[AArch64][CostModel] getCastInstrCost

[samparker]

Summary

Pass the instruction to the base implementation.

[dmgreen]

Are there costmodel tests for these? If not can you copy the ones over from ARM?

[samparker]

I copied over the tests in https://reviews.llvm.org/rG751da4d596ea, and this patch doesn't change the results.

[dmgreen]

Is that missing the load_extends tests? Are they the same?

[samparker]

Bingo. Cheers Dave, with those tests ported over it shows some differences.

[dmgreen]

They do look like they should be free to me.

LGTM.

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

if (isWideningInstruction(Dst, SingleUser->getOpcode(), Operands)) {
           return 0;
     }
   }
 
   EVT SrcTy = TLI->getValueType(DL, Src);
   EVT DstTy = TLI->getValueType(DL, Dst);
 
   if (!SrcTy.isSimple() || !DstTy.isSimple())
-    return BaseT::getCastInstrCost(Opcode, Dst, Src, CostKind);
+    return BaseT::getCastInstrCost(Opcode, Dst, Src, CostKind, I);
 
   static const TypeConversionCostTblEntry
   ConversionTbl[] = {
     { ISD::TRUNCATE, MVT::v4i16, MVT::v4i32,  1 },
     { ISD::TRUNCATE, MVT::v4i32, MVT::v4i64,  0 },
     { ISD::TRUNCATE, MVT::v8i8,  MVT::v8i32,  3 },
     { ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 6 },
 
ConversionTbl[] = {
     { ISD::FP_TO_UINT, MVT::v2i8,  MVT::v2f64, 2 },
   };
 
   if (const auto *Entry = ConvertCostTableLookup(ConversionTbl, ISD,
                                                  DstTy.getSimpleVT(),
                                                  SrcTy.getSimpleVT()))
     return Entry->Cost;
 
-  return BaseT::getCastInstrCost(Opcode, Dst, Src, CostKind);
+  return BaseT::getCastInstrCost(Opcode, Dst, Src, CostKind, I);
 }
 
 int AArch64TTIImpl::getExtractWithExtendCost(unsigned Opcode, Type *Dst,
                                              VectorType *VecTy,
                                              unsigned Index) {
 
   // Make sure we were given a valid extend opcode.
   assert((Opcode == Instruction::SExt || Opcode == Instruction::ZExt) &&

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

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi16 = load i16, i16* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadi32 = load i32, i32* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %loadv2i8 = load <2 x i8>, <2 x i8>* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %loadv4i8 = load <4 x i8>, <4 x i8>* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv8i8 = load <8 x i8>, <8 x i8>* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i16 = load <2 x i16>, <2 x i16>* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv4i16 = load <4 x i16>, <4 x i16>* undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %loadv2i32 = load <2 x i32>, <2 x i32>* undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r0 = sext i8 %loadi8 to i16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r1 = zext i8 %loadi8 to i16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r2 = sext i8 %loadi8 to i32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r3 = zext i8 %loadi8 to i32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i8 %loadi8 to i64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r0 = sext i8 %loadi8 to i16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r1 = zext i8 %loadi8 to i16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r2 = sext i8 %loadi8 to i32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r3 = zext i8 %loadi8 to i32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r4 = sext i8 %loadi8 to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r5 = zext i8 %loadi8 to i64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r6 = sext i16 %loadi16 to i32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r7 = zext i16 %loadi16 to i32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r8 = sext i16 %loadi16 to i64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r6 = sext i16 %loadi16 to i32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r7 = zext i16 %loadi16 to i32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r8 = sext i16 %loadi16 to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r9 = zext i16 %loadi16 to i64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r11 = zext i32 %loadi32 to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>

llvm/test/Transforms/SLPVectorizer/AArch64/horizontal.ll

 }
 
 ; YAML:      --- !Passed
 ; YAML-NEXT: Pass:            slp-vectorizer
 ; YAML-NEXT: Name:            VectorizedHorizontalReduction
 ; YAML-NEXT: Function:        test_unrolled_select
 ; YAML-NEXT: Args:
 ; YAML-NEXT:   - String:          'Vectorized horizontal reduction with cost '
-; YAML-NEXT:   - Cost:            '-47'
+; YAML-NEXT:   - Cost:            '-31'
 ; YAML-NEXT:   - String:          ' and with tree size '
 ; YAML-NEXT:   - TreeSize:        '10'
 
 define i32 @test_unrolled_select(i8* noalias nocapture readonly %blk1, i8* noalias nocapture readonly %blk2, i32 %lx, i32 %h, i32 %lim) #0 {
 ; CHECK-LABEL: @test_unrolled_select(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP_43:%.*]] = icmp sgt i32 [[H:%.*]], 0
 ; CHECK-NEXT:    br i1 [[CMP_43]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]