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
@@ -3209,42 +3209,48 @@
     return TTI::TCC_Basic;
   }
 
-  // Handle non-power-of-two vectors such as <3 x float>
-  if (auto *VTy = dyn_cast<FixedVectorType>(Src)) {
-    unsigned NumElem = VTy->getNumElements();
-
-    // Handle a few common cases:
-    // <3 x float>
-    if (NumElem == 3 && VTy->getScalarSizeInBits() == 32)
-      // Cost = 64 bit store + extract + 32 bit store.
-      return 3;
-
-    // <3 x double>
-    if (NumElem == 3 && VTy->getScalarSizeInBits() == 64)
-      // Cost = 128 bit store + unpack + 64 bit store.
-      return 3;
-
-    // Assume that all other non-power-of-two numbers are scalarized.
-    if (!isPowerOf2_32(NumElem)) {
-      APInt DemandedElts = APInt::getAllOnesValue(NumElem);
-      InstructionCost Cost = BaseT::getMemoryOpCost(
-          Opcode, VTy->getScalarType(), Alignment, AddressSpace, CostKind);
-      int SplitCost = getScalarizationOverhead(VTy, DemandedElts,
-                                               Opcode == Instruction::Load,
-                                               Opcode == Instruction::Store);
-      return NumElem * Cost + SplitCost;
-    }
-  }
-
+  assert((Opcode == Instruction::Load || Opcode == Instruction::Store) &&
+         "Invalid Opcode");
   // Type legalization can't handle structs
-  if (TLI->getValueType(DL, Src,  true) == MVT::Other)
+  if (TLI->getValueType(DL, Src, true) == MVT::Other)
     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);
-  assert((Opcode == Instruction::Load || Opcode == Instruction::Store) &&
-         "Invalid Opcode");
 
   // Each load/store unit costs 1.
   int Cost = LT.first * 1;
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
@@ -20,23 +20,23 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, <8 x i32>* undef, align 4
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, <8 x i64>* undef, align 4
 ; 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 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* 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 13 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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 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
 ;
 ; AVX-LABEL: 'stores'
@@ -54,21 +54,21 @@
 ; 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 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 117 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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 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
 ;
 ; AVX512-LABEL: 'stores'
@@ -86,21 +86,21 @@
 ; 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 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 131 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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
 ;
   store i8 undef, i8* undef, align 4
@@ -158,23 +158,23 @@
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, <8 x i32>* undef, align 64
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, <8 x i64>* undef, align 64
 ; 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 3 for instruction: store <3 x double> undef, <3 x double>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: store <3 x i32> undef, <3 x i32>* 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 13 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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 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
 ;
 ; AVX-LABEL: 'stores_align'
@@ -192,21 +192,21 @@
 ; 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 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 59 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 117 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 122 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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 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
 ;
 ; AVX512-LABEL: 'stores_align'
@@ -224,21 +224,21 @@
 ; 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 3 for instruction: store <3 x i64> undef, <3 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: store <5 x i32> undef, <5 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: store <5 x i64> undef, <5 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: store <5 x i16> undef, <5 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <6 x i16> undef, <6 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <7 x i16> undef, <7 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: store <11 x i16> undef, <11 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: store <12 x i16> undef, <12 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: store <13 x i16> undef, <13 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: store <23 x i16> undef, <23 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: store <24 x i16> undef, <24 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 67 for instruction: store <25 x i16> undef, <25 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 125 for instruction: store <47 x i16> undef, <47 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: store <48 x i16> undef, <48 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 131 for instruction: store <49 x i16> undef, <49 x i16>* 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 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 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 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
 ;
   store i8 undef, i8* undef, align 64
@@ -295,24 +295,24 @@
 ; 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 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
-; SSE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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 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 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 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
 ;
 ; AVX-LABEL: 'loads'
@@ -328,23 +328,23 @@
 ; 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 3 for instruction: %13 = load <3 x double>, <3 x double>* 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 3 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 13 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 102 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
-; AVX-NEXT:  Cost Model: Found an estimated cost of 105 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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
 ;
 ; AVX512-LABEL: 'loads'
@@ -360,23 +360,23 @@
 ; 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 3 for instruction: %13 = load <3 x double>, <3 x double>* 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 3 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 14 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 102 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 4
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 106 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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 3 for instruction: %12 = load <3 x float>, <3 x float>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %13 = load <3 x double>, <3 x double>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %14 = load <3 x i32>, <3 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; SSE-NEXT:  Cost Model: Found an estimated cost of 98 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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 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 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 0 for instruction: ret i32 undef
 ;
 ; AVX-LABEL: 'loads_align'
@@ -466,23 +466,23 @@
 ; 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 3 for instruction: %13 = load <3 x double>, <3 x double>* 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 3 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 49 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 102 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; AVX-NEXT:  Cost Model: Found an estimated cost of 105 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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 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 0 for instruction: ret i32 undef
 ;
 ; AVX512-LABEL: 'loads_align'
@@ -498,23 +498,23 @@
 ; 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 3 for instruction: %13 = load <3 x double>, <3 x double>* 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 3 for instruction: %15 = load <3 x i64>, <3 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %16 = load <5 x i32>, <5 x i32>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %17 = load <5 x i64>, <5 x i64>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %18 = load <5 x i16>, <5 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %19 = load <6 x i16>, <6 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %20 = load <7 x i16>, <7 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %21 = load <11 x i16>, <11 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %22 = load <12 x i16>, <12 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %23 = load <13 x i16>, <13 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %24 = load <23 x i16>, <23 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 51 for instruction: %25 = load <24 x i16>, <24 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %26 = load <25 x i16>, <25 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %27 = load <47 x i16>, <47 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 102 for instruction: %28 = load <48 x i16>, <48 x i16>* undef, align 64
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 106 for instruction: %29 = load <49 x i16>, <49 x i16>* 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 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 0 for instruction: ret i32 undef
 ;
   load i8, i8* undef, align 64