// 实现核函数
extern "C" __global__ __aicore__ void add_custom(GM_ADDR x, GM_ADDR y, GM_ADDR z)
{
    // 初始化算子类，算子类提供算子初始化和核心处理等方法
    KernelAdd op;
    // 初始化函数，获取该核函数需要处理的输入输出地址，同时完成必要的内存初始化工作
    op.Init(x, y, z);
    // 核心处理函数，完成算子的数据搬运与计算等核心逻辑
    op.Process();
}

class KernelAdd {
public:
    __aicore__ inline KernelAdd() {}
    __aicore__ inline void Init(GM_ADDR x, GM_ADDR y, GM_ADDR z {}
    __aicore__ inline void Process(){}

private:
    __aicore__ inline void CopyIn(int32_t progress) {}
    __aicore__ inline void Compute(int32_t progress) {}
    __aicore__ inline void CopyOut(int32_t progress){}

private:
    TPipe pipe;
    // create queues for input, in this case depth is equal to buffer num
    TQue<QuePosition::VECIN, BUFFER_NUM> inQueueX, inQueueY;
    // create queue for output, in this case depth is equal to buffer num
    TQue<QuePosition::VECOUT, BUFFER_NUM> outQueueZ;
    GlobalTensor<half> xGm, yGm, zGm;
};

class KernelAdd {
public:
    __aicore__ inline KernelAdd() {}
    __aicore__ inline void Init(GM_ADDR x, GM_ADDR y, GM_ADDR z)
    {
        // get start index for current core, core parallel
        xGm.SetGlobalBuffer((__gm__ half*)x + BLOCK_LENGTH * GetBlockIdx(), BLOCK_LENGTH);
        yGm.SetGlobalBuffer((__gm__ half*)y + BLOCK_LENGTH * GetBlockIdx(), BLOCK_LENGTH);
        zGm.SetGlobalBuffer((__gm__ half*)z + BLOCK_LENGTH * GetBlockIdx(), BLOCK_LENGTH);
        // pipe alloc memory to queue, the unit is Bytes
        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()
    {
        // loop count need to be doubled, due to double buffer
        constexpr int32_t loopCount = TILE_NUM * BUFFER_NUM;
        // tiling strategy, pipeline parallel
        for (int32_t i = 0; i < loopCount; i++) {
            CopyIn(i);
            Compute(i);
            CopyOut(i);
        }
    }

private:
    __aicore__ inline void CopyIn(int32_t progress)
    {
        // alloc tensor from queue memory
        LocalTensor<half> xLocal = inQueueX.AllocTensor<half>();
        LocalTensor<half> yLocal = inQueueY.AllocTensor<half>();
        // copy progress_th tile from global tensor to local tensor
        DataCopy(xLocal, xGm[progress * TILE_LENGTH], TILE_LENGTH);
        DataCopy(yLocal, yGm[progress * TILE_LENGTH], TILE_LENGTH);
        // enque input tensors to VECIN queue
        inQueueX.EnQue(xLocal);
        inQueueY.EnQue(yLocal);
    }
    __aicore__ inline void Compute(int32_t progress)
    {
        // deque input tensors from VECIN queue
        LocalTensor<half> xLocal = inQueueX.DeQue<half>();
        LocalTensor<half> yLocal = inQueueY.DeQue<half>();
        LocalTensor<half> zLocal = outQueueZ.AllocTensor<half>();
        // call Add instr for computation
        Add(zLocal, xLocal, yLocal, TILE_LENGTH);
        // enque the output tensor to VECOUT queue
        outQueueZ.EnQue<half>(zLocal);
        // free input tensors for reuse
        inQueueX.FreeTensor(xLocal);
        inQueueY.FreeTensor(yLocal);
    }
    __aicore__ inline void CopyOut(int32_t progress)
    {
        // deque output tensor from VECOUT queue
        LocalTensor<half> zLocal = outQueueZ.DeQue<half>();
        // copy progress_th tile from local tensor to global tensor
        DataCopy(zGm[progress * TILE_LENGTH], zLocal, TILE_LENGTH);
        // free output tensor for reuse
        outQueueZ.FreeTensor(zLocal);
    }

private:
    TPipe pipe;
    // create queues for input, in this case depth is equal to buffer num
    TQue<QuePosition::VECIN, BUFFER_NUM> inQueueX, inQueueY;
    // create queue for output, in this case depth is equal to buffer num
    TQue<QuePosition::VECOUT, BUFFER_NUM> outQueueZ;
    GlobalTensor<half> xGm, yGm, zGm;
};

ICPU_RUN_KF(add_custom, blockDim, x, y, z); // use this macro for cpu debug

#ifndef __CCE_KT_TEST__
//call of kernel function
void add_custom_do(uint32_t blockDim, void* l2ctrl, void* stream, uint8_t* x, uint8_t* y, uint8_t* z);
{
     add_custom<<<blockDim, l2ctrl, stream>>> (x, y, z);
}
#endif