/**
 * 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.
 *
 * Function : z = x + y
 * This sample is a very basic sample that implements vector add on Ascend plaform.
 */
#include "kernel_operator.h"
#include "include/adv_api/matmul/matmul_intf.h"
using namespace AscendC;
using namespace matmul;

constexpr int32_t BUFFER_NUM = 2;

class KernelAdd {
public:
    __aicore__ inline KernelAdd() {}
    __aicore__ inline void Init(GM_ADDR x, GM_ADDR y, GM_ADDR z, uint32_t totalLength, uint32_t tileNum)
    {
        ASSERT(GetBlockNum() != 0 && "block dim can not be zero!");
        this->blockLength = totalLength / GetBlockNum();
        this->tileNum = tileNum;
        ASSERT(tileNum != 0 && "tile num can not be zero!");
        this->tileLength = this->blockLength / tileNum / BUFFER_NUM;

        xGm.SetGlobalBuffer((__gm__ DTYPE_X*)x + this->blockLength * GetBlockIdx(), this->blockLength);
        yGm.SetGlobalBuffer((__gm__ DTYPE_Y*)y + this->blockLength * GetBlockIdx(), this->blockLength);
        zGm.SetGlobalBuffer((__gm__ DTYPE_Z*)z + this->blockLength * GetBlockIdx(), this->blockLength);
        pipe.InitBuffer(inQueueX, BUFFER_NUM, this->tileLength * sizeof(DTYPE_X));
        pipe.InitBuffer(inQueueY, BUFFER_NUM, this->tileLength * sizeof(DTYPE_Y));
        pipe.InitBuffer(outQueueZ, BUFFER_NUM, this->tileLength * sizeof(DTYPE_Z));
    }
    __aicore__ inline void Process()
    {
        int32_t loopCount = this->tileNum * BUFFER_NUM;
        for (int32_t i = 0; i < loopCount; i++) {
            CopyIn(i);
            Compute(i);
            CopyOut(i);
        }
    }

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

private:
    TPipe pipe;
    TQue<TPosition::VECIN, BUFFER_NUM> inQueueX, inQueueY;
    TQue<TPosition::VECOUT, BUFFER_NUM> outQueueZ;
    TBufPool<TPosition::VECCALC> a, b, c;

    GlobalTensor<DTYPE_X> xGm;
    GlobalTensor<DTYPE_Y> yGm;
    GlobalTensor<DTYPE_Z> zGm;
    uint32_t blockLength;
    uint32_t tileNum;
    uint32_t tileLength;
};

extern "C" __global__ __aicore__ void add_custom(GM_ADDR x, GM_ADDR y, GM_ADDR z, GM_ADDR workspace, GM_ADDR tiling)
{
    if ASCEND_IS_AIC {
        return;
    }
    GET_TILING_DATA(tilingData, tiling);
    KernelAdd op;
    op.Init(
        x, y, z, tilingData.D_in_tiling.C_in_D.B_in_C.A_in_B.totalLength,
        tilingData.D_in_tiling.C_in_D.B_in_C.A_in_B.tileNum);
    if (TILING_KEY_IS(1)) {
        op.Process();
    } else if (TILING_KEY_IS(2)) {
        op.Process();
    }
}