[AArch64] Add CostKind to getSpliceCost (#135537)

This likely does not alter much yet with how the costs are used. Like
other cost functions the CostKind should be passed into and through the
function.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -5207,7 +5207,8 @@ AArch64TTIImpl::getMulAccReductionCost(bool IsUnsigned, Type *ResTy,
   return BaseT::getMulAccReductionCost(IsUnsigned, ResTy, VecTy, CostKind);
 }
 
-InstructionCost AArch64TTIImpl::getSpliceCost(VectorType *Tp, int Index) {
+InstructionCost AArch64TTIImpl::getSpliceCost(VectorType *Tp, int Index,
+                                              TTI::TargetCostKind CostKind) {
   static const CostTblEntry ShuffleTbl[] = {
       { TTI::SK_Splice, MVT::nxv16i8,  1 },
       { TTI::SK_Splice, MVT::nxv8i16,  1 },
@@ -5233,7 +5234,6 @@ InstructionCost AArch64TTIImpl::getSpliceCost(VectorType *Tp, int Index) {
 
   std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(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;
@@ -5616,7 +5616,7 @@ InstructionCost AArch64TTIImpl::getShuffleCost(
   }
 
   if (Kind == TTI::SK_Splice && isa<ScalableVectorType>(Tp))
-    return getSpliceCost(Tp, Index);
+    return getSpliceCost(Tp, Index, CostKind);
 
   // Inserting a subvector can often be done with either a D, S or H register
   // move, so long as the inserted vector is "aligned".

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -219,7 +219,8 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
                                                 VectorType *ValTy,
                                                 TTI::TargetCostKind CostKind);
 
-  InstructionCost getSpliceCost(VectorType *Tp, int Index);
+  InstructionCost getSpliceCost(VectorType *Tp, int Index,
+                                TTI::TargetCostKind CostKind);
 
   InstructionCost getArithmeticInstrCost(
       unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,

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

@@ -638,10 +638,10 @@ define void @vector_splice() #0 {
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
@@ -671,10 +671,10 @@ define void @vector_splice() #0 {
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;
@@ -702,10 +702,10 @@ define void @vector_splice() #0 {
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:3 Lat:3 SizeLat:3 for: %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
@@ -735,10 +735,10 @@ define void @vector_splice() #0 {
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
-; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv8i1_neg = call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
+; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:5 Lat:5 SizeLat:5 for: %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)
 ; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;