diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index add82dc80c429..fa7c7c57be257 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -376,6 +376,104 @@ static VectorType *getVRGatherIndexType(MVT DataVT, const RISCVSubtarget &ST,
   return cast<VectorType>(EVT(IndexVT).getTypeForEVT(C));
 }
 
+/// Try to perform better estimation of the permutation.
+/// 1. Split the source/destination vectors into real registers.
+/// 2. Do the mask analysis to identify which real registers are
+/// permuted. If more than 1 source registers are used for the
+/// destination register building, the cost for this destination register
+/// is (Number_of_source_register - 1) * Cost_PermuteTwoSrc. If only one
+/// source register is used, build mask and calculate the cost as a cost
+/// of PermuteSingleSrc.
+/// Also, for the single register permute we try to identify if the
+/// destination register is just a copy of the source register or the
+/// copy of the previous destination register (the cost is
+/// TTI::TCC_Basic). If the source register is just reused, the cost for
+/// this operation is 0.
+static InstructionCost
+costShuffleViaVRegSplitting(RISCVTTIImpl &TTI, MVT LegalVT,
+                            std::optional<unsigned> VLen, VectorType *Tp,
+                            ArrayRef<int> Mask, TTI::TargetCostKind CostKind) {
+  InstructionCost NumOfDests = InstructionCost::getInvalid();
+  if (VLen && LegalVT.isFixedLengthVector() && !Mask.empty()) {
+    MVT ElemVT = LegalVT.getVectorElementType();
+    unsigned ElemsPerVReg = *VLen / ElemVT.getFixedSizeInBits();
+    LegalVT = TTI.getTypeLegalizationCost(
+                     FixedVectorType::get(Tp->getElementType(), ElemsPerVReg))
+                  .second;
+    // Number of destination vectors after legalization:
+    NumOfDests = divideCeil(Mask.size(), LegalVT.getVectorNumElements());
+  }
+  if (!NumOfDests.isValid() || NumOfDests <= 1 ||
+      !LegalVT.isFixedLengthVector() ||
+      LegalVT.getVectorElementType().getSizeInBits() !=
+          Tp->getElementType()->getPrimitiveSizeInBits() ||
+      LegalVT.getVectorNumElements() >= Tp->getElementCount().getFixedValue())
+    return InstructionCost::getInvalid();
+
+  unsigned VecTySize = TTI.getDataLayout().getTypeStoreSize(Tp);
+  unsigned LegalVTSize = LegalVT.getStoreSize();
+  // Number of source vectors after legalization:
+  unsigned NumOfSrcs = divideCeil(VecTySize, LegalVTSize);
+
+  auto *SingleOpTy = FixedVectorType::get(Tp->getElementType(),
+                                          LegalVT.getVectorNumElements());
+
+  unsigned E = *NumOfDests.getValue();
+  unsigned NormalizedVF =
+      LegalVT.getVectorNumElements() * std::max(NumOfSrcs, E);
+  unsigned NumOfSrcRegs = NormalizedVF / LegalVT.getVectorNumElements();
+  unsigned NumOfDestRegs = NormalizedVF / LegalVT.getVectorNumElements();
+  SmallVector<int> NormalizedMask(NormalizedVF, PoisonMaskElem);
+  assert(NormalizedVF >= Mask.size() &&
+         "Normalized mask expected to be not shorter than original mask.");
+  copy(Mask, NormalizedMask.begin());
+  InstructionCost Cost = 0;
+  SmallBitVector ExtractedRegs(2 * NumOfSrcRegs);
+  int NumShuffles = 0;
+  processShuffleMasks(
+      NormalizedMask, NumOfSrcRegs, NumOfDestRegs, NumOfDestRegs, []() {},
+      [&](ArrayRef<int> RegMask, unsigned SrcReg, unsigned DestReg) {
+        if (ExtractedRegs.test(SrcReg)) {
+          Cost += TTI.getShuffleCost(TTI::SK_ExtractSubvector, Tp, {}, CostKind,
+                                     (SrcReg % NumOfSrcRegs) *
+                                         SingleOpTy->getNumElements(),
+                                     SingleOpTy);
+          ExtractedRegs.set(SrcReg);
+        }
+        if (!ShuffleVectorInst::isIdentityMask(RegMask, RegMask.size())) {
+          ++NumShuffles;
+          Cost += TTI.getShuffleCost(TTI::SK_PermuteSingleSrc, SingleOpTy,
+                                     RegMask, CostKind, 0, nullptr);
+          return;
+        }
+      },
+      [&](ArrayRef<int> RegMask, unsigned Idx1, unsigned Idx2, bool NewReg) {
+        if (ExtractedRegs.test(Idx1)) {
+          Cost += TTI.getShuffleCost(
+              TTI::SK_ExtractSubvector, Tp, {}, CostKind,
+              (Idx1 % NumOfSrcRegs) * SingleOpTy->getNumElements(), SingleOpTy);
+          ExtractedRegs.set(Idx1);
+        }
+        if (ExtractedRegs.test(Idx2)) {
+          Cost += TTI.getShuffleCost(
+              TTI::SK_ExtractSubvector, Tp, {}, CostKind,
+              (Idx2 % NumOfSrcRegs) * SingleOpTy->getNumElements(), SingleOpTy);
+          ExtractedRegs.set(Idx2);
+        }
+        Cost += TTI.getShuffleCost(TTI::SK_PermuteTwoSrc, SingleOpTy, RegMask,
+                                   CostKind, 0, nullptr);
+        NumShuffles += 2;
+      });
+  // Note: check that we do not emit too many shuffles here to prevent code
+  // size explosion.
+  // TODO: investigate, if it can be improved by extra analysis of the masks
+  // to check if the code is more profitable.
+  if ((NumOfDestRegs > 2 && NumShuffles <= static_cast<int>(NumOfDestRegs)) ||
+      (NumOfDestRegs <= 2 && NumShuffles < 4))
+    return Cost;
+  return InstructionCost::getInvalid();
+}
+
 InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
                                              VectorType *Tp, ArrayRef<int> Mask,
                                              TTI::TargetCostKind CostKind,
@@ -389,7 +487,11 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
   // First, handle cases where having a fixed length vector enables us to
   // give a more accurate cost than falling back to generic scalable codegen.
   // TODO: Each of these cases hints at a modeling gap around scalable vectors.
-  if (isa<FixedVectorType>(Tp)) {
+  if (ST->hasVInstructions() && isa<FixedVectorType>(Tp)) {
+    InstructionCost VRegSplittingCost = costShuffleViaVRegSplitting(
+        *this, LT.second, ST->getRealVLen(), Tp, Mask, CostKind);
+    if (VRegSplittingCost.isValid())
+      return VRegSplittingCost;
     switch (Kind) {
     default:
       break;
diff --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-exact-vlen.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-exact-vlen.ll
index cada8ab240cc7..c951184a31731 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-exact-vlen.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-exact-vlen.ll
@@ -19,12 +19,12 @@ define <64 x i32> @interleave_v32i32(<32 x i32> %x, <32 x i32> %y) vscale_range(
 
 define void @extract(<64 x i32> %v, ptr %out) vscale_range(2,2) vscale_range(2,2) {
 ; CHECK-LABEL: 'extract'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %shuffle.i5 = shufflevector <64 x i32> %v, <64 x i32> poison, <64 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %shuffle.i5 = shufflevector <64 x i32> %v, <64 x i32> poison, <64 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <64 x i32> %shuffle.i5, ptr %out, align 4
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-SIZE-LABEL: 'extract'
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %shuffle.i5 = shufflevector <64 x i32> %v, <64 x i32> poison, <64 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %shuffle.i5 = shufflevector <64 x i32> %v, <64 x i32> poison, <64 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <64 x i32> %shuffle.i5, ptr %out, align 4
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
@@ -58,7 +58,7 @@ define void @shuffle() vscale_range(2,2) {
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v11 = shufflevector <2 x i16> poison, <2 x i16> poison, <2 x i32> <i32 1, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v12 = shufflevector <4 x i16> poison, <4 x i16> poison, <4 x i32> <i32 1, i32 3, i32 2, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v13 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v10b = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v10b = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v14 = shufflevector <2 x i32> poison, <2 x i32> poison, <2 x i32> <i32 1, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v15 = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 1, i32 3, i32 2, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v16 = shufflevector <2 x float> poison, <2 x float> poison, <2 x i32> <i32 1, i32 0>
@@ -94,16 +94,16 @@ define void @concat() vscale_range(2,2) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = shufflevector <8 x i8> poison, <8 x i8> poison, <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 14, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = shufflevector <2 x i16> poison, <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = shufflevector <4 x i16> poison, <4 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = shufflevector <8 x i16> poison, <8 x i16> poison, <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 14, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i16 = shufflevector <8 x i16> poison, <8 x i16> poison, <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 14, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = shufflevector <2 x i32> poison, <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = shufflevector <4 x i32> poison, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = shufflevector <2 x i64> poison, <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v8i32 = shufflevector <4 x i32> poison, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v4i64 = shufflevector <2 x i64> poison, <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %v4f16 = shufflevector <2 x half> poison, <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %v8f16 = shufflevector <4 x half> poison, <4 x half> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %v16f16 = shufflevector <8 x half> poison, <8 x half> poison, <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 14, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = shufflevector <2 x float> poison, <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32 = shufflevector <4 x float> poison, <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64 = shufflevector <2 x double> poison, <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v8f32 = shufflevector <4 x float> poison, <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v4f64 = shufflevector <2 x double> poison, <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-SIZE-LABEL: 'concat'
@@ -112,16 +112,16 @@ define void @concat() vscale_range(2,2) {
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i8 = shufflevector <8 x i8> poison, <8 x i8> poison, <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 14, i32 15>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = shufflevector <2 x i16> poison, <2 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = shufflevector <4 x i16> poison, <4 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16 = shufflevector <8 x i16> poison, <8 x i16> poison, <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 14, i32 15>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i16 = shufflevector <8 x i16> poison, <8 x i16> poison, <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 14, i32 15>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = shufflevector <2 x i32> poison, <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32 = shufflevector <4 x i32> poison, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i64 = shufflevector <2 x i64> poison, <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v8i32 = shufflevector <4 x i32> poison, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v4i64 = shufflevector <2 x i64> poison, <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-SIZE-NEXT:  Cost Model: Invalid cost for instruction: %v4f16 = shufflevector <2 x half> poison, <2 x half> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-SIZE-NEXT:  Cost Model: Invalid cost for instruction: %v8f16 = shufflevector <4 x half> poison, <4 x half> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Invalid cost for instruction: %v16f16 = shufflevector <8 x half> poison, <8 x half> poison, <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 14, i32 15>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f32 = shufflevector <2 x float> poison, <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8f32 = shufflevector <4 x float> poison, <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4f64 = shufflevector <2 x double> poison, <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v8f32 = shufflevector <4 x float> poison, <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v4f64 = shufflevector <2 x double> poison, <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v4i8 = shufflevector <2 x i8> poison, <2 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
@@ -170,23 +170,23 @@ define void @insert_subvec() vscale_range(2,2) {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_2 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_3 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_05 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i16_4_0 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_4_1 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_4_2 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_4_3 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16_4_05 = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_0 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_1 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_2 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_3 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_05 = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2_0 = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2_1 = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8i32_2_0 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2_1 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2_2 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2_3 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32_2_05 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v16i32_4_0 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_4_1 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_4_2 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_4_3 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16i32_4_05 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_0 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_1 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_2 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_3 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_05 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_0 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_1 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_2 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_3 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_4_05 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-SIZE-LABEL: 'insert_subvec'
@@ -209,23 +209,23 @@ define void @insert_subvec() vscale_range(2,2) {
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_2 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_3 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16_2_05 = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v16i16_4_0 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_0 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_1 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_2 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_3 = shufflevector <16 x i16> poison, <16 x i16> poison, <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>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i16_4_05 = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v4i32_2_0 = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32_2_1 = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v8i32_2_0 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_0 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_1 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_2 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_3 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i32_2_05 = shufflevector <8 x i32> poison, <8 x i32> poison, <8 x i32> <i32 0, i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v16i32_4_0 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i32_4_1 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i32_4_2 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i32_4_3 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16i32_4_05 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_0 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_1 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_2 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v16i32_4_3 = shufflevector <16 x i32> poison, <16 x i32> poison, <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>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16i32_4_05 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 18, i32 19, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v4i8_2_0 = shufflevector <4 x i8> poison, <4 x i8> poison, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
@@ -732,64 +732,44 @@ define void @shuffle2() vscale_range(2,2) {
 
 
 define void @multipart() vscale_range(2,2) {
-; RV32-LABEL: 'multipart'
-; RV32-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v16a = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16c = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %v16d = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %v32a4 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32idrev = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many2 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 1, i32 4, i32 8, i32 12, i32 17, i32 20, i32 24, i32 28, i32 2, i32 6, i32 11, i32 14, i32 18, i32 22, i32 27, i32 30>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v323 = shufflevector <3 x i32> poison, <3 x i32> poison, <3 x i32> <i32 2, i32 3, i32 0>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64a = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> <i32 1, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64b = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> zeroinitializer
-; RV32-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v64ab = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %v64d = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 4, i32 4>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64a = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> <i32 1, i32 1>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64b = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> zeroinitializer
-; RV32-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %f64ab = shufflevector <4 x double> poison, <4 x double> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; RV64-LABEL: 'multipart'
-; RV64-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v16a = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v16c = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %v16d = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %v32a4 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32idrev = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many2 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 1, i32 4, i32 8, i32 12, i32 17, i32 20, i32 24, i32 28, i32 2, i32 6, i32 11, i32 14, i32 18, i32 22, i32 27, i32 30>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v323 = shufflevector <3 x i32> poison, <3 x i32> poison, <3 x i32> <i32 2, i32 3, i32 0>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64a = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> <i32 1, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64b = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> zeroinitializer
-; RV64-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v64ab = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %v64d = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 4, i32 4>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64a = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> <i32 1, i32 1>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64b = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> zeroinitializer
-; RV64-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %f64ab = shufflevector <4 x double> poison, <4 x double> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; CHECK-LABEL: 'multipart'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v16a = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16c = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16d = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v32a4 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v32idrev = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %v32many2 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 1, i32 4, i32 8, i32 12, i32 17, i32 20, i32 24, i32 28, i32 2, i32 6, i32 11, i32 14, i32 18, i32 22, i32 27, i32 30>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v323 = shufflevector <3 x i32> poison, <3 x i32> poison, <3 x i32> <i32 2, i32 3, i32 0>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64a = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> <i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64b = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v64ab = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v64d = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 4, i32 4>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64a = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> <i32 1, i32 1>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64b = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64ab = shufflevector <4 x double> poison, <4 x double> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; CHECK-SIZE-LABEL: 'multipart'
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v16a = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v16c = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v16d = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16c = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %v16d = shufflevector <16 x i16> poison, <16 x i16> poison, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a = shufflevector <4 x i32> poison, <4 x i32> poison, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v32a4 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v32idrev = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v32a4 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v32idrev = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 15, i32 14, i32 13, i32 12, i32 16, i32 17, i32 18, i32 19, i32 31, i32 30, i32 29, i32 28>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v32many = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v32many2 = shufflevector <16 x i32> poison, <16 x i32> poison, <16 x i32> <i32 1, i32 4, i32 8, i32 12, i32 17, i32 20, i32 24, i32 28, i32 2, i32 6, i32 11, i32 14, i32 18, i32 22, i32 27, i32 30>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v323 = shufflevector <3 x i32> poison, <3 x i32> poison, <3 x i32> <i32 2, i32 3, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64a = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> <i32 1, i32 1>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v64b = shufflevector <2 x i64> poison, <2 x i64> poison, <2 x i32> zeroinitializer
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v64ab = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v64d = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 4, i32 4>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v64ab = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v64d = shufflevector <4 x i64> poison, <4 x i64> poison, <4 x i32> <i32 1, i32 1, i32 4, i32 4>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64a = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> <i32 1, i32 1>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %f64b = shufflevector <2 x double> poison, <2 x double> poison, <2 x i32> zeroinitializer
-; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %f64ab = shufflevector <4 x double> poison, <4 x double> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
+; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64ab = shufflevector <4 x double> poison, <4 x double> poison, <4 x i32> <i32 1, i32 1, i32 0, i32 0>
 ; CHECK-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v16a = shufflevector <8 x i16> poison, <8 x i16> poison, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
diff --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-extract_subvector.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-extract_subvector.ll
index d65668fa30ca6..e8dd30345cc76 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-extract_subvector.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-extract_subvector.ll
@@ -30,9 +30,9 @@ define void @test_vXf64(<4 x double> %src256, <8 x double> %src512) {
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_45 = shufflevector <8 x double> %src512, <8 x double> undef, <2 x i32> <i32 4, i32 5>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_67 = shufflevector <8 x double> %src512, <8 x double> undef, <2 x i32> <i32 6, i32 7>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_2345 = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_4567 = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V512_567u = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 5, i32 6, i32 7, i32 poison>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_2345 = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_4567 = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V512_567u = shufflevector <8 x double> %src512, <8 x double> undef, <4 x i32> <i32 5, i32 6, i32 7, i32 poison>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V256_01 = shufflevector <4 x double> %src256, <4 x double> undef, <2 x i32> <i32 0, i32 1>
@@ -69,8 +69,8 @@ define void @test_vXi64(<4 x i64> %src256, <8 x i64> %src512) {
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_45 = shufflevector <8 x i64> %src512, <8 x i64> undef, <2 x i32> <i32 4, i32 5>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_67 = shufflevector <8 x i64> %src512, <8 x i64> undef, <2 x i32> <i32 6, i32 7>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_0123 = shufflevector <8 x i64> %src512, <8 x i64> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_2345 = shufflevector <8 x i64> %src512, <8 x i64> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_4567 = shufflevector <8 x i64> %src512, <8 x i64> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_2345 = shufflevector <8 x i64> %src512, <8 x i64> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 5>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_4567 = shufflevector <8 x i64> %src512, <8 x i64> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V256_01 = shufflevector <4 x i64> %src256, <4 x i64> undef, <2 x i32> <i32 0, i32 1>
@@ -133,7 +133,7 @@ define void @test_vXi32(<4 x i32> %src128, <8 x i32> %src256, <16 x i32> %src512
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89AB = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_CDEF = shufflevector <16 x i32> %src512, <16 x i32> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_01234567 = shufflevector <16 x i32> %src512, <16 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_89ABCDEF = shufflevector <16 x i32> %src512, <16 x i32> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_89ABCDEF = shufflevector <16 x i32> %src512, <16 x i32> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V128_01 = shufflevector <4 x i32> %src128, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
@@ -277,7 +277,7 @@ define void @test_vXi16(<4 x i16> %src64, <8 x i16> %src128, <16 x i16> %src256,
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17 = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_18_19_1A_1B_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <8 x i32> <i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07_08_09_0A_0B_0C_0D_0E_0F = shufflevector <32 x i16> %src512, <32 x i16> undef, <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 14, i32 15>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_10_11_12_13_14_15_16_17_18_19_1A_1B_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <16 x i32> <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>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_10_11_12_13_14_15_16_17_18_19_1A_1B_1C_1D_1E_1F = shufflevector <32 x i16> %src512, <32 x i16> undef, <16 x i32> <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>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V64_01 = shufflevector <4 x i16> %src64, <4 x i16> undef, <2 x i32> <i32 0, i32 1>
@@ -575,7 +575,7 @@ define void @test_vXi8(<8 x i8> %src64, <16 x i8> %src128, <32 x i8> %src256, <6
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_20_21_22_23_24_25_26_27_28_29_2A_2B_2C_2D_2E_2F = shufflevector <64 x i8> %src512, <64 x i8> undef, <16 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_30_31_32_33_34_35_36_37_38_39_3A_3B_3C_3D_3E_3F = shufflevector <64 x i8> %src512, <64 x i8> undef, <16 x i32> <i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_00_01_02_03_04_05_06_07_08_09_0A_0B_0C_0D_0E_0F_10_11_12_13_14_15_16_17_18_19_1A_1B_1C_1D_1E_1F = shufflevector <64 x i8> %src512, <64 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 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>
-; VLEN128-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V512_20_21_22_23_24_25_26_27_28_29_2A_2B_2C_2D_2E_2F_30_31_32_33_34_35_36_37_38_39_3A_3B_3C_3D_3E_3F = shufflevector <64 x i8> %src512, <64 x i8> undef, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %V512_20_21_22_23_24_25_26_27_28_29_2A_2B_2C_2D_2E_2F_30_31_32_33_34_35_36_37_38_39_3A_3B_3C_3D_3E_3F = shufflevector <64 x i8> %src512, <64 x i8> undef, <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; VLEN128-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %V64_01 = shufflevector <8 x i8> %src64, <8 x i8> undef, <2 x i32> <i32 0, i32 1>
diff --git a/llvm/test/Analysis/CostModel/RISCV/shuffle-insert_subvector.ll b/llvm/test/Analysis/CostModel/RISCV/shuffle-insert_subvector.ll
index 2c93112fbf9c8..ea536f9e2deb8 100644
--- a/llvm/test/Analysis/CostModel/RISCV/shuffle-insert_subvector.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/shuffle-insert_subvector.ll
@@ -523,19 +523,19 @@ define void @test_vXi8(<2 x i8> %src16, <4 x i8> %src32, <8 x i8> %src64, <16x i
 
 define void @fixed_m1_in_m2_notail(<8 x i32> %src, <8 x i32> %passthru) vscale_range(2) {
 ; CHECK-LABEL: 'fixed_m1_in_m2_notail'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %1 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 9, i32 10, i32 11, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %5 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SIZE-LABEL: 'fixed_m1_in_m2_notail'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %1 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %1 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 6, i32 7>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 9, i32 10, i32 11, i32 7>
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %5 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
@@ -548,19 +548,19 @@ define void @fixed_m1_in_m2_notail(<8 x i32> %src, <8 x i32> %passthru) vscale_r
 
 define void @fixed_m2_in_m4_notail(<8 x i64> %src, <8 x i64> %passthru) vscale_range(2) {
 ; CHECK-LABEL: 'fixed_m2_in_m4_notail'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %1 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %1 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %2 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 8, i32 8, i32 10, i32 11, i32 5, i32 6, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %3 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 10, i32 11, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 10, i32 11, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %4 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 8, i32 10, i32 11, i32 7>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %5 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SIZE-LABEL: 'fixed_m2_in_m4_notail'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %1 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %1 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %2 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 8, i32 8, i32 10, i32 11, i32 5, i32 6, i32 7>
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %3 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 10, i32 11, i32 6, i32 7>
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 8, i32 8, i32 10, i32 11, i32 6, i32 7>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %4 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 8, i32 8, i32 10, i32 11, i32 7>
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %5 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 11>
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 11>
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   shufflevector <8 x i64> %src, <8 x i64> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
@@ -574,7 +574,7 @@ define void @fixed_m2_in_m4_notail(<8 x i64> %src, <8 x i64> %passthru) vscale_r
 define void @fixed_m1_in_m2_tail(<8 x i32> %src, <8 x i32> %passthru) vscale_range(2) {
 ; CHECK-LABEL: 'fixed_m1_in_m2_tail'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %1 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 8, i32 9, i32 10, i32 4, i32 4, i32 5, i32 6, i32 8>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %2 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %2 = shufflevector <8 x i32> %src, <8 x i32> %passthru, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 8, i32 10, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SIZE-LABEL: 'fixed_m1_in_m2_tail'