[AArch64] Add vector saturating add intrinsic costs

This adds sadd.sat, uadd.sat, ssub.sat and usub.sat costs for AArch64,
similar to how they were recently added for ARM.

Differential Revision: https://reviews.llvm.org/D95292

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -235,6 +235,22 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return LT.first;
     break;
   }
+  case Intrinsic::sadd_sat:
+  case Intrinsic::ssub_sat:
+  case Intrinsic::uadd_sat:
+  case Intrinsic::usub_sat: {
+    static const auto ValidSatTys = {MVT::v8i8,  MVT::v16i8, MVT::v4i16,
+                                     MVT::v8i16, MVT::v2i32, MVT::v4i32,
+                                     MVT::v2i64};
+    auto LT = TLI->getTypeLegalizationCost(DL, RetTy);
+    // This is a base cost of 1 for the vadd, plus 3 extract shifts if we
+    // need to extend the type, as it uses shr(qadd(shl, shl)).
+    unsigned Instrs =
+        LT.second.getScalarSizeInBits() == RetTy->getScalarSizeInBits() ? 1 : 4;
+    if (any_of(ValidSatTys, [&LT](MVT M) { return M == LT.second; }))
+      return LT.first * Instrs;
+    break;
+  }
   default:
     break;
   }