[CostModel][X86][ARM] Teach getCastInstrCost to include the splitting factor when handling operations that type legalize to the same number of subvectors or scalar components

[craig.topper]

Summary

Previously, we just always returned 1. But that ignores that we have to do the operation for each subvector or scalar component.

[RKSimon]

LGTM - cheers

llvm/include/llvm/CodeGen/BasicTTIImpl.h

if ((Opcode == Instruction::ZExt || Opcode == Instruction::SExt) &&
           ((Opcode == Instruction::ZExt) ? ISD::ZEXTLOAD : ISD::SEXTLOAD);
         if (TLI->isLoadExtLegal(LType, ExtVT, LoadVT))
           return 0;
     }
 
     // If the cast is marked as legal (or promote) then assume low cost.
     if (SrcLT.first == DstLT.first &&
         TLI->isOperationLegalOrPromote(ISD, DstLT.second))
-      return 1;
+      return SrcLT.first;
 
     // Handle scalar conversions.
     if (!Src->isVectorTy() && !Dst->isVectorTy()) {
       // Scalar bitcasts are usually free.
       if (Opcode == Instruction::BitCast)
         return 0;
 
       // Just check the op cost. If the operation is legal then assume it costs

llvm/test/Analysis/CostModel/ARM/cast.ll

 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r128 = fptoui <4 x double> undef to <4 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %r129 = fptosi <4 x double> undef to <4 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r130 = fptoui <8 x float> undef to <8 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r131 = fptosi <8 x float> undef to <8 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r132 = fptoui <8 x float> undef to <8 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r133 = fptosi <8 x float> undef to <8 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r134 = fptoui <8 x float> undef to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r135 = fptosi <8 x float> undef to <8 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r136 = fptoui <8 x float> undef to <8 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r137 = fptosi <8 x float> undef to <8 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r136 = fptoui <8 x float> undef to <8 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r137 = fptosi <8 x float> undef to <8 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r138 = fptoui <8 x float> undef to <8 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r139 = fptosi <8 x float> undef to <8 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r140 = fptoui <8 x double> undef to <8 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r141 = fptosi <8 x double> undef to <8 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r142 = fptoui <8 x double> undef to <8 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r143 = fptosi <8 x double> undef to <8 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r144 = fptoui <8 x double> undef to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r145 = fptosi <8 x double> undef to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r146 = fptoui <8 x double> undef to <8 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r147 = fptosi <8 x double> undef to <8 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r148 = fptoui <8 x double> undef to <8 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %r149 = fptosi <8 x double> undef to <8 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r150 = fptoui <16 x float> undef to <16 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r151 = fptosi <16 x float> undef to <16 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r152 = fptoui <16 x float> undef to <16 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r153 = fptosi <16 x float> undef to <16 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r154 = fptoui <16 x float> undef to <16 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r155 = fptosi <16 x float> undef to <16 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r156 = fptoui <16 x float> undef to <16 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r157 = fptosi <16 x float> undef to <16 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r156 = fptoui <16 x float> undef to <16 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r157 = fptosi <16 x float> undef to <16 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r158 = fptoui <16 x float> undef to <16 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1322 for instruction: %r159 = fptosi <16 x float> undef to <16 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r160 = fptoui <16 x double> undef to <16 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r161 = fptosi <16 x double> undef to <16 x i1>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r162 = fptoui <16 x double> undef to <16 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r163 = fptosi <16 x double> undef to <16 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r164 = fptoui <16 x double> undef to <16 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 661 for instruction: %r165 = fptosi <16 x double> undef to <16 x i16>

 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r208 = uitofp <4 x i64> undef to <4 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 130 for instruction: %r209 = sitofp <4 x i64> undef to <4 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r210 = uitofp <8 x i1> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r211 = sitofp <8 x i1> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r212 = uitofp <8 x i8> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r213 = sitofp <8 x i8> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r214 = uitofp <8 x i16> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r215 = sitofp <8 x i16> undef to <8 x float>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r216 = uitofp <8 x i32> undef to <8 x float>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r217 = sitofp <8 x i32> undef to <8 x float>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r216 = uitofp <8 x i32> undef to <8 x float>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r217 = sitofp <8 x i32> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r218 = uitofp <8 x i64> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r219 = sitofp <8 x i64> undef to <8 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r220 = uitofp <8 x i1> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r221 = sitofp <8 x i1> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r222 = uitofp <8 x i8> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r223 = sitofp <8 x i8> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r224 = uitofp <8 x i16> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r225 = sitofp <8 x i16> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r226 = uitofp <8 x i16> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r227 = sitofp <8 x i16> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r228 = uitofp <8 x i64> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 522 for instruction: %r229 = sitofp <8 x i64> undef to <8 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r230 = uitofp <16 x i1> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r231 = sitofp <16 x i1> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r232 = uitofp <16 x i8> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r233 = sitofp <16 x i8> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r234 = uitofp <16 x i16> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r235 = sitofp <16 x i16> undef to <16 x float>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r236 = uitofp <16 x i32> undef to <16 x float>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r237 = sitofp <16 x i32> undef to <16 x float>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r236 = uitofp <16 x i32> undef to <16 x float>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r237 = sitofp <16 x i32> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 170 for instruction: %r238 = uitofp <16 x i64> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 170 for instruction: %r239 = sitofp <16 x i64> undef to <16 x float>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r240 = uitofp <16 x i1> undef to <16 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r241 = sitofp <16 x i1> undef to <16 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r242 = uitofp <16 x i8> undef to <16 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r243 = sitofp <16 x i8> undef to <16 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r244 = uitofp <16 x i16> undef to <16 x double>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1045 for instruction: %r245 = sitofp <16 x i16> undef to <16 x double>

 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r62 = sitofp i32 undef to float
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r63 = uitofp i32 undef to float
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r64 = sitofp i32 undef to double
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r65 = uitofp i32 undef to double
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r66 = sitofp i64 undef to float
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r67 = uitofp i64 undef to float
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r68 = sitofp i64 undef to double
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r69 = uitofp i64 undef to double
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_0 = sext <8 x i8> undef to <8 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_1 = zext <8 x i8> undef to <8 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %rext_2 = sext <8 x i16> undef to <8 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_3 = zext <8 x i16> undef to <8 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %rext_4 = sext <4 x i16> undef to <4 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %rext_5 = zext <4 x i16> undef to <4 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %rext_6 = sext <2 x i8> undef to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>

 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r62 = sitofp i32 undef to float
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r63 = uitofp i32 undef to float
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r64 = sitofp i32 undef to double
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r65 = uitofp i32 undef to double
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r66 = sitofp i64 undef to float
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r67 = uitofp i64 undef to float
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r68 = sitofp i64 undef to double
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r69 = uitofp i64 undef to double
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_0 = sext <8 x i8> undef to <8 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_1 = zext <8 x i8> undef to <8 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 55 for instruction: %rext_2 = sext <8 x i16> undef to <8 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %rext_3 = zext <8 x i16> undef to <8 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %rext_4 = sext <4 x i16> undef to <4 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %rext_5 = zext <4 x i16> undef to <4 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %rext_6 = sext <2 x i8> undef to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>

 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i8 %loadi8 to i64
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r5 = zext i8 %loadi8 to i64
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r6 = sext i16 %loadi16 to i32
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r7 = zext i16 %loadi16 to i32
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r8 = sext i16 %loadi16 to i64
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %loadi16 to i64
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r11 = zext i32 %loadi32 to i64
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
-; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-V8M-MAIN-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; CHECK-V8M-BASE-LABEL: 'load_extends'
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi8 = load i8, i8* undef

 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i8 %loadi8 to i64
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r5 = zext i8 %loadi8 to i64
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r6 = sext i16 %loadi16 to i32
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r7 = zext i16 %loadi16 to i32
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r8 = sext i16 %loadi16 to i64
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %loadi16 to i64
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r11 = zext i32 %loadi32 to i64
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
-; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-V8M-BASE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; CHECK-V8R-LABEL: 'load_extends'
 ; CHECK-V8R-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi8 = load i8, i8* undef

llvm/test/Analysis/CostModel/X86/fptosi.ll

;
   %V2I64 = fptosi <2 x float> undef to <2 x i64>
   %V4I64 = fptosi <4 x float> undef to <4 x i64>
   %V8I64 = fptosi <8 x float> undef to <8 x i64>
   %V16I64 = fptosi <16 x float> undef to <16 x i64>
   ret i32 undef
 }
 
 define i32 @fptosi_float_i32(i32 %arg) {
-; CHECK-LABEL: 'fptosi_float_i32'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE-LABEL: 'fptosi_float_i32'
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
+; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
+; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX-LABEL: 'fptosi_float_i32'
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
+; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+;
+; AVX512-LABEL: 'fptosi_float_i32'
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
+; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I32 = fptosi float undef to i32
   %V4I32 = fptosi <4 x float> undef to <4 x i32>
   %V8I32 = fptosi <8 x float> undef to <8 x i32>
   %V16I32 = fptosi <16 x float> undef to <16 x i32>
   ret i32 undef
 }