[AArch64] Basic vector bswap costs

[dmgreen]

Summary

This adds some basic vector bswap costs, providing the type is supported.

[SjoerdMeijer]

Yeah, this looks a lot better to me.

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

case Intrinsic::abs: {
     static const auto ValidAbsTys = {MVT::v8i8,  MVT::v16i8, MVT::v4i16,
                                      MVT::v8i16, MVT::v2i32, MVT::v4i32,
                                      MVT::v2i64};
     auto LT = getTypeLegalizationCost(RetTy);
     if (any_of(ValidAbsTys, [&LT](MVT M) { return M == LT.second; }))
       return LT.first;
     break;
   }
+  case Intrinsic::bswap: {
+    static const auto ValidAbsTys = {MVT::v4i16, MVT::v8i16, MVT::v2i32,
+                                     MVT::v4i32, MVT::v2i64};
+    auto LT = getTypeLegalizationCost(RetTy);
+    if (any_of(ValidAbsTys, [&LT](MVT M) { return M == LT.second; }) &&
+        LT.second.getScalarSizeInBits() == RetTy->getScalarSizeInBits())
+      return LT.first;
+    break;
+  }
   case Intrinsic::experimental_stepvector: {
     InstructionCost Cost = 1; // Cost of the `index' instruction
     auto LT = getTypeLegalizationCost(RetTy);
     // Legalisation of illegal vectors involves an `index' instruction plus
     // (LT.first - 1) vector adds.
     if (LT.first > 1) {
       Type *LegalVTy = EVT(LT.second).getTypeForEVT(RetTy->getContext());
       InstructionCost AddCost =

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

;
   %b16 = call i16 @llvm.bswap.i16(i16 undef)
   %b32 = call i32 @llvm.bswap.i32(i32 undef)
   %b64 = call i64 @llvm.bswap.i64(i64 undef)
   ret void
 }
 
 define void @neon() {
 ; CHECK-LABEL: 'neon'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %v4i48 = call <4 x i48> @llvm.bswap.v4i48(<4 x i48> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %v4i16 = call <4 x i16> @llvm.bswap.v4i16(<4 x i16> undef)
   %v8i16 = call <8 x i16> @llvm.bswap.v8i16(<8 x i16> undef)
   %v16i16 = call <16 x i16> @llvm.bswap.v16i16(<16 x i16> undef)
   %v2i32 = call <2 x i32> @llvm.bswap.v2i32(<2 x i32> undef)
   %v4i32 = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> undef)
   %v8i32 = call <8 x i32> @llvm.bswap.v8i32(<8 x i32> undef)
   %v2i64 = call <2 x i64> @llvm.bswap.v2i64(<2 x i64> undef)
   %v4i64 = call <4 x i64> @llvm.bswap.v4i64(<4 x i64> undef)
 
   %v3i32 = call <3 x i32> @llvm.bswap.v3i32(<3 x i32> undef)
   %v4i48 = call <4 x i48> @llvm.bswap.v4i48(<4 x i48> undef)
   ret void
 }