[CostModel][AArch64] Add missing costs for getShuffleCost for scalable vectors

[sdesmalen]

LGTM, thanks @CarolineConcatto!

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

static const CostTblEntry ShuffleTbl[] = {
       { TTI::SK_Reverse, MVT::v2f32, 1 }, // mov.
       { TTI::SK_Reverse, MVT::v4f32, 2 }, // REV64; EXT
       { TTI::SK_Reverse, MVT::v2f64, 1 }, // mov.
       // Broadcast shuffle kinds for scalable vectors
       { TTI::SK_Broadcast, MVT::nxv16i8,  1 },
       { TTI::SK_Broadcast, MVT::nxv8i16,  1 },
       { TTI::SK_Broadcast, MVT::nxv4i32,  1 },
       { TTI::SK_Broadcast, MVT::nxv2i64,  1 },
+      { TTI::SK_Broadcast, MVT::nxv2f16,  1 },
+      { TTI::SK_Broadcast, MVT::nxv4f16,  1 },
       { TTI::SK_Broadcast, MVT::nxv8f16,  1 },
+      { TTI::SK_Broadcast, MVT::nxv2bf16, 1 },
+      { TTI::SK_Broadcast, MVT::nxv4bf16, 1 },
       { TTI::SK_Broadcast, MVT::nxv8bf16, 1 },
+      { TTI::SK_Broadcast, MVT::nxv2f32,  1 },
       { TTI::SK_Broadcast, MVT::nxv4f32,  1 },
       { TTI::SK_Broadcast, MVT::nxv2f64,  1 },
+      { TTI::SK_Broadcast, MVT::nxv16i1,  1 },
+      { TTI::SK_Broadcast, MVT::nxv8i1,   1 },
+      { TTI::SK_Broadcast, MVT::nxv4i1,   1 },
+      { TTI::SK_Broadcast, MVT::nxv2i1,   1 },
       // Handle the cases for vector.reverse with scalable vectors
       { TTI::SK_Reverse, MVT::nxv16i8,  1 },
       { TTI::SK_Reverse, MVT::nxv8i16,  1 },
       { TTI::SK_Reverse, MVT::nxv4i32,  1 },
       { TTI::SK_Reverse, MVT::nxv2i64,  1 },
+      { TTI::SK_Reverse, MVT::nxv2f16,  1 },
+      { TTI::SK_Reverse, MVT::nxv4f16,  1 },
       { TTI::SK_Reverse, MVT::nxv8f16,  1 },
+      { TTI::SK_Reverse, MVT::nxv2bf16, 1 },
+      { TTI::SK_Reverse, MVT::nxv4bf16, 1 },
       { TTI::SK_Reverse, MVT::nxv8bf16, 1 },
+      { TTI::SK_Reverse, MVT::nxv2f32,  1 },
       { TTI::SK_Reverse, MVT::nxv4f32,  1 },
       { TTI::SK_Reverse, MVT::nxv2f64,  1 },
       { TTI::SK_Reverse, MVT::nxv16i1,  1 },
       { TTI::SK_Reverse, MVT::nxv8i1,   1 },
       { TTI::SK_Reverse, MVT::nxv4i1,   1 },
       { TTI::SK_Reverse, MVT::nxv2i1,   1 },
     };
     std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
     if (const auto *Entry = CostTableLookup(ShuffleTbl, Kind, LT.second))
       return LT.first * Entry->Cost;
   }
 
   return BaseT::getShuffleCost(Kind, Tp, Mask, Index, SubTp);
 }

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

 declare <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32>, i1)
 declare <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32>, i1)
 
 
 define void @vector_reverse() #0 {
 ; CHECK-LABEL: 'vector_reverse':
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8if16 = call <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
 
   %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8> undef)
   %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8> undef)
+  %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.experimental.vector.reverse.nxv2i16(<vscale x 2 x i16> undef)
+  %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.experimental.vector.reverse.nxv4i16(<vscale x 4 x i16> undef)
   %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.experimental.vector.reverse.nxv8i16(<vscale x 8 x i16> undef)
   %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.experimental.vector.reverse.nxv16i16(<vscale x 16 x i16> undef)
   %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32> undef)
   %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.experimental.vector.reverse.nxv8i32(<vscale x 8 x i32> undef)
   %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.experimental.vector.reverse.nxv2i64(<vscale x 2 x i64> undef)
   %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.experimental.vector.reverse.nxv4i64(<vscale x 4 x i64> undef)
-  %reverse_nxv8if16 = call <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
+  %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.experimental.vector.reverse.nxv2f16(<vscale x 2 x half> undef)
+  %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.experimental.vector.reverse.nxv4f16(<vscale x 4 x half> undef)
+  %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half> undef)
   %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.experimental.vector.reverse.nxv16f16(<vscale x 16 x half> undef)
+  %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.experimental.vector.reverse.nxv2f32(<vscale x 2 x float> undef)
   %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.experimental.vector.reverse.nxv4f32(<vscale x 4 x float> undef)
   %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.experimental.vector.reverse.nxv8f32(<vscale x 8 x float> undef)
   %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.experimental.vector.reverse.nxv2f64(<vscale x 2 x double> undef)
   %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double> undef)
+  %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.experimental.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> undef)
+  %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.experimental.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> undef)
   %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> undef)
   %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> undef)
   %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1> undef)
   %reverse_nxv8i1 =  call <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1> undef)
   %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1> undef)
   %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1> undef)
   ret void
 }
 declare <vscale x 16 x i8> @llvm.experimental.vector.reverse.nxv16i8(<vscale x 16 x i8>)
 declare <vscale x 32 x i8> @llvm.experimental.vector.reverse.nxv32i8(<vscale x 32 x i8>)
+declare <vscale x 2 x i16> @llvm.experimental.vector.reverse.nxv2i16(<vscale x 2 x i16>)
+declare <vscale x 4 x i16> @llvm.experimental.vector.reverse.nxv4i16(<vscale x 4 x i16>)
 declare <vscale x 8 x i16> @llvm.experimental.vector.reverse.nxv8i16(<vscale x 8 x i16>)
 declare <vscale x 16 x i16> @llvm.experimental.vector.reverse.nxv16i16(<vscale x 16 x i16>)
 declare <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32>)
 declare <vscale x 8 x i32> @llvm.experimental.vector.reverse.nxv8i32(<vscale x 8 x i32>)
 declare <vscale x 2 x i64> @llvm.experimental.vector.reverse.nxv2i64(<vscale x 2 x i64>)
 declare <vscale x 4 x i64> @llvm.experimental.vector.reverse.nxv4i64(<vscale x 4 x i64>)
+declare <vscale x 2 x half> @llvm.experimental.vector.reverse.nxv2f16(<vscale x 2 x half>)
+declare <vscale x 4 x half> @llvm.experimental.vector.reverse.nxv4f16(<vscale x 4 x half>)
 declare <vscale x 8 x half> @llvm.experimental.vector.reverse.nxv8f16(<vscale x 8 x half>)
 declare <vscale x 16 x half> @llvm.experimental.vector.reverse.nxv16f16(<vscale x 16 x half>)
+declare <vscale x 2 x float> @llvm.experimental.vector.reverse.nxv2f32(<vscale x 2 x float>)
 declare <vscale x 4 x float> @llvm.experimental.vector.reverse.nxv4f32(<vscale x 4 x float>)
 declare <vscale x 8 x float> @llvm.experimental.vector.reverse.nxv8f32(<vscale x 8 x float>)
 declare <vscale x 2 x double> @llvm.experimental.vector.reverse.nxv2f64(<vscale x 2 x double>)
 declare <vscale x 4 x double> @llvm.experimental.vector.reverse.nxv4f64(<vscale x 4 x double>)
+declare <vscale x 2 x bfloat> @llvm.experimental.vector.reverse.nxv2bf16(<vscale x 2 x bfloat>)
+declare <vscale x 4 x bfloat> @llvm.experimental.vector.reverse.nxv4bf16(<vscale x 4 x bfloat>)
 declare <vscale x 8 x bfloat> @llvm.experimental.vector.reverse.nxv8bf16(<vscale x 8 x bfloat>)
 declare <vscale x 16 x bfloat> @llvm.experimental.vector.reverse.nxv16bf16(<vscale x 16 x bfloat>)
 declare <vscale x 16 x i1> @llvm.experimental.vector.reverse.nxv16i1(<vscale x 16 x i1>)
 declare <vscale x 8 x i1> @llvm.experimental.vector.reverse.nxv8i1(<vscale x 8 x i1>)
 declare <vscale x 4 x i1> @llvm.experimental.vector.reverse.nxv4i1(<vscale x 4 x i1>)
 declare <vscale x 2 x i1> @llvm.experimental.vector.reverse.nxv2i1(<vscale x 2 x i1>)
 
 define void @unsupported_fp_ops(<vscale x 4 x float> %vec) {

llvm/test/Analysis/CostModel/AArch64/sve-shuffle-broadcast.ll

 ; Check getShuffleCost for SK_BroadCast with scalable vector
 
 ; RUN: opt -cost-model -analyze -mtriple=aarch64--linux-gnu -mattr=sve  < %s | FileCheck %s
 
 define void  @broadcast() #0{
 ; CHECK-LABEL: 'broadcast':
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %zero = shufflevector <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction:   %1 = shufflevector <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %2 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %3 = shufflevector <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %4 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %5 = shufflevector <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %6 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %7 = shufflevector <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %8 = shufflevector <vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %9 = shufflevector <vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %10 = shufflevector <vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %11 = shufflevector <vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %12 = shufflevector <vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %13 = shufflevector <vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %14 = shufflevector <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %15 = shufflevector <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %8 = shufflevector <vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %9 = shufflevector <vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %10 = shufflevector <vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %11 = shufflevector <vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %12 = shufflevector <vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %13 = shufflevector <vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %14 = shufflevector <vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %15 = shufflevector <vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %16 = shufflevector <vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %17 = shufflevector <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %18 = shufflevector <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %19 = shufflevector <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction:   %20 = shufflevector <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %21 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %22 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %23 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction:   %24 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NETX: Cost Model: Found an estimated cost of 0 for instruction:   ret void
 
   %zero = shufflevector <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
   %1 = shufflevector <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i32> zeroinitializer
   %2 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
   %3 = shufflevector <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i32> zeroinitializer
   %4 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
   %5 = shufflevector <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> zeroinitializer
   %6 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
   %7 = shufflevector <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i32> zeroinitializer
-  %8 = shufflevector <vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
-  %9 = shufflevector <vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
- %10 = shufflevector <vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
-  %11 = shufflevector <vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
- %12 = shufflevector <vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
- %13 = shufflevector <vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
- %14 = shufflevector <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x i32> zeroinitializer
- %15 = shufflevector <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x i32> zeroinitializer
+  %8 = shufflevector <vscale x 2 x half> undef, <vscale x 2 x half> undef, <vscale x 2 x i32> zeroinitializer
+  %9 = shufflevector <vscale x 4 x half> undef, <vscale x 4 x half> undef, <vscale x 4 x i32> zeroinitializer
+  %10 = shufflevector <vscale x 8 x half> undef, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
+  %11 = shufflevector <vscale x 16 x half> undef, <vscale x 16 x half> undef, <vscale x 16 x i32> zeroinitializer
+ %12 = shufflevector <vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i32> zeroinitializer
+ %13 = shufflevector <vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i32> zeroinitializer
+ %14 = shufflevector <vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i32> zeroinitializer
+ %15 = shufflevector <vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i32> zeroinitializer
+ %16 = shufflevector <vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i32> zeroinitializer
+ %17 = shufflevector <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x i32> zeroinitializer
+ %18 = shufflevector <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x i32> zeroinitializer
+ %19 = shufflevector <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x i32> zeroinitializer
+ %20 = shufflevector <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x i32> zeroinitializer
+ %21 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+ %22 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
+ %23 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
+ %24 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
   ret void
 }
 
 attributes #0 = { "target-features"="+sve,+bf16" }