/**
* 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.
*/

/*!
 * \file add.cpp
 * \brief
 */
#include "kernel_operator.h"
#include "data_utils.h"
#include "tikicpulib.h"

constexpr int32_t TOTAL_LENGTH = 8 * 2048;                            // total length of data
constexpr int32_t USE_CORE_NUM = 8;                                   // num of core used
constexpr int32_t BLOCK_LENGTH = TOTAL_LENGTH / USE_CORE_NUM;         // length computed of each core
constexpr int32_t TILE_NUM = 8;                                       // split data into 1 tiles for each core
constexpr int32_t BUFFER_NUM = 2;                                     // tensor num for each queue
constexpr int32_t TILE_LENGTH = BLOCK_LENGTH / TILE_NUM / BUFFER_NUM; // separate to 2 parts, due to double buffer
constexpr int32_t OFFSET_LENGTH = 32; // offset length for DumpAccChkPoint
constexpr int32_t DUMP_LENGTH = 32; // dump length

class KernelAdd {
public:
    __aicore__ inline KernelAdd() {}
    __aicore__ inline void Init(GM_ADDR x, GM_ADDR y, GM_ADDR z)
    {
        xGm.SetGlobalBuffer((__gm__ half *)x + BLOCK_LENGTH * AscendC::GetBlockIdx(), BLOCK_LENGTH);
        yGm.SetGlobalBuffer((__gm__ half *)y + BLOCK_LENGTH * AscendC::GetBlockIdx(), BLOCK_LENGTH);
        zGm.SetGlobalBuffer((__gm__ half *)z + BLOCK_LENGTH * AscendC::GetBlockIdx(), BLOCK_LENGTH);
        pipe.InitBuffer(inQueueX, BUFFER_NUM, TILE_LENGTH * sizeof(half));
        pipe.InitBuffer(inQueueY, BUFFER_NUM, TILE_LENGTH * sizeof(half));
        pipe.InitBuffer(outQueueZ, BUFFER_NUM, TILE_LENGTH * sizeof(half));
    }
    __aicore__ inline void Process()
    {
        int32_t loopCount = TILE_NUM * BUFFER_NUM;
        for (int32_t i = 0; i < loopCount; i++) {
            CopyIn(i);
            Compute(i);
            CopyOut(i);
        }
    }

private:
    __aicore__ inline void CopyIn(int32_t progress)
    {
        AscendC::LocalTensor<half> xLocal = inQueueX.AllocTensor<half>();
        AscendC::LocalTensor<half> yLocal = inQueueY.AllocTensor<half>();
        AscendC::DataCopy(xLocal, xGm[progress * TILE_LENGTH], TILE_LENGTH);
        AscendC::DataCopy(yLocal, yGm[progress * TILE_LENGTH], TILE_LENGTH);
        inQueueX.EnQue(xLocal);
        inQueueY.EnQue(yLocal);
    }
    __aicore__ inline void Compute(int32_t progress)
    {
        AscendC::LocalTensor<half> xLocal = inQueueX.DeQue<half>();
        AscendC::LocalTensor<half> yLocal = inQueueY.DeQue<half>();
        AscendC::LocalTensor<half> zLocal = outQueueZ.AllocTensor<half>();
        AscendC::Add(zLocal, xLocal, yLocal, TILE_LENGTH);
        outQueueZ.EnQue<half>(zLocal);
        inQueueX.FreeTensor(xLocal);
        inQueueY.FreeTensor(yLocal);
    }
    __aicore__ inline void CopyOut(int32_t progress)
    {
        AscendC::LocalTensor<half> zLocal = outQueueZ.DeQue<half>();
        AscendC::DataCopy(zGm[progress * TILE_LENGTH], zLocal, TILE_LENGTH);
        outQueueZ.FreeTensor(zLocal);
    }

private:
    AscendC::TPipe pipe;
    AscendC::TQue<AscendC::TPosition::VECIN, BUFFER_NUM> inQueueX, inQueueY;
    AscendC::TQue<AscendC::TPosition::VECOUT, BUFFER_NUM> outQueueZ;
    AscendC::GlobalTensor<half> xGm;
    AscendC::GlobalTensor<half> yGm;
    AscendC::GlobalTensor<half> zGm;
};

__global__ __aicore__ void add_custom(GM_ADDR x, GM_ADDR y, GM_ADDR z)
{
    KernelAdd op;
    op.Init(x, y, z);
    op.Process();
}

int32_t main(int32_t argc, char *argv[])
{
    uint32_t numBlocks = 8;
    size_t inputByteSize = 8 * 2048 * sizeof(uint16_t);
    size_t outputByteSize = 8 * 2048 * sizeof(uint16_t);

    uint8_t *x = (uint8_t *)AscendC::GmAlloc(inputByteSize);
    uint8_t *y = (uint8_t *)AscendC::GmAlloc(inputByteSize);
    uint8_t *z = (uint8_t *)AscendC::GmAlloc(outputByteSize);

    ReadFile("./input_x.bin", inputByteSize, x, inputByteSize);
    ReadFile("./input_y.bin", inputByteSize, y, inputByteSize);

    AscendC::SetKernelMode(KernelMode::AIV_MODE);
    ICPU_RUN_KF(add_custom, numBlocks, x, y, z); // use this macro for cpu debug

    WriteFile("./output.bin", z, outputByteSize);

    AscendC::GmFree((void *)x);
    AscendC::GmFree((void *)y);
    AscendC::GmFree((void *)z);
    return 0;
}