diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 5b40e49714069..4d5cd963e0926 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -1376,7 +1376,7 @@ class TargetTransformInfoImplCRTPBase : public TargetTransformInfoImplBase {
 
           return TargetTTI->getShuffleCost(
               IsUnary ? TTI::SK_PermuteSingleSrc : TTI::SK_PermuteTwoSrc, VecTy,
-              AdjustMask, CostKind, 0, nullptr, {}, Shuffle);
+              AdjustMask, CostKind, 0, nullptr, Operands, Shuffle);
         }
 
         // Narrowing shuffle - perform shuffle at original wider width and
@@ -1385,7 +1385,7 @@ class TargetTransformInfoImplCRTPBase : public TargetTransformInfoImplBase {
 
         InstructionCost ShuffleCost = TargetTTI->getShuffleCost(
             IsUnary ? TTI::SK_PermuteSingleSrc : TTI::SK_PermuteTwoSrc,
-            VecSrcTy, AdjustMask, CostKind, 0, nullptr, {}, Shuffle);
+            VecSrcTy, AdjustMask, CostKind, 0, nullptr, Operands, Shuffle);
 
         SmallVector<int, 16> ExtractMask(Mask.size());
         std::iota(ExtractMask.begin(), ExtractMask.end(), 0);
diff --git a/llvm/include/llvm/IR/Instructions.h b/llvm/include/llvm/IR/Instructions.h
index 4ffa6349871ba..d7ec3c16bec21 100644
--- a/llvm/include/llvm/IR/Instructions.h
+++ b/llvm/include/llvm/IR/Instructions.h
@@ -2631,6 +2631,16 @@ class ShuffleVectorInst : public Instruction {
     return isInterleaveMask(Mask, Factor, NumInputElts, StartIndexes);
   }
 
+  /// Check if the mask is a DE-interleave mask of the given factor
+  /// \p Factor like:
+  ///     <Index, Index+Factor, ..., Index+(NumElts-1)*Factor>
+  static bool isDeInterleaveMaskOfFactor(ArrayRef<int> Mask, unsigned Factor,
+                                         unsigned &Index);
+  static bool isDeInterleaveMaskOfFactor(ArrayRef<int> Mask, unsigned Factor) {
+    unsigned Unused;
+    return isDeInterleaveMaskOfFactor(Mask, Factor, Unused);
+  }
+
   /// Checks if the shuffle is a bit rotation of the first operand across
   /// multiple subelements, e.g:
   ///
diff --git a/llvm/lib/CodeGen/InterleavedAccessPass.cpp b/llvm/lib/CodeGen/InterleavedAccessPass.cpp
index 438ac1c3cc6e2..8989eabbe6df2 100644
--- a/llvm/lib/CodeGen/InterleavedAccessPass.cpp
+++ b/llvm/lib/CodeGen/InterleavedAccessPass.cpp
@@ -200,28 +200,6 @@ FunctionPass *llvm::createInterleavedAccessPass() {
   return new InterleavedAccess();
 }
 
-/// Check if the mask is a DE-interleave mask of the given factor
-/// \p Factor like:
-///     <Index, Index+Factor, ..., Index+(NumElts-1)*Factor>
-static bool isDeInterleaveMaskOfFactor(ArrayRef<int> Mask, unsigned Factor,
-                                       unsigned &Index) {
-  // Check all potential start indices from 0 to (Factor - 1).
-  for (Index = 0; Index < Factor; Index++) {
-    unsigned i = 0;
-
-    // Check that elements are in ascending order by Factor. Ignore undef
-    // elements.
-    for (; i < Mask.size(); i++)
-      if (Mask[i] >= 0 && static_cast<unsigned>(Mask[i]) != Index + i * Factor)
-        break;
-
-    if (i == Mask.size())
-      return true;
-  }
-
-  return false;
-}
-
 /// Check if the mask is a DE-interleave mask for an interleaved load.
 ///
 /// E.g. DE-interleave masks (Factor = 2) could be:
@@ -238,7 +216,7 @@ static bool isDeInterleaveMask(ArrayRef<int> Mask, unsigned &Factor,
     // Make sure we don't produce a load wider than the input load.
     if (Mask.size() * Factor > NumLoadElements)
       return false;
-    if (isDeInterleaveMaskOfFactor(Mask, Factor, Index))
+    if (ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, Factor, Index))
       return true;
   }
 
@@ -333,8 +311,8 @@ bool InterleavedAccessImpl::lowerInterleavedLoad(
   for (auto *Shuffle : Shuffles) {
     if (Shuffle->getType() != VecTy)
       return false;
-    if (!isDeInterleaveMaskOfFactor(Shuffle->getShuffleMask(), Factor,
-                                    Index))
+    if (!ShuffleVectorInst::isDeInterleaveMaskOfFactor(
+            Shuffle->getShuffleMask(), Factor, Index))
       return false;
 
     assert(Shuffle->getShuffleMask().size() <= NumLoadElements);
@@ -343,8 +321,8 @@ bool InterleavedAccessImpl::lowerInterleavedLoad(
   for (auto *Shuffle : BinOpShuffles) {
     if (Shuffle->getType() != VecTy)
       return false;
-    if (!isDeInterleaveMaskOfFactor(Shuffle->getShuffleMask(), Factor,
-                                    Index))
+    if (!ShuffleVectorInst::isDeInterleaveMaskOfFactor(
+            Shuffle->getShuffleMask(), Factor, Index))
       return false;
 
     assert(Shuffle->getShuffleMask().size() <= NumLoadElements);
diff --git a/llvm/lib/IR/Instructions.cpp b/llvm/lib/IR/Instructions.cpp
index cec02e2ce6338..d2babc748731a 100644
--- a/llvm/lib/IR/Instructions.cpp
+++ b/llvm/lib/IR/Instructions.cpp
@@ -2978,6 +2978,31 @@ bool ShuffleVectorInst::isInterleaveMask(
   return true;
 }
 
+/// Check if the mask is a DE-interleave mask of the given factor
+/// \p Factor like:
+///     <Index, Index+Factor, ..., Index+(NumElts-1)*Factor>
+bool ShuffleVectorInst::isDeInterleaveMaskOfFactor(ArrayRef<int> Mask,
+                                                   unsigned Factor,
+                                                   unsigned &Index) {
+  // Check all potential start indices from 0 to (Factor - 1).
+  for (unsigned Idx = 0; Idx < Factor; Idx++) {
+    unsigned I = 0;
+
+    // Check that elements are in ascending order by Factor. Ignore undef
+    // elements.
+    for (; I < Mask.size(); I++)
+      if (Mask[I] >= 0 && static_cast<unsigned>(Mask[I]) != Idx + I * Factor)
+        break;
+
+    if (I == Mask.size()) {
+      Index = Idx;
+      return true;
+    }
+  }
+
+  return false;
+}
+
 /// Try to lower a vector shuffle as a bit rotation.
 ///
 /// Look for a repeated rotation pattern in each sub group.
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index e80931a03f30b..700242b88346c 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3827,9 +3827,18 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
       Tp->getScalarSizeInBits() == LT.second.getScalarSizeInBits() &&
       Mask.size() > LT.second.getVectorNumElements() && !Index && !SubTp) {
 
+    // Check for LD3/LD4 instructions, which are represented in llvm IR as
+    // deinterleaving-shuffle(load). The shuffle cost could potentially be free,
+    // but we model it with a cost of LT.first so that LD3/LD4 have a higher
+    // cost than just the load.
+    if (Args.size() >= 1 && isa<LoadInst>(Args[0]) &&
+        (ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, 3) ||
+         ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, 4)))
+      return std::max<InstructionCost>(1, LT.first / 4);
+
     // Check for ST3/ST4 instructions, which are represented in llvm IR as
     // store(interleaving-shuffle). The shuffle cost could potentially be free,
-    // but we model it with a cost of LT.first so that LD3/LD3 have a higher
+    // but we model it with a cost of LT.first so that ST3/ST4 have a higher
     // cost than just the store.
     if (CxtI && CxtI->hasOneUse() && isa<StoreInst>(*CxtI->user_begin()) &&
         (ShuffleVectorInst::isInterleaveMask(
diff --git a/llvm/test/Analysis/CostModel/AArch64/shuffle-load.ll b/llvm/test/Analysis/CostModel/AArch64/shuffle-load.ll
index 106f2f9edc2e4..bf81d7aa5e689 100644
--- a/llvm/test/Analysis/CostModel/AArch64/shuffle-load.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/shuffle-load.ll
@@ -572,45 +572,45 @@ define void @vld3(ptr %p) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_1 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_2 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = load <24 x i8>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i8 = load <48 x i8>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = load <6 x i16>, ptr %p, align 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_0 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 0, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_1 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 1, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_2 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 2, i32 5>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = load <12 x i16>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i16 = load <24 x i16>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i16 = load <48 x i16>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32 = load <6 x i32>, ptr %p, align 32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 0, i32 3>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_2 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 2, i32 5>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32 = load <12 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32 = load <24 x i32>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32 = load <48 x i32>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2i64 = load <6 x i64>, ptr %p, align 64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 0, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 1, i32 4>
@@ -639,45 +639,45 @@ define void @vld3(ptr %p) {
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_1 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_2 = shufflevector <12 x i8> %v4i8, <12 x i8> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = load <24 x i8>, ptr %p, align 32
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_1 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_2 = shufflevector <24 x i8> %v8i8, <24 x i8> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i8 = load <48 x i8>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_1 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_2 = shufflevector <48 x i8> %v16i8, <48 x i8> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = load <6 x i16>, ptr %p, align 16
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_0 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 0, i32 3>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_1 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 1, i32 4>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_2 = shufflevector <6 x i16> %v2i16, <6 x i16> undef, <2 x i32> <i32 2, i32 5>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = load <12 x i16>, ptr %p, align 32
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_1 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_2 = shufflevector <12 x i16> %v4i16, <12 x i16> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i16 = load <24 x i16>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_1 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2 = shufflevector <24 x i16> %v8i16, <24 x i16> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i16 = load <48 x i16>, ptr %p, align 128
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_0 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_1 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_2 = shufflevector <48 x i16> %v16i16, <48 x i16> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32 = load <6 x i32>, ptr %p, align 32
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 0, i32 3>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_2 = shufflevector <6 x i32> %v2i32, <6 x i32> undef, <2 x i32> <i32 2, i32 5>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32 = load <12 x i32>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_1 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2 = shufflevector <12 x i32> %v4i32, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32 = load <24 x i32>, ptr %p, align 128
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_0 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_1 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2 = shufflevector <24 x i32> %v8i32, <24 x i32> undef, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32 = load <48 x i32>, ptr %p, align 256
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_0 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21, i32 24, i32 27, i32 30, i32 33, i32 36, i32 39, i32 42, i32 45>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_1 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22, i32 25, i32 28, i32 31, i32 34, i32 37, i32 40, i32 43, i32 46>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_2 = shufflevector <48 x i32> %v16i32, <48 x i32> undef, <16 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23, i32 26, i32 29, i32 32, i32 35, i32 38, i32 41, i32 44, i32 47>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2i64 = load <6 x i64>, ptr %p, align 64
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 0, i32 3>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = shufflevector <6 x i64> %v2i64, <6 x i64> undef, <2 x i32> <i32 1, i32 4>
@@ -780,55 +780,55 @@ define void @vld4(ptr %p) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = load <32 x i8>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i8 = load <64 x i8>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = load <8 x i16>, ptr %p, align 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = load <16 x i16>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i16 = load <32 x i16>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i16 = load <64 x i16>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32 = load <8 x i32>, ptr %p, align 32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32 = load <16 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32 = load <32 x i32>, ptr %p, align 128
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32 = load <64 x i32>, ptr %p, align 256
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2i64 = load <8 x i64>, ptr %p, align 64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>
@@ -863,55 +863,55 @@ define void @vld4(ptr %p) {
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_2 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4i8_3 = shufflevector <16 x i8> %v4i8, <16 x i8> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i8 = load <32 x i8>, ptr %p, align 32
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_0 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_1 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_2 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i8_3 = shufflevector <32 x i8> %v8i8, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i8 = load <64 x i8>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_0 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_1 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_2 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8_3 = shufflevector <64 x i8> %v16i8, <64 x i8> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i16 = load <8 x i16>, ptr %p, align 16
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_0 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 0, i32 4>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_1 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 1, i32 5>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_2 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 2, i32 6>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v2i16_3 = shufflevector <8 x i16> %v2i16, <8 x i16> undef, <2 x i32> <i32 3, i32 7>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i16 = load <16 x i16>, ptr %p, align 32
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_0 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_1 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_2 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16_3 = shufflevector <16 x i16> %v4i16, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i16 = load <32 x i16>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_0 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_1 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_3 = shufflevector <32 x i16> %v8i16, <32 x i16> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16i16 = load <64 x i16>, ptr %p, align 128
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_0 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_1 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_2 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_3 = shufflevector <64 x i16> %v16i16, <64 x i16> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32 = load <8 x i32>, ptr %p, align 32
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_0 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 0, i32 4>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_1 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 1, i32 5>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_2 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 2, i32 6>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32_3 = shufflevector <8 x i32> %v2i32, <8 x i32> undef, <2 x i32> <i32 3, i32 7>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4i32 = load <16 x i32>, ptr %p, align 64
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_0 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_1 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_3 = shufflevector <16 x i32> %v4i32, <16 x i32> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v8i32 = load <32 x i32>, ptr %p, align 128
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_0 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_1 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_3 = shufflevector <32 x i32> %v8i32, <32 x i32> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v16i32 = load <64 x i32>, ptr %p, align 256
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
-; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_0 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_1 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_2 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30, i32 34, i32 38, i32 42, i32 46, i32 50, i32 54, i32 58, i32 62>
+; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_3 = shufflevector <64 x i32> %v16i32, <64 x i32> undef, <16 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31, i32 35, i32 39, i32 43, i32 47, i32 51, i32 55, i32 59, i32 63>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2i64 = load <8 x i64>, ptr %p, align 64
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_0 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 0, i32 4>
 ; CODESIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64_1 = shufflevector <8 x i64> %v2i64, <8 x i64> undef, <2 x i32> <i32 1, i32 5>