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
@@ -911,6 +911,39 @@
       int NumSubElts = SubLT.second.getVectorNumElements();
       if ((Index % NumSubElts) == 0 && (NumElts % NumSubElts) == 0)
         return SubLT.first;
+      // Handle some cases for widening legalization. For now we only handle
+      // cases where the original subvector was naturally aligned and evenly
+      // fit in its legalized subvector type.
+      // FIXME: Remove some of the alignment restrictions.
+      // FIXME: We can use permq for 64-bit or larger extracts from 256-bit
+      // vectors.
+      int OrigSubElts = SubTp->getVectorNumElements();
+      if (NumSubElts > OrigSubElts &&
+          (Index % OrigSubElts) == 0 && (NumSubElts % OrigSubElts) == 0 &&
+          LT.second.getVectorElementType() ==
+            SubLT.second.getVectorElementType() &&
+          LT.second.getVectorElementType().getSizeInBits() ==
+            Tp->getVectorElementType()->getPrimitiveSizeInBits()) {
+        assert(NumElts >= NumSubElts && NumElts > OrigSubElts &&
+               "Unexpected number of elements!");
+        Type *VecTy = VectorType::get(Tp->getVectorElementType(),
+                                      LT.second.getVectorNumElements());
+        Type *SubTy = VectorType::get(Tp->getVectorElementType(),
+                                      SubLT.second.getVectorNumElements());
+        int ExtractIndex = alignDown((Index % NumElts), NumSubElts);
+        int ExtractCost = getShuffleCost(TTI::SK_ExtractSubvector, VecTy,
+                                         ExtractIndex, SubTy);
+
+        // If the original size is 32-bits or more, we can use pshufd. Otherwise
+        // if we have SSSE3 we can use pshufb.
+        if (SubTp->getPrimitiveSizeInBits() >= 32 || ST->hasSSSE3())
+          return ExtractCost + 1; // pshufd or pshufb
+
+        assert(SubTp->getPrimitiveSizeInBits() == 16 &&
+               "Unexpected vector size");
+
+        return ExtractCost + 2; // worst case pshufhw + pshufd
+      }
     }
   }
 
diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
--- a/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
+++ b/llvm/test/Analysis/CostModel/X86/shuffle-extract_subvector.ll
@@ -141,21 +141,21 @@
 define void @test_vXi32(<4 x i32> %src128, <8 x i32> %src256, <16 x i32> %src512) {
 ; SSE-LABEL: 'test_vXi32'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 8, i32 9>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_CD = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 12, i32 13>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_4567 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -166,21 +166,21 @@
 ;
 ; AVX-LABEL: 'test_vXi32'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 8, i32 9>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_CD = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 12, i32 13>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_4567 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -191,21 +191,21 @@
 ;
 ; AVX512-LABEL: 'test_vXi32'
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 4, i32 5>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 0, i32 1>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 4, i32 5>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 8, i32 9>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_CD = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 12, i32 13>
-; AVX512-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_4567 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_89AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -216,21 +216,21 @@
 ;
 ; BTVER2-LABEL: 'test_vXi32'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <8 x i32> %src256, <8 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <8 x i32> %src256, <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_01 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_23 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_45 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_67 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89 = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 8, i32 9>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 10, i32 11>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_CD = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 12, i32 13>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_EF = shufflevector <16 x i32> %src512, <16 x i32> undef, <2 x i32> <i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_4567 = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
@@ -267,55 +267,55 @@
 define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256, <32 x i16> %src512) {
 ; SSE-LABEL: 'test_vXi16'
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 8, i32 9>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_2345 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_6789 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 0, i32 1>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 8, i32 9>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 16, i32 17>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_18_19 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 24, i32 25>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_18_19_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
@@ -326,55 +326,55 @@
 ;
 ; AVX-LABEL: 'test_vXi16'
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_2345 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_6789 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 16, i32 17>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 24, i32 25>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
@@ -385,55 +385,55 @@
 ;
 ; AVX512F-LABEL: 'test_vXi16'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_2345 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_6789 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 16, i32 17>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 24, i32 25>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
+; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
@@ -444,55 +444,55 @@
 ;
 ; AVX512BW-LABEL: 'test_vXi16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_2345 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_6789 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 0, i32 1>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 8, i32 9>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_10_11 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 16, i32 17>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 24, i32 25>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_10_11_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
@@ -503,55 +503,55 @@
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 4, i32 5>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 4, i32 5>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 8, i32 9>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 10, i32 11>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 12, i32 13>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_2345 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_6789 = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 0, i32 1>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 2, i32 3>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 4, i32 5>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 8, i32 9>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 10, i32 11>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 12, i32 13>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 16, i32 17>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 18, i32 19>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 20, i32 21>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 22, i32 23>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19 = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 24, i32 25>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 26, i32 27>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 28, i32 29>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <2 x i32> <i32 30, i32 31>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_02_03_04_05 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_06_07_08_09 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 6, i32 7, i32 8, i32 9>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 16, i32 17, i32 18, i32 19>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 20, i32 21, i32 22, i32 23>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_18_19_1A_1B = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 24, i32 25, i32 26, i32 27>
-; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
+; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <4 x i32> <i32 28, i32 29, i32 30, i32 31>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>