[ARM] Update trunc costs

[dmgreen]

Summary

We did not have specific costs for larger than legal truncates that were not otherwise cheap (where they were next to stores, for example). As MVE does not have a dedicated instruction for them (and we do not use loads/stores yet), they should be expensive as they get expanded to a series of lane moves.

[samtebbs]

LGTM

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

if (CCH == TTI::CastContextHint::Normal ||
     }
 
     // The truncate of a store is free. This is the mirror of extends above.
     static const TypeConversionCostTblEntry MVEStoreConversionTbl[] = {
         {ISD::TRUNCATE, MVT::v4i32, MVT::v4i16, 0},
         {ISD::TRUNCATE, MVT::v4i32, MVT::v4i8, 0},
         {ISD::TRUNCATE, MVT::v8i16, MVT::v8i8, 0},
         {ISD::TRUNCATE, MVT::v8i32, MVT::v8i16, 1},
+        {ISD::TRUNCATE, MVT::v8i32, MVT::v8i8, 1},
         {ISD::TRUNCATE, MVT::v16i32, MVT::v16i8, 3},
         {ISD::TRUNCATE, MVT::v16i16, MVT::v16i8, 1},
     };
     if (SrcTy.isVector() && ST->hasMVEIntegerOps()) {
       if (const auto *Entry =
               ConvertCostTableLookup(MVEStoreConversionTbl, ISD,
                                      SrcTy.getSimpleVT(), DstTy.getSimpleVT()))
         return AdjustCost(Entry->Cost * ST->getMVEVectorCostFactor());
if (SrcTy.isFixedLengthVector())
       Lanes = SrcTy.getVectorNumElements();
 
     if (IsLegalFPType(SrcTy) && IsLegalFPType(DstTy))
       return Lanes;
     else
       return Lanes * CallCost;
   }
 
+  if (ISD == ISD::TRUNCATE && ST->hasMVEIntegerOps() &&
+      SrcTy.isFixedLengthVector()) {
+    // Treat a truncate with larger than legal source (128bits for MVE) as
+    // expensive, 2 instructions per lane.
+    if ((SrcTy.getScalarType() == MVT::i8 ||
+         SrcTy.getScalarType() == MVT::i16 ||
+         SrcTy.getScalarType() == MVT::i32) &&
+        SrcTy.getSizeInBits() > 128 &&
+        SrcTy.getSizeInBits() > DstTy.getSizeInBits())
+      return SrcTy.getVectorNumElements() * 2;
+  }
+
   // Scalar integer conversion costs.
   static const TypeConversionCostTblEntry ARMIntegerConversionTbl[] = {
     // i16 -> i64 requires two dependent operations.
     { ISD::SIGN_EXTEND, MVT::i64, MVT::i16, 2 },
 
     // Truncates on i64 are assumed to be free.
     { ISD::TRUNCATE,    MVT::i32, MVT::i64, 0 },
     { ISD::TRUNCATE,    MVT::i16, MVT::i64, 0 },

llvm/test/Analysis/CostModel/ARM/arith-overflow.ll

 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 288 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 768 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 86 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 316 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1208 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 424 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 164 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 488 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 424 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 228 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 616 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'smul'
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)

 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 101 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 325 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 153 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 557 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 75 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 147 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 71 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 139 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 275 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 
   %I32 = call {i32, i1} @llvm.smul.with.overflow.i32(i32 undef, i32 undef)

 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 248 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 624 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 312 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 1200 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 480 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 416 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 224 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 608 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'umul'
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)

 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 61 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 181 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 151 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 553 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 73 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 143 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 137 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 271 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 
   %I32 = call {i32, i1} @llvm.umul.with.overflow.i32(i32 undef, i32 undef)

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

 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %rext_8 = sext <2 x i16> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_9 = zext <2 x i16> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %rext_a = sext <2 x i32> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_b = zext <2 x i32> undef to <2 x i64>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i32i8 = trunc <4 x i32> undef to <4 x i8>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i32i16 = trunc <4 x i32> undef to <4 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i16i8 = trunc <4 x i16> undef to <4 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tv8i32i8 = trunc <8 x i32> undef to <8 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tv8i32i16 = trunc <8 x i32> undef to <8 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %tv8i32i8 = trunc <8 x i32> undef to <8 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %tv8i32i16 = trunc <8 x i32> undef to <8 x i16>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv8i16i8 = trunc <8 x i16> undef to <8 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %tv16i32i8 = trunc <16 x i32> undef to <16 x i8>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %tv16i32i16 = trunc <16 x i32> undef to <16 x i16>
-; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %tv16i16i8 = trunc <16 x i16> undef to <16 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i32i8 = trunc <16 x i32> undef to <16 x i8>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i32i16 = trunc <16 x i32> undef to <16 x i16>
+; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i16i8 = trunc <16 x i16> undef to <16 x i8>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r80df = fptrunc double undef to float
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r81df = fptrunc <2 x double> undef to <2 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r82df = fptrunc <4 x double> undef to <4 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %r83df = fptrunc <8 x double> undef to <8 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %r84df = fptrunc <16 x double> undef to <16 x float>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r80dh = fptrunc double undef to half
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r81dh = fptrunc <2 x double> undef to <2 x half>
 ; CHECK-MVE-RECIP-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r82dh = fptrunc <4 x double> undef to <4 x half>

 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_8 = sext <2 x i16> undef to <2 x i64>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_9 = zext <2 x i16> undef to <2 x i64>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_a = sext <2 x i32> undef to <2 x i64>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_b = zext <2 x i32> undef to <2 x i64>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i32i8 = trunc <4 x i32> undef to <4 x i8>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i32i16 = trunc <4 x i32> undef to <4 x i16>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv4i16i8 = trunc <4 x i16> undef to <4 x i8>
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tv8i32i8 = trunc <8 x i32> undef to <8 x i8>
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tv8i32i16 = trunc <8 x i32> undef to <8 x i16>
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %tv8i32i8 = trunc <8 x i32> undef to <8 x i8>
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %tv8i32i16 = trunc <8 x i32> undef to <8 x i16>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %tv8i16i8 = trunc <8 x i16> undef to <8 x i8>
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tv16i32i8 = trunc <16 x i32> undef to <16 x i8>
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tv16i32i16 = trunc <16 x i32> undef to <16 x i16>
-; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tv16i16i8 = trunc <16 x i16> undef to <16 x i8>
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i32i8 = trunc <16 x i32> undef to <16 x i8>
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i32i16 = trunc <16 x i32> undef to <16 x i16>
+; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %tv16i16i8 = trunc <16 x i16> undef to <16 x i8>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r80df = fptrunc double undef to float
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r81df = fptrunc <2 x double> undef to <2 x float>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r82df = fptrunc <4 x double> undef to <4 x float>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %r83df = fptrunc <8 x double> undef to <8 x float>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %r84df = fptrunc <16 x double> undef to <16 x float>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r80dh = fptrunc double undef to half
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %r81dh = fptrunc <2 x double> undef to <2 x half>
 ; CHECK-MVE-SIZE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %r82dh = fptrunc <4 x double> undef to <4 x half>

llvm/test/Analysis/CostModel/ARM/mve-gather-scatter-cost.ll

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x i16*>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext4 = zext <8 x i16> %ind16 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i16, i16* %base, <8 x i32> %indzext4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indtrunc = trunc <8 x i32> %ind32 to <8 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %indtrunc = trunc <8 x i32> %ind32 to <8 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %indtrunc, <8 x i16*> %gep4, i32 2, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep4, i32 2, <8 x i1> %mask, <8 x i16> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %ressext = sext <8 x i16> %res to <8 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %restrunc = trunc <8 x i32> %ressext to <8 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %restrunc = trunc <8 x i32> %ressext to <8 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %restrunc, <8 x i16*> %gep4, i32 4, <8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   ; no offset ext
   %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
   %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
   call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
 

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <16 x i32> %indzext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <16 x i16*> %gepbs to <16 x i8*>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 528 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext4 = zext <16 x i8> %ind8 to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i8, i8* %base, <16 x i32> %indzext
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indtrunc = trunc <16 x i32> %ind32 to <16 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %indtrunc = trunc <16 x i32> %ind32 to <16 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %indtrunc, <16 x i8*> %gep4, i32 2, <16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   ; no offset ext
   %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
   %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
   call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)