[AArch64][CostModel] Add cost model for experimental.vector.splice

This patch adds a new  ShuffleKind SK_Splice and then handle the cost in
getShuffleCost, as in experimental.vector.reverse.

Differential Revision: https://reviews.llvm.org/D104630

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -858,8 +858,11 @@ public:
     SK_ExtractSubvector, ///< ExtractSubvector Index indicates start offset.
     SK_PermuteTwoSrc,    ///< Merge elements from two source vectors into one
                          ///< with any shuffle mask.
-    SK_PermuteSingleSrc  ///< Shuffle elements of single source vector with any
+    SK_PermuteSingleSrc, ///< Shuffle elements of single source vector with any
                          ///< shuffle mask.
+    SK_Splice            ///< Concatenates elements from the first input vector
+                         ///< with elements of the second input vector. Returning
+                         ///< a vector of the same type as the input vectors.
   };
 
   /// Kind of the reduction data.

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -825,6 +825,7 @@ public:
     case TTI::SK_Transpose:
     case TTI::SK_InsertSubvector:
     case TTI::SK_ExtractSubvector:
+    case TTI::SK_Splice:
       break;
     }
     return Kind;
@@ -838,6 +839,7 @@ public:
     case TTI::SK_Broadcast:
       return getBroadcastShuffleOverhead(cast<FixedVectorType>(Tp));
     case TTI::SK_Select:
+    case TTI::SK_Splice:
     case TTI::SK_Reverse:
     case TTI::SK_Transpose:
     case TTI::SK_PermuteSingleSrc:
@@ -1371,6 +1373,12 @@ public:
                                      cast<VectorType>(Args[0]->getType()), None,
                                      0, cast<VectorType>(RetTy));
     }
+    case Intrinsic::experimental_vector_splice: {
+      unsigned Index = cast<ConstantInt>(Args[2])->getZExtValue();
+      return thisT()->getShuffleCost(TTI::SK_Splice,
+                                     cast<VectorType>(Args[0]->getType()), None,
+                                     Index, cast<VectorType>(RetTy));
+    }
     case Intrinsic::vector_reduce_add:
     case Intrinsic::vector_reduce_mul:
     case Intrinsic::vector_reduce_and:

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -18508,6 +18508,10 @@ bool AArch64TargetLowering::isAllActivePredicate(SDValue N) const {
   return ::isAllActivePredicate(N);
 }
 
+EVT AArch64TargetLowering::getPromotedVTForPredicate(EVT VT) const {
+  return ::getPromotedVTForPredicate(VT);
+}
+
 bool AArch64TargetLowering::SimplifyDemandedBitsForTargetNode(
     SDValue Op, const APInt &OriginalDemandedBits,
     const APInt &OriginalDemandedElts, KnownBits &Known, TargetLoweringOpt &TLO,

llvm/lib/Target/AArch64/AArch64ISelLowering.h

@@ -822,6 +822,7 @@ public:
   }
 
   bool isAllActivePredicate(SDValue N) const;
+  EVT getPromotedVTForPredicate(EVT VT) const;
 
 private:
   /// Keep a pointer to the AArch64Subtarget around so that we can

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -839,6 +839,7 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
     { ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i16, 1 },
     { ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i32, 3 },
     { ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i64, 5 },
+    { ISD::TRUNCATE, MVT::nxv16i1, MVT::nxv16i8, 1 },
     { ISD::TRUNCATE, MVT::nxv2i16, MVT::nxv2i32, 1 },
     { ISD::TRUNCATE, MVT::nxv2i32, MVT::nxv2i64, 1 },
     { ISD::TRUNCATE, MVT::nxv4i16, MVT::nxv4i32, 1 },
@@ -1897,6 +1898,55 @@ AArch64TTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *ValTy,
                                            CostKind);
 }
 
+InstructionCost AArch64TTIImpl::getSpliceCost(VectorType *Tp, int Index) {
+  static const CostTblEntry ShuffleTbl[] = {
+      { TTI::SK_Splice, MVT::nxv16i8,  1 },
+      { TTI::SK_Splice, MVT::nxv8i16,  1 },
+      { TTI::SK_Splice, MVT::nxv4i32,  1 },
+      { TTI::SK_Splice, MVT::nxv2i64,  1 },
+      { TTI::SK_Splice, MVT::nxv2f16,  1 },
+      { TTI::SK_Splice, MVT::nxv4f16,  1 },
+      { TTI::SK_Splice, MVT::nxv8f16,  1 },
+      { TTI::SK_Splice, MVT::nxv2bf16, 1 },
+      { TTI::SK_Splice, MVT::nxv4bf16, 1 },
+      { TTI::SK_Splice, MVT::nxv8bf16, 1 },
+      { TTI::SK_Splice, MVT::nxv2f32,  1 },
+      { TTI::SK_Splice, MVT::nxv4f32,  1 },
+      { TTI::SK_Splice, MVT::nxv2f64,  1 },
+  };
+
+  std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
+  Type *LegalVTy = EVT(LT.second).getTypeForEVT(Tp->getContext());
+  TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+  EVT PromotedVT = LT.second.getScalarType() == MVT::i1
+                       ? TLI->getPromotedVTForPredicate(EVT(LT.second))
+                       : LT.second;
+  Type *PromotedVTy = EVT(PromotedVT).getTypeForEVT(Tp->getContext());
+  InstructionCost LegalizationCost = 0;
+  if (Index < 0) {
+    LegalizationCost =
+        getCmpSelInstrCost(Instruction::ICmp, PromotedVTy, PromotedVTy,
+                           CmpInst::BAD_ICMP_PREDICATE, CostKind) +
+        getCmpSelInstrCost(Instruction::Select, PromotedVTy, LegalVTy,
+                           CmpInst::BAD_ICMP_PREDICATE, CostKind);
+  }
+
+  // Predicated splice are promoted when lowering. See AArch64ISelLowering.cpp
+  // Cost performed on a promoted type.
+  if (LT.second.getScalarType() == MVT::i1) {
+    LegalizationCost +=
+        getCastInstrCost(Instruction::ZExt, PromotedVTy, LegalVTy,
+                         TTI::CastContextHint::None, CostKind) +
+        getCastInstrCost(Instruction::Trunc, LegalVTy, PromotedVTy,
+                         TTI::CastContextHint::None, CostKind);
+  }
+  const auto *Entry =
+      CostTableLookup(ShuffleTbl, TTI::SK_Splice, PromotedVT.getSimpleVT());
+  assert(Entry && "Illegal Type for Splice");
+  LegalizationCost += Entry->Cost;
+  return LegalizationCost * LT.first;
+}
+
 InstructionCost AArch64TTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
                                                VectorType *Tp,
                                                ArrayRef<int> Mask, int Index,
@@ -1993,6 +2043,7 @@ InstructionCost AArch64TTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
     if (const auto *Entry = CostTableLookup(ShuffleTbl, Kind, LT.second))
       return LT.first * Entry->Cost;
   }
-
+  if (Kind == TTI::SK_Splice && isa<ScalableVectorType>(Tp))
+    return getSpliceCost(Tp, Index);
   return BaseT::getShuffleCost(Kind, Tp, Mask, Index, SubTp);
 }

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -166,6 +166,8 @@ public:
                                                 bool IsPairwiseForm,
                                                 TTI::TargetCostKind CostKind);
 
+  InstructionCost getSpliceCost(VectorType *Tp, int Index);
+
   InstructionCost getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,
       TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,

llvm/test/Analysis/CostModel/AArch64/splice.ll

@@ -0,0 +1,94 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -analyze -cost-model -S -mtriple=aarch64--linux-gnu | FileCheck %s
+
+define void @vector_splice() #0 {
+; CHECK-LABEL: 'vector_splice'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %splice.v16i8 = call <16 x i8> @llvm.experimental.vector.splice.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 180 for instruction: %splice.v32i8 = call <32 x i8> @llvm.experimental.vector.splice.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2i16 = call <2 x i16> @llvm.experimental.vector.splice.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4i16 = call <4 x i16> @llvm.experimental.vector.splice.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %splice.v8i16 = call <8 x i16> @llvm.experimental.vector.splice.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %splice.v16i16 = call <16 x i16> @llvm.experimental.vector.splice.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4i32 = call <4 x i32> @llvm.experimental.vector.splice.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %splice.v8i32 = call <8 x i32> @llvm.experimental.vector.splice.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2i64 = call <2 x i64> @llvm.experimental.vector.splice.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %splice.v4i64 = call <4 x i64> @llvm.experimental.vector.splice.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2f16 = call <2 x half> @llvm.experimental.vector.splice.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4f16 = call <4 x half> @llvm.experimental.vector.splice.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %splice.v8f16 = call <8 x half> @llvm.experimental.vector.splice.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %splice.v16f16 = call <16 x half> @llvm.experimental.vector.splice.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2f32 = call <2 x float> @llvm.experimental.vector.splice.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4f32 = call <4 x float> @llvm.experimental.vector.splice.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %splice.v8f32 = call <8 x float> @llvm.experimental.vector.splice.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2f64 = call <2 x double> @llvm.experimental.vector.splice.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %splice.v4f64 = call <4 x double> @llvm.experimental.vector.splice.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2bf16 = call <2 x bfloat> @llvm.experimental.vector.splice.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4bf16 = call <4 x bfloat> @llvm.experimental.vector.splice.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %splice.v8bf16 = call <8 x bfloat> @llvm.experimental.vector.splice.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %splice.v16bf16 = call <16 x bfloat> @llvm.experimental.vector.splice.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 90 for instruction: %splice.v16i1 = call <16 x i1> @llvm.experimental.vector.splice.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %splice.v8i1 = call <8 x i1> @llvm.experimental.vector.splice.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %splice.v4i1 = call <4 x i1> @llvm.experimental.vector.splice.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice.v2i1 = call <2 x i1> @llvm.experimental.vector.splice.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
+;
+  %splice.v16i8 = call <16 x i8> @llvm.experimental.vector.splice.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
+  %splice.v32i8 = call <32 x i8> @llvm.experimental.vector.splice.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
+  %splice.v2i16 = call <2 x i16> @llvm.experimental.vector.splice.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
+  %splice.v4i16 = call <4 x i16> @llvm.experimental.vector.splice.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
+  %splice.v8i16 = call <8 x i16> @llvm.experimental.vector.splice.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
+  %splice.v16i16 = call <16 x i16> @llvm.experimental.vector.splice.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
+  %splice.v4i32 = call <4 x i32> @llvm.experimental.vector.splice.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
+  %splice.v8i32 = call <8 x i32> @llvm.experimental.vector.splice.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
+  %splice.v2i64 = call <2 x i64> @llvm.experimental.vector.splice.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
+  %splice.v4i64 = call <4 x i64> @llvm.experimental.vector.splice.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
+  %splice.v2f16 = call <2 x half> @llvm.experimental.vector.splice.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
+  %splice.v4f16 = call <4 x half> @llvm.experimental.vector.splice.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
+  %splice.v8f16 = call <8 x half> @llvm.experimental.vector.splice.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
+  %splice.v16f16 = call <16 x half> @llvm.experimental.vector.splice.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
+  %splice.v2f32 = call <2 x float> @llvm.experimental.vector.splice.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
+  %splice.v4f32 = call <4 x float> @llvm.experimental.vector.splice.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
+  %splice.v8f32 = call <8 x float> @llvm.experimental.vector.splice.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
+  %splice.v2f64 = call <2 x double> @llvm.experimental.vector.splice.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
+  %splice.v4f64 = call <4 x double> @llvm.experimental.vector.splice.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
+  %splice.v2bf16 = call <2 x bfloat> @llvm.experimental.vector.splice.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
+  %splice.v4bf16 = call <4 x bfloat> @llvm.experimental.vector.splice.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
+  %splice.v8bf16 = call <8 x bfloat> @llvm.experimental.vector.splice.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
+  %splice.v16bf16 = call <16 x bfloat> @llvm.experimental.vector.splice.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
+  %splice.v16i1 = call <16 x i1> @llvm.experimental.vector.splice.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
+  %splice.v8i1 =  call <8 x i1> @llvm.experimental.vector.splice.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
+  %splice.v4i1 = call <4 x i1> @llvm.experimental.vector.splice.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
+  %splice.v2i1 = call <2 x i1> @llvm.experimental.vector.splice.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
+  ret void
+}
+
+declare <2 x i1> @llvm.experimental.vector.splice.v2i1(<2 x i1>, <2 x i1>, i32)
+declare <4 x i1> @llvm.experimental.vector.splice.v4i1(<4 x i1>, <4 x i1>, i32)
+declare <8 x i1> @llvm.experimental.vector.splice.v8i1(<8 x i1>, <8 x i1>, i32)
+declare <16 x i1> @llvm.experimental.vector.splice.v16i1(<16 x i1>, <16 x i1>, i32)
+declare <2 x i8> @llvm.experimental.vector.splice.v2i8(<2 x i8>, <2 x i8>, i32)
+declare <16 x i8> @llvm.experimental.vector.splice.v16i8(<16 x i8>, <16 x i8>, i32)
+declare <32 x i8> @llvm.experimental.vector.splice.v32i8(<32 x i8>, <32 x i8>, i32)
+declare <2 x i16> @llvm.experimental.vector.splice.v2i16(<2 x i16>, <2 x i16>, i32)
+declare <4 x i16> @llvm.experimental.vector.splice.v4i16(<4 x i16>, <4 x i16>, i32)
+declare <8 x i16> @llvm.experimental.vector.splice.v8i16(<8 x i16>, <8 x i16>, i32)
+declare <16 x i16> @llvm.experimental.vector.splice.v16i16(<16 x i16>, <16 x i16>, i32)
+declare <4 x i32> @llvm.experimental.vector.splice.v4i32(<4 x i32>, <4 x i32>, i32)
+declare <8 x i32> @llvm.experimental.vector.splice.v8i32(<8 x i32>, <8 x i32>, i32)
+declare <2 x i64> @llvm.experimental.vector.splice.v2i64(<2 x i64>, <2 x i64>, i32)
+declare <4 x i64> @llvm.experimental.vector.splice.v4i64(<4 x i64>, <4 x i64>, i32)
+declare <2 x half> @llvm.experimental.vector.splice.v2f16(<2 x half>, <2 x half>, i32)
+declare <4 x half> @llvm.experimental.vector.splice.v4f16(<4 x half>, <4 x half>, i32)
+declare <8 x half> @llvm.experimental.vector.splice.v8f16(<8 x half>, <8 x half>, i32)
+declare <16 x half> @llvm.experimental.vector.splice.v16f16(<16 x half>, <16 x half>, i32)
+declare <2 x bfloat> @llvm.experimental.vector.splice.v2bf16(<2 x bfloat>, <2 x bfloat>, i32)
+declare <4 x bfloat> @llvm.experimental.vector.splice.v4bf16(<4 x bfloat>, <4 x bfloat>, i32)
+declare <8 x bfloat> @llvm.experimental.vector.splice.v8bf16(<8 x bfloat>, <8 x bfloat>, i32)
+declare <16 x bfloat> @llvm.experimental.vector.splice.v16bf16(<16 x bfloat>, <16 x bfloat>, i32)
+declare <2 x float> @llvm.experimental.vector.splice.v2f32(<2 x float>, <2 x float>, i32)
+declare <4 x float> @llvm.experimental.vector.splice.v4f32(<4 x float>, <4 x float>, i32)
+declare <8 x float> @llvm.experimental.vector.splice.v8f32(<8 x float>, <8 x float>, i32)
+declare <16 x float> @llvm.experimental.vector.splice.v16f32(<16 x float>, <16 x float>, i32)
+declare <2 x double> @llvm.experimental.vector.splice.v2f64(<2 x double>, <2 x double>, i32)
+declare <4 x double> @llvm.experimental.vector.splice.v4f64(<4 x double>, <4 x double>, i32)
+
+attributes #0 = { "target-features"="+bf16" }

llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll

@@ -1,4 +1,5 @@
-; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=+sve  < %s | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -analyze -cost-model -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s
 
 define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
 ; CHECK-LABEL: 'vector_insert_extract'
@@ -231,4 +232,149 @@ declare <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float>)
 declare <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float>)
 declare <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float>)
 
+define void @vector_splice() #0 {
+; CHECK-LABEL: 'vector_splice'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2i64_neg = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+
+  %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
+  %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
+  %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
+  %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
+  %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
+  %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
+  %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
+  %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
+  %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
+  %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
+  %splice_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
+  %splice_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
+  %splice_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
+  %splice_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
+  %splice_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
+  %splice_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
+  %splice_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
+  %splice_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
+  %splice_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
+  %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
+  %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
+  %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
+  %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
+  %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+  %splice_nxv8i1 =  call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+  %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+  %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+;; negative Index
+  %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
+  %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
+  %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
+  %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
+  %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
+  %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
+  %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
+  %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
+  %splice_nxv2i64_neg= call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
+  %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
+  %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
+  %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
+  %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
+  %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
+  %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
+  %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
+  %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
+  %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
+  %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
+  %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
+  %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
+  %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
+  %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
+  %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+  %splice_nxv8i1_neg =  call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+  %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+  %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+  ret void
+}
+
+declare <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, i32)
+declare <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, i32)
+declare <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, i32)
+declare <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, i32)
+declare <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i8>, i32)
+declare <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, i32)
+declare <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>, i32)
+declare <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>, i32)
+declare <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>, i32)
+declare <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, i32)
+declare <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>, i32)
+declare <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, i32)
+declare <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32)
+declare <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, i32)
+declare <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>, i32)
+declare <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, i32)
+declare <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, i32)
+declare <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
+declare <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, i32)
+declare <vscale x 2 x bfloat> @llvm.experimental.vector.splice.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat>, i32)
+declare <vscale x 4 x bfloat> @llvm.experimental.vector.splice.nxv4bf16(<vscale x 4 x bfloat>, <vscale x 4 x bfloat>, i32)
+declare <vscale x 8 x bfloat> @llvm.experimental.vector.splice.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>, i32)
+declare <vscale x 16 x bfloat> @llvm.experimental.vector.splice.nxv16bf16(<vscale x 16 x bfloat>, <vscale x 16 x bfloat>, i32)
+declare <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, i32)
+declare <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
+declare <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, i32)
+declare <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, i32)
+declare <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)
+declare <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, i32)
+
 attributes #0 = { "target-features"="+sve,+bf16" }