[X86][CostModel] Bump the cost of vpermw/vpermt2b/vperm2w

[craig.topper]

Summary

vpermw is 2 uops. vpermt2b/vpermt2w are two shuffle uops and a port 015 uop. Weirdly vpermb is a single uop.

This patch bumps the cost to 2 for these operations. Maybe should go to 3 for the vpermt2*, but I've started conservative.

I've also removed a few entries that were now the same as earlier subtargets or that I didn't think we really did. Like I don't think we extend v32i8 to v32i16, shuffle, and then truncate.

[craig.topper]

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

1092

We would just use pshufb for v8i16.

[RKSimon]

LGTM

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

int X86TTIImpl::getShuffleCost(TTI::ShuffleKind Kind, VectorType *BaseTp,
 
   static const CostTblEntry AVX512VBMIShuffleTbl[] = {
       {TTI::SK_Reverse, MVT::v64i8, 1}, // vpermb
       {TTI::SK_Reverse, MVT::v32i8, 1}, // vpermb
 
       {TTI::SK_PermuteSingleSrc, MVT::v64i8, 1}, // vpermb
       {TTI::SK_PermuteSingleSrc, MVT::v32i8, 1}, // vpermb
 
-      {TTI::SK_PermuteTwoSrc, MVT::v64i8, 1}, // vpermt2b
-      {TTI::SK_PermuteTwoSrc, MVT::v32i8, 1}, // vpermt2b
-      {TTI::SK_PermuteTwoSrc, MVT::v16i8, 1}  // vpermt2b
+      {TTI::SK_PermuteTwoSrc, MVT::v64i8, 2}, // vpermt2b
+      {TTI::SK_PermuteTwoSrc, MVT::v32i8, 2}, // vpermt2b
+      {TTI::SK_PermuteTwoSrc, MVT::v16i8, 2}  // vpermt2b
   };
 
   if (ST->hasVBMI())
     if (const auto *Entry =
             CostTableLookup(AVX512VBMIShuffleTbl, Kind, LT.second))
       return LT.first * Entry->Cost;
 
   static const CostTblEntry AVX512BWShuffleTbl[] = {
       {TTI::SK_Broadcast, MVT::v32i16, 1}, // vpbroadcastw
       {TTI::SK_Broadcast, MVT::v64i8, 1},  // vpbroadcastb
 
-      {TTI::SK_Reverse, MVT::v32i16, 1}, // vpermw
-      {TTI::SK_Reverse, MVT::v16i16, 1}, // vpermw
+      {TTI::SK_Reverse, MVT::v32i16, 2}, // vpermw
+      {TTI::SK_Reverse, MVT::v16i16, 2}, // vpermw
       {TTI::SK_Reverse, MVT::v64i8, 2},  // pshufb + vshufi64x2
 
-      {TTI::SK_PermuteSingleSrc, MVT::v32i16, 1}, // vpermw
-      {TTI::SK_PermuteSingleSrc, MVT::v16i16, 1}, // vpermw
-      {TTI::SK_PermuteSingleSrc, MVT::v8i16, 1},  // vpermw
+      {TTI::SK_PermuteSingleSrc, MVT::v32i16, 2}, // vpermw
+      {TTI::SK_PermuteSingleSrc, MVT::v16i16, 2}, // vpermw
       {TTI::SK_PermuteSingleSrc, MVT::v64i8, 8},  // extend to v32i16
-      {TTI::SK_PermuteSingleSrc, MVT::v32i8, 3},  // vpermw + zext/trunc
 
-      {TTI::SK_PermuteTwoSrc, MVT::v32i16, 1}, // vpermt2w
-      {TTI::SK_PermuteTwoSrc, MVT::v16i16, 1}, // vpermt2w
-      {TTI::SK_PermuteTwoSrc, MVT::v8i16, 1},  // vpermt2w
-      {TTI::SK_PermuteTwoSrc, MVT::v32i8, 3},  // zext + vpermt2w + trunc
+      {TTI::SK_PermuteTwoSrc, MVT::v32i16, 2}, // vpermt2w
+      {TTI::SK_PermuteTwoSrc, MVT::v16i16, 2}, // vpermt2w
+      {TTI::SK_PermuteTwoSrc, MVT::v8i16, 2},  // vpermt2w
       {TTI::SK_PermuteTwoSrc, MVT::v64i8, 19}, // 6 * v32i8 + 1
-      {TTI::SK_PermuteTwoSrc, MVT::v16i8, 3}   // zext + vpermt2w + trunc
   };
 
   if (ST->hasBWI())
     if (const auto *Entry =
             CostTableLookup(AVX512BWShuffleTbl, Kind, LT.second))
       return LT.first * Entry->Cost;
 
   static const CostTblEntry AVX512ShuffleTbl[] = {

llvm/test/Analysis/CostModel/X86/shuffle-insert_subvector.ll

 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src32_512 = shufflevector <2 x i16> %src32, <2 x i16> undef, <32 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src64_128 = shufflevector <4 x i16> %src64, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src64_256 = shufflevector <4 x i16> %src64, <4 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src64_512 = shufflevector <4 x i16> %src64, <4 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src128_256 = shufflevector <8 x i16> %src128, <8 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src128_512 = shufflevector <8 x i16> %src128, <8 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Unknown cost for instruction: %src256_512 = shufflevector <16 x i16> %src256, <16 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> %src32_64, <4 x i32> <i32 4, i32 5, 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> %src32_64, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> %src32_64, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, 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> %src32_128, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, 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> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, 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: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, 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: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, 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: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, 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: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, 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 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, 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 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, 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 2 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, 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> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, 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: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, 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: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, 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 2 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, 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> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, 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: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VMBI-LABEL: 'test_vXi16'
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src32_64 = shufflevector <2 x i16> %src32, <2 x i16> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src32_128 = shufflevector <2 x i16> %src32, <2 x i16> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src32_256 = shufflevector <2 x i16> %src32, <2 x i16> undef, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src32_512 = shufflevector <2 x i16> %src32, <2 x i16> undef, <32 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_128 = shufflevector <4 x i16> %src64, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_256 = shufflevector <4 x i16> %src64, <4 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_512 = shufflevector <4 x i16> %src64, <4 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src128_256 = shufflevector <8 x i16> %src128, <8 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src128_512 = shufflevector <8 x i16> %src128, <8 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src256_512 = shufflevector <16 x i16> %src256, <16 x i16> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> %src32_64, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> %src32_64, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_23 = shufflevector <4 x i16> %src64, <4 x i16> %src32_64, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_45 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_67 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_4567 = shufflevector <8 x i16> %src128, <8 x i16> %src32_128, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_01 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_23 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_45 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_67 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_89 = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_AB = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CD = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_EF = shufflevector <16 x i16> %src256, <16 x i16> %src64_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_0123 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_4567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_89AB = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_CDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_01234567 = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256_89ABCDEF = shufflevector <16 x i16> %src256, <16 x i16> %src128_256, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Unknown cost for instruction: %src32_64 = shufflevector <2 x i16> %src32, <2 x i16> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
 ; BTVER2-NEXT:  Cost Model: Unknown cost for instruction: %src32_128 = shufflevector <2 x i16> %src32, <2 x i16> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; BTVER2-NEXT:  Cost Model: Unknown cost for instruction: %src32_256 = shufflevector <2 x i16> %src32, <2 x i16> undef, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; BTVER2-NEXT:  Cost Model: Unknown cost for instruction: %src32_512 = shufflevector <2 x i16> %src32, <2 x i16> undef, <32 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; BTVER2-NEXT:  Cost Model: Unknown cost for instruction: %src64_128 = shufflevector <4 x i16> %src64, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>

 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src32_512 = shufflevector <4 x i8> %src32, <4 x i8> undef, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_128 = shufflevector <8 x i8> %src64, <8 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_256 = shufflevector <8 x i8> %src64, <8 x i8> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src64_512 = shufflevector <8 x i8> %src64, <8 x i8> undef, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src128_256 = shufflevector <16 x i8> %src128, <16 x i8> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src128_512 = shufflevector <16 x i8> %src128, <16 x i8> undef, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Unknown cost for instruction: %src256_512 = shufflevector <32 x i8> %src256, <32 x i8> undef, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32_01 = shufflevector <4 x i8> %src32, <4 x i8> %src16_32, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32_23 = shufflevector <4 x i8> %src32, <4 x i8> %src16_32, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32_23 = shufflevector <4 x i8> %src32, <4 x i8> %src16_32, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_01 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_23 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_45 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_67 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_23 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_45 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_67 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_0123 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64_4567 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64_4567 = shufflevector <8 x i8> %src64, <8 x i8> %src32_64, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_01 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 16, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_23 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_45 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_67 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_89 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_AB = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_CD = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_EF = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_23 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_45 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_67 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_89 = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_AB = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 16, i32 17, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_CD = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_EF = shufflevector <16 x i8> %src128, <16 x i8> %src16_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_0123 = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_4567 = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_89AB = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_CDEF = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_4567 = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_89AB = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_CDEF = shufflevector <16 x i8> %src128, <16 x i8> %src32_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_01234567 = shufflevector <16 x i8> %src128, <16 x i8> %src64_128, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128_89ABCDEF = shufflevector <16 x i8> %src128, <16 x i8> %src64_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
+; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128_89ABCDEF = shufflevector <16 x i8> %src128, <16 x i8> %src64_128, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
 ; AVX512VMBI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %src16_32   = shufflevector <2 x i8> %src16,   <2 x i8> undef,   <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
   %src16_64   = shufflevector <2 x i8> %src16,   <2 x i8> undef,   <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %src16_128  = shufflevector <2 x i8> %src16,   <2 x i8> undef,  <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %src16_256  = shufflevector <2 x i8> %src16,   <2 x i8> undef,  <32 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %src16_512  = shufflevector <2 x i8> %src16,   <2 x i8> undef,  <64 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   %src32_64   = shufflevector <4 x i8> %src32,   <4 x i8> undef,   <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>

llvm/test/Analysis/CostModel/X86/shuffle-reverse.ll

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi16'
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>

llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi16'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 1>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 2, i32 2, i32 1, i32 1>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 6, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 13, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 13, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi16'
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 1>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 2, i32 2, i32 1, i32 1>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 6, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 13, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 13, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> <i32 1, i32 1>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> <i32 2, i32 2, i32 1, i32 1>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> <i32 7, i32 6, i32 6, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 13, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> <i32 31, i32 30, i32 20, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> undef, <2 x i32> <i32 1, i32 1>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> undef, <4 x i32> <i32 3, i32 3, i32 1, i32 1>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> <i32 7, i32 7, i32 5, i32 5, i32 3, i32 3, i32 1, i32 1>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> <i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> <i32 63, i32 62, i32 61, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi8'
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> undef, <2 x i32> <i32 1, i32 1>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> undef, <4 x i32> <i32 3, i32 3, i32 1, i32 1>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> <i32 7, i32 7, i32 5, i32 5, i32 3, i32 3, i32 1, i32 1>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>

llvm/test/Analysis/CostModel/X86/shuffle-transpose.ll

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi16'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi16'
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %a32, <2 x i16> %b32, <2 x i32> <i32 0, i32 2>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %a64, <4 x i16> %b64, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %a128, <8 x i16> %b128, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %a256, <16 x i16> %b256, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %a512, <32 x i16> %b512, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16 = shufflevector <2 x i8> %a16, <2 x i8> %b16, <2 x i32> <i32 0, i32 2>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi8'
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = shufflevector <2 x i8> %a16, <2 x i8> %b16, <2 x i32> <i32 0, i32 2>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16 = shufflevector <2 x i8> %a16, <2 x i8> %b16, <2 x i32> <i32 0, i32 2>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <64 x i8> %a512, <64 x i8> %b512, <64 x i32> <i32 0, i32 64, i32 2, i32 66, i32 4, i32 68, i32 6, i32 70, i32 8, i32 72, i32 10, i32 74, i32 12, i32 76, i32 14, i32 78, i32 16, i32 80, i32 18, i32 82, i32 20, i32 84, i32 22, i32 86, i32 24, i32 88, i32 26, i32 90, i32 28, i32 92, i32 30, i32 94, i32 32, i32 96, i32 34, i32 98, i32 36, i32 100, i32 38, i32 102, i32 40, i32 104, i32 42, i32 106, i32 44, i32 108, i32 46, i32 110, i32 48, i32 112, i32 50, i32 114, i32 52, i32 116, i32 54, i32 118, i32 56, i32 120, i32 58, i32 122, i32 60, i32 124, i32 62, i32 126>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi8'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16 = shufflevector <2 x i8> %a16, <2 x i8> %b16, <2 x i32> <i32 0, i32 2>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %a32, <4 x i8> %b32, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %a64, <8 x i8> %b64, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %a128, <16 x i8> %b128, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %a256, <32 x i8> %b256, <32 x i32> <i32 0, i32 32, i32 2, i32 34, i32 4, i32 36, i32 6, i32 38, i32 8, i32 40, i32 10, i32 42, i32 12, i32 44, i32 14, i32 46, i32 16, i32 48, i32 18, i32 50, i32 20, i32 52, i32 22, i32 54, i32 24, i32 56, i32 26, i32 58, i32 28, i32 60, i32 30, i32 62>

llvm/test/Analysis/CostModel/X86/shuffle-two-src.ll

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 252 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> %src1024_1, <64 x i32> <i32 63, i32 62, i32 71, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 66, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi16'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> %src32_1, <2 x i32> <i32 3, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> %src1024_1, <64 x i32> <i32 63, i32 62, i32 71, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 66, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> %src32_1, <2 x i32> <i32 3, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> %src1024_1, <64 x i32> <i32 63, i32 62, i32 71, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 66, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi16'
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> %src32_1, <2 x i32> <i32 3, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> %src1024_1, <64 x i32> <i32 63, i32 62, i32 71, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 66, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> %src32_1, <2 x i32> <i32 3, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> %src1024_1, <64 x i32> <i32 63, i32 62, i32 71, i32 60, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 66, i32 2, i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi16'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> %src32_1, <2 x i32> <i32 3, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> %src64_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> %src128_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> %src256_1, <16 x i32> <i32 15, i32 14, i32 13, i32 20, i32 21, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> %src512_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 38, i32 11, i32 11, i32 9, i32 8, i32 7, i32 11, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>

 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> %src512_1, <64 x i32> <i32 63, i32 100, i32 61, i32 96, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512BW-LABEL: 'test_vXi8'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> %src16_1, <2 x i32> <i32 3, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> %src32_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> %src64_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> %src128_1, <16 x i32> <i32 29, i32 14, i32 28, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> %src256_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> %src256_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> %src512_1, <64 x i32> <i32 63, i32 100, i32 61, i32 96, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; AVX512VBMI-LABEL: 'test_vXi8'
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> %src16_1, <2 x i32> <i32 3, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> %src32_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> %src64_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> %src128_1, <16 x i32> <i32 29, i32 14, i32 28, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> %src256_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
-; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> %src512_1, <64 x i32> <i32 63, i32 100, i32 61, i32 96, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> %src16_1, <2 x i32> <i32 3, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> %src32_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> %src64_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> %src128_1, <16 x i32> <i32 29, i32 14, i32 28, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> %src256_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>
+; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> %src512_1, <64 x i32> <i32 63, i32 100, i32 61, i32 96, i32 59, i32 58, i32 57, i32 56, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 47, i32 46, i32 45, i32 44, i32 43, i32 42, i32 41, i32 40, i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 20, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; AVX512VBMI-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; BTVER2-LABEL: 'test_vXi8'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16 = shufflevector <2 x i8> %src16, <2 x i8> %src16_1, <2 x i32> <i32 3, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> %src32_1, <4 x i32> <i32 3, i32 6, i32 1, i32 5>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> %src64_1, <8 x i32> <i32 7, i32 6, i32 6, i32 8, i32 9, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> %src128_1, <16 x i32> <i32 29, i32 14, i32 28, i32 12, i32 11, i32 10, i32 11, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> %src256_1, <32 x i32> <i32 31, i32 30, i32 45, i32 28, i32 27, i32 26, i32 25, i32 24, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 8, i32 8, i32 7, i32 6, i32 8, i32 4, i32 3, i32 2, i32 1, i32 0>

llvm/test/Analysis/CostModel/X86/strided-load-i16.ll

 ; REQUIRES: asserts
 ; RUN: opt -loop-vectorize -S -mattr=avx512bw --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @A = global [10240 x i16] zeroinitializer, align 16
 @B = global [10240 x i16] zeroinitializer, align 16
 
 ; Function Attrs: nounwind uwtable
 define void @load_i16_stride2() {
 ;CHECK-LABEL: load_i16_stride2
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 16 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 2 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 32 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = shl nsw i64 %indvars.iv, 1
   %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
   %1 = load i16, i16* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
   store i16 %1, i16* %arrayidx2, align 2
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond = icmp eq i64 %indvars.iv.next, 1024
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i16_stride3() {
 ;CHECK-LABEL: load_i16_stride3
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 5 for VF 32 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = mul nsw i64 %indvars.iv, 3
   %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
   %1 = load i16, i16* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
   store i16 %1, i16* %arrayidx2, align 2
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond = icmp eq i64 %indvars.iv.next, 1024
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i16_stride4() {
 ;CHECK-LABEL: load_i16_stride4
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 2 for VF 16 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 5 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 8 for VF 32 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = shl nsw i64 %indvars.iv, 2
   %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
   %1 = load i16, i16* %arrayidx, align 4
   %arrayidx2 = getelementptr inbounds [10240 x i16], [10240 x i16]* @B, i64 0, i64 %indvars.iv
   store i16 %1, i16* %arrayidx2, align 2
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
   %exitcond = icmp eq i64 %indvars.iv.next, 1024
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i16_stride5() {
 ;CHECK-LABEL: load_i16_stride5
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 2 for VF 8 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 6 for VF 32 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 2 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 2 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 5 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 10 for VF 32 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = mul nsw i64 %indvars.iv, 5
   %arrayidx = getelementptr inbounds [10240 x i16], [10240 x i16]* @A, i64 0, i64 %0
   %1 = load i16, i16* %arrayidx, align 4

llvm/test/Analysis/CostModel/X86/strided-load-i8.ll

 ; REQUIRES: asserts
 ; RUN: opt -loop-vectorize -S -mattr=avx512bw --debug-only=loop-vectorize < %s 2>&1| FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @A = global [10240 x i8] zeroinitializer, align 16
 @B = global [10240 x i8] zeroinitializer, align 16
 
 ; Function Attrs: nounwind uwtable
 define void @load_i8_stride2() {
 ;CHECK-LABEL: load_i8_stride2
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 8 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 16 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 4 for VF 16 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 8 for VF 32 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 20 for VF 64 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
   %0 = shl nsw i64 %indvars.iv, 1
for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i8_stride3() {
 ;CHECK-LABEL: load_i8_stride3
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 4 for VF 8 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 13 for VF 16 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 16 for VF 32 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 25 for VF 64 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i8_stride4() {
 ;CHECK-LABEL: load_i8_stride4
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 4 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 8 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 4 for VF 8 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 8 for VF 16 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 20 for VF 32 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 59 for VF 64 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]

 for.end:                                          ; preds = %for.body
   ret void
 }
 
 define void @load_i8_stride5() {
 ;CHECK-LABEL: load_i8_stride5
 ;CHECK: Found an estimated cost of 1 for VF 1 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 1 for VF 2 For instruction:   %1 = load
-;CHECK: Found an estimated cost of 3 for VF 4 For instruction:   %1 = load
+;CHECK: Found an estimated cost of 4 for VF 4 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 8 for VF 8 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 20 for VF 16 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 39 for VF 32 For instruction:   %1 = load
 ;CHECK: Found an estimated cost of 78 for VF 64 For instruction:   %1 = load
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %for.body, %entry