
+; AVX512-NEXT:    [[TMP25:%.*]] = select <16 x i1> [[TMP24]], <16 x i8> [[TMP23]], <16 x i8> [[TMP21]]
+; AVX512-NEXT:    [[TMP26:%.*]] = zext <16 x i8> [[TMP25]] to <16 x i32>
+; AVX512-NEXT:    [[TMP27:%.*]] = mul <16 x i32> [[TMP26]], [[TMP15]]
+; AVX512-NEXT:    [[TMP28:%.*]] = trunc <16 x i32> [[TMP27]] to <16 x i8>
+; AVX512-NEXT:    [[ARRAYIDX188:%.*]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 15
+; AVX512-NEXT:    [[TMP29:%.*]] = bitcast i8* [[E_ADDR_0354]] to <16 x i8>*
+; AVX512-NEXT:    store <16 x i8> [[TMP28]], <16 x i8>* [[TMP29]], align 1
+; AVX512-NEXT:    [[INC]] = add nuw nsw i32 [[I_0356]], 1
+; AVX512-NEXT:    [[ADD_PTR]] = getelementptr inbounds i8, i8* [[A_ADDR_0355]], i64 16
+; AVX512-NEXT:    [[ADD_PTR189]] = getelementptr inbounds i8, i8* [[B_ADDR_0351]], i64 16
+; AVX512-NEXT:    [[ADD_PTR190]] = getelementptr inbounds i8, i8* [[C_ADDR_0352]], i64 16
+; AVX512-NEXT:    [[ADD_PTR191]] = getelementptr inbounds i8, i8* [[D_ADDR_0353]], i64 16
+; AVX512-NEXT:    [[ADD_PTR192]] = getelementptr inbounds i8, i8* [[E_ADDR_0354]], i64 16
+; AVX512-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 8
+; AVX512-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; AVX512:       for.end:
+; AVX512-NEXT:    ret void
 ;
 entry:
   br label %for.body
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/pr46983.ll b/llvm/test/Transforms/SLPVectorizer/X86/pr46983.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/pr46983.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/pr46983.ll
@@ -51,41 +51,18 @@
 
 define void @store_i8(i8* nocapture %0, i32 %1, i32 %2) {
 ; CHECK-LABEL: @store_i8(
-; CHECK-NEXT:    [[TMP4:%.*]] = load i8, i8* [[TMP0:%.*]], align 1, [[TBAA4:!tbaa !.*]]
-; CHECK-NEXT:    [[TMP5:%.*]] = zext i8 [[TMP4]] to i32
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i32 [[TMP5]], [[TMP1:%.*]]
-; CHECK-NEXT:    [[TMP7:%.*]] = lshr i32 [[TMP6]], 15
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp ult i32 [[TMP7]], 255
-; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[TMP8]], i32 [[TMP7]], i32 255
-; CHECK-NEXT:    [[TMP10:%.*]] = trunc i32 [[TMP9]] to i8
-; CHECK-NEXT:    store i8 [[TMP10]], i8* [[TMP0]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 1
-; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[TMP11]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP13:%.*]] = zext i8 [[TMP12]] to i32
-; CHECK-NEXT:    [[TMP14:%.*]] = mul i32 [[TMP13]], [[TMP1]]
-; CHECK-NEXT:    [[TMP15:%.*]] = lshr i32 [[TMP14]], 15
-; CHECK-NEXT:    [[TMP16:%.*]] = icmp ult i32 [[TMP15]], 255
-; CHECK-NEXT:    [[TMP17:%.*]] = select i1 [[TMP16]], i32 [[TMP15]], i32 255
-; CHECK-NEXT:    [[TMP18:%.*]] = trunc i32 [[TMP17]] to i8
-; CHECK-NEXT:    store i8 [[TMP18]], i8* [[TMP11]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 2
-; CHECK-NEXT:    [[TMP20:%.*]] = load i8, i8* [[TMP19]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP21:%.*]] = zext i8 [[TMP20]] to i32
-; CHECK-NEXT:    [[TMP22:%.*]] = mul i32 [[TMP21]], [[TMP1]]
-; CHECK-NEXT:    [[TMP23:%.*]] = lshr i32 [[TMP22]], 15
-; CHECK-NEXT:    [[TMP24:%.*]] = icmp ult i32 [[TMP23]], 255
-; CHECK-NEXT:    [[TMP25:%.*]] = select i1 [[TMP24]], i32 [[TMP23]], i32 255
-; CHECK-NEXT:    [[TMP26:%.*]] = trunc i32 [[TMP25]] to i8
-; CHECK-NEXT:    store i8 [[TMP26]], i8* [[TMP19]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i8, i8* [[TMP0]], i64 3
-; CHECK-NEXT:    [[TMP28:%.*]] = load i8, i8* [[TMP27]], align 1, [[TBAA4]]
-; CHECK-NEXT:    [[TMP29:%.*]] = zext i8 [[TMP28]] to i32
-; CHECK-NEXT:    [[TMP30:%.*]] = mul i32 [[TMP29]], [[TMP1]]
-; CHECK-NEXT:    [[TMP31:%.*]] = lshr i32 [[TMP30]], 15
-; CHECK-NEXT:    [[TMP32:%.*]] = icmp ult i32 [[TMP31]], 255
-; CHECK-NEXT:    [[TMP33:%.*]] = select i1 [[TMP32]], i32 [[TMP31]], i32 255
-; CHECK-NEXT:    [[TMP34:%.*]] = trunc i32 [[TMP33]] to i8
-; CHECK-NEXT:    store i8 [[TMP34]], i8* [[TMP27]], align 1, [[TBAA4]]
+; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP0:%.*]] to <4 x i8>*
+; CHECK-NEXT:    [[TMP5:%.*]] = load <4 x i8>, <4 x i8>* [[TMP4]], align 1, [[TBAA4:!tbaa !.*]]
+; CHECK-NEXT:    [[TMP6:%.*]] = zext <4 x i8> [[TMP5]] to <4 x i32>
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x i32> undef, i32 [[TMP1:%.*]], i32 0
+; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <4 x i32> [[TMP7]], <4 x i32> undef, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = mul <4 x i32> [[TMP8]], [[TMP6]]
+; CHECK-NEXT:    [[TMP10:%.*]] = lshr <4 x i32> [[TMP9]], <i32 15, i32 15, i32 15, i32 15>
+; CHECK-NEXT:    [[TMP11:%.*]] = icmp ult <4 x i32> [[TMP10]], <i32 255, i32 255, i32 255, i32 255>
+; CHECK-NEXT:    [[TMP12:%.*]] = select <4 x i1> [[TMP11]], <4 x i32> [[TMP10]], <4 x i32> <i32 255, i32 255, i32 255, i32 255>
+; CHECK-NEXT:    [[TMP13:%.*]] = trunc <4 x i32> [[TMP12]] to <4 x i8>
+; CHECK-NEXT:    [[TMP14:%.*]] = bitcast i8* [[TMP0]] to <4 x i8>*
+; CHECK-NEXT:    store <4 x i8> [[TMP13]], <4 x i8>* [[TMP14]], align 1, [[TBAA4]]
 ; CHECK-NEXT:    ret void
 ;
   %4 = load i8, i8* %0, align 1, !tbaa !6