/**
 * Generates a multi-function with the following parameters:
 * 1. single input (SI) of type In1
 * 2. single input (SI) of type In2
 * 3. single output (SO) of type Out1
 */
template<typename In1, typename In2, typename Out1>
class CustomMF_SI_SI_SO : public MultiFunction {
 private:
  using FunctionT =
      std::function<void(IndexMask, const VArray<In1> &, const VArray<In2> &, MutableSpan<Out1>)>;
  FunctionT function_;
  MFSignature signature_;

 public:
  CustomMF_SI_SI_SO(const char *name, FunctionT function) : function_(std::move(function))
  {
    MFSignatureBuilder signature{name};
    signature.single_input<In1>("In1");
    signature.single_input<In2>("In2");
    signature.single_output<Out1>("Out1");
    signature_ = signature.build();
    this->set_signature(&signature_);
  }

  template<typename ElementFuncT>
  CustomMF_SI_SI_SO(const char *name, ElementFuncT element_fn)
      : CustomMF_SI_SI_SO(name, CustomMF_SI_SI_SO::create_function(element_fn))
  {
  }

  template<typename ElementFuncT> static FunctionT create_function(ElementFuncT element_fn)
  {
    return [=](IndexMask mask,
               const VArray<In1> &in1,
               const VArray<In2> &in2,
               MutableSpan<Out1> out1) {
      /* Devirtualization results in a 2-3x speedup for some simple functions. */
      devirtualize_varray2(in1, in2, [&](const auto &in1, const auto &in2) {
        mask.to_best_mask_type(
            [&](const auto &mask) { execute_SI_SI_SO(element_fn, mask, in1, in2, out1.data()); });
      });
    };
  }

  template<typename ElementFuncT, typename MaskT, typename In1Array, typename In2Array>
  BLI_NOINLINE static void execute_SI_SI_SO(const ElementFuncT &element_fn,
                                            MaskT mask,
                                            const In1Array &in1,
                                            const In2Array &in2,
                                            Out1 *__restrict r_out)
  {
    for (const int64_t i : mask) {
      new (r_out + i) Out1(element_fn(in1[i], in2[i]));
    }
  }

  void call(IndexMask mask, MFParams params, MFContext UNUSED(context)) const override
  {
    const VArray<In1> &in1 = params.readonly_single_input<In1>(0);
    const VArray<In2> &in2 = params.readonly_single_input<In2>(1);
    MutableSpan<Out1> out1 = params.uninitialized_single_output<Out1>(2);
    function_(mask, in1, in2, out1);
  }
};