/**
 * Copyright (c) 2025 Huawei Technologies Co., Ltd.
 * This program is free software, you can redistribute it and/or modify it under the terms and conditions of
 * CANN Open Software License Agreement Version 2.0 (the "License").
 * Please refer to the License for details. You may not use this file except in compliance with the License.
 * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
 * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
 * See LICENSE in the root of the software repository for the full text of the License.
 */

#include "elewise/kernel/elewise_kernel.h"

using AddOpTraits = ATVC::OpTraits<ATVC::OpInputs<DTYPE_X, DTYPE_Y>, ATVC::OpOutputs<DTYPE_Z>>;

template <typename Traits>
struct AddComputeFunc {
    template <typename T>
    __aicore__ inline void operator()(AscendC::LocalTensor<T> x, AscendC::LocalTensor<T> y, AscendC::LocalTensor<T> z)
    {
        AscendC::Add(z, x, y, z.GetSize());
    }
};

extern "C" __global__ __aicore__ void add_custom(GM_ADDR x, GM_ADDR y, GM_ADDR z, GM_ADDR workspace, GM_ADDR tiling)
{
    KERNEL_TASK_TYPE_DEFAULT(KERNEL_TYPE_AIV_ONLY);
    REGISTER_TILING_DEFAULT(ATVC::EleWiseParam);
    GET_TILING_DATA(param, tiling);
    auto op = ATVC::Kernel::EleWiseOpTemplate<AddComputeFunc<AddOpTraits>>();
    op.Run(x, y, z, &param);
}