diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -3216,49 +3216,81 @@
     return BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
                                   CostKind);
 
-  // Handle non-power-of-two vectors such as <3 x float> and <48 x i16>
-  if (auto *VTy = dyn_cast<FixedVectorType>(Src)) {
-    const unsigned NumElem = VTy->getNumElements();
-    if (!isPowerOf2_32(NumElem)) {
-      // Factorize NumElem into sum of power-of-two.
-      InstructionCost Cost = 0;
-      unsigned NumElemDone = 0;
-      for (unsigned NumElemLeft = NumElem, Factor;
-           Factor = PowerOf2Floor(NumElemLeft), NumElemLeft > 0;
-           NumElemLeft -= Factor) {
-        Type *SubTy = FixedVectorType::get(VTy->getScalarType(), Factor);
-        unsigned SubTyBytes = SubTy->getPrimitiveSizeInBits() / 8;
-
-        Cost +=
-            getMemoryOpCost(Opcode, SubTy, Alignment, AddressSpace, CostKind);
-
-        std::pair<int, MVT> LST = TLI->getTypeLegalizationCost(DL, SubTy);
-        if (!LST.second.isVector()) {
-          APInt DemandedElts =
-              APInt::getBitsSet(NumElem, NumElemDone, NumElemDone + Factor);
-          Cost += getScalarizationOverhead(VTy, DemandedElts,
-                                           Opcode == Instruction::Load,
-                                           Opcode == Instruction::Store);
-        }
-
-        NumElemDone += Factor;
-        Alignment = commonAlignment(Alignment.valueOrOne(), SubTyBytes);
-      }
-      assert(NumElemDone == NumElem && "Processed wrong element count?");
-      return Cost;
-    }
-  }
-
   // Legalize the type.
   std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src);
 
-  // Each load/store unit costs 1.
-  int Cost = LT.first * 1;
+  errs() << "LT " << *EVT(LT.second).getTypeForEVT(Src->getContext()) << "\n";
 
-  // This isn't exactly right. We're using slow unaligned 32-byte accesses as a
-  // proxy for a double-pumped AVX memory interface such as on Sandybridge.
-  if (LT.second.getStoreSize() == 32 && ST->isUnalignedMem32Slow())
-    Cost *= 2;
+  auto *VTy = dyn_cast<FixedVectorType>(Src);
+
+  // Handle the simple case of non-vectors.
+  // NOTE: this assumes that legalizatio never creates vector from scalars!
+  if (!VTy || !LT.second.isVector())
+    // Each load/store unit costs 1.
+    return LT.first * 1;
+
+  InstructionCost Cost = 0;
+
+  // Source of truth: how many elements were there in the original IR vector?
+  const unsigned SrcNumElt = VTy->getNumElements();
+
+  // To what vector did we legalize?
+  const int LegalBytes = LT.second.getSizeInBits() / 8;
+  const int LegalNumElt = LT.second.getVectorNumElements();
+
+  int NumEltRemaining = SrcNumElt;
+  auto NumEltDone = [&]() { return SrcNumElt - NumEltRemaining; };
+
+  // With what size are we currently operating?
+  int CurrLegalBytes = LegalBytes;
+  int CurrLegalNumElt = LegalNumElt;
+
+  auto *LegalizedTy =
+      EVT(LT.second.getVectorElementType()).getTypeForEVT(Src->getContext());
+  int NumEltInXMM = 128 / LegalizedTy->getScalarSizeInBits();
+  auto *LegalizedVTy = FixedVectorType::get(
+      LegalizedTy, LT.first * LT.second.getVectorNumElements());
+
+  // First, try to use whole-vector operations, with decreasing vector sizes.
+  for (; NumEltRemaining > 0 && CurrLegalBytes >= 64 / 8;
+       CurrLegalBytes /= 2, CurrLegalNumElt /= 2) {
+    assert(CurrLegalNumElt > 0 && "Reduced vector size too much?");
+    auto *CurrTy =
+        FixedVectorType::get(LegalizedVTy->getElementType(),
+                             std::max((int)CurrLegalNumElt, NumEltInXMM));
+    while (NumEltRemaining > 0) {
+      // Can we use this vector size, as per the remaining element count?
+      // Iff the vector is naturally aligned, we can do a wide load regardless.
+      if (NumEltRemaining < CurrLegalNumElt &&
+          (Opcode != Instruction::Load ||
+           Alignment.valueOrOne() < CurrLegalBytes))
+        break; // Try smalled vector size.
+
+      if (CurrLegalBytes != LegalBytes) {
+        Cost += getShuffleCost(Opcode == Instruction::Load
+                                   ? TTI::ShuffleKind::SK_InsertSubvector
+                                   : TTI::ShuffleKind::SK_ExtractSubvector,
+                               LegalizedVTy, None, NumEltDone(), CurrTy);
+      }
+
+      Cost += 1;
+      NumEltRemaining -= CurrLegalNumElt;
+      Alignment = commonAlignment(Alignment.valueOrOne(), CurrLegalBytes);
+    }
+  }
+
+  // Was that all, or do we still have remaining elements?
+  if (NumEltRemaining <= 0)
+    return Cost;
+
+  // The rest will have to be scalarized
+  // FIXME: we could coalesce loads, but getScalarizationOverhead() won't cope.
+  // FIXME: what are the legality rules for performing wider scalar loads?
+  Cost += countPopulation((unsigned)NumEltRemaining);
+  APInt DemandedElts = APInt::getBitsSet(SrcNumElt, NumEltDone(), SrcNumElt);
+  Cost +=
+      getScalarizationOverhead(VTy, DemandedElts, Opcode == Instruction::Load,
+                               Opcode == Instruction::Store);
 
   return Cost;
 }
diff --git a/llvm/test/Analysis/CostModel/X86/load_store.ll b/llvm/test/Analysis/CostModel/X86/load_store.ll
--- a/llvm/test/Analysis/CostModel/X86/load_store.ll
+++ b/llvm/test/Analysis/CostModel/X86/load_store.ll
@@ -22,19 +22,19 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <3 x double> undef, <3 x double>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -54,19 +54,19 @@
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -86,19 +86,19 @@
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -160,19 +160,19 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <3 x double> undef, <3 x double>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -192,19 +192,19 @@
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -224,19 +224,19 @@
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x float> undef, <3 x float>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: store <49 x i16> undef, <49 x i16>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -289,28 +289,28 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load i32, i32* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load i64, i64* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = load i128, i128* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = load <4 x i32>, <4 x i32>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = load <8 x i32>, <8 x i32>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
+; SSE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -321,28 +321,28 @@
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load i32, i32* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load i64, i64* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = load i128, i128* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = load <4 x i32>, <4 x i32>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = load <8 x i32>, <8 x i32>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
+; AVX-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 4
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
@@ -353,30 +353,30 @@
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load i32, i32* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load i64, i64* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = load i128, i128* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %6 = load <2 x i32>, <2 x i32>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = load <4 x i32>, <4 x i32>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = load <8 x i32>, <8 x i32>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 97 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 4
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   load i8, i8* undef, align 4
@@ -433,24 +433,24 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
+; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'loads_align'
@@ -465,24 +465,24 @@
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
+; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'loads_align'
@@ -497,24 +497,24 @@
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = load <2 x i64>, <2 x i64>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = load <4 x i64>, <4 x i64>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %11 = load <8 x i64>, <8 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %29 = load <49 x i16>, <49 x i16>* undef, align 64
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   load i8, i8* undef, align 64