/**
 * 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.
 */

 /*
 * Below is the operator used for computing the addition of two matrices.
 * This operator allows users to configure the tiling information with placeholders.
 */

#include "kernel_operator.h"

namespace {
    constexpr int32_t USE_CORE_NUM = 8;                                   // num of core used                            
    constexpr int32_t BUFFER_NUM = 2;                                     // tensor num for each queue
}

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)
    {
        this->blockLength = totalLength / USE_CORE_NUM;
        this->tileNum = tileNum;
        if (tileNum == 0) {
            return;
        }
        this->tileLength = this->blockLength / tileNum / BUFFER_NUM;
        xGm.SetGlobalBuffer((__gm__ half *)x + this->blockLength * AscendC::GetBlockIdx(), this->blockLength);
        yGm.SetGlobalBuffer((__gm__ half *)y + this->blockLength * AscendC::GetBlockIdx(), this->blockLength);
        zGm.SetGlobalBuffer((__gm__ half *)z + this->blockLength * AscendC::GetBlockIdx(), this->blockLength);
        pipe.InitBuffer(inQueueX, BUFFER_NUM, this->tileLength * sizeof(half));
        pipe.InitBuffer(inQueueY, BUFFER_NUM, this->tileLength * sizeof(half));
        pipe.InitBuffer(outQueueZ, BUFFER_NUM, this->tileLength * sizeof(half));
    }
    __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)
    {
        AscendC::LocalTensor<half> xLocal = inQueueX.AllocTensor<half>();
        AscendC::LocalTensor<half> yLocal = inQueueY.AllocTensor<half>();
        AscendC::DataCopy(xLocal, xGm[progress * this->tileLength], this->tileLength);
        AscendC::DataCopy(yLocal, yGm[progress * this->tileLength], this->tileLength);
        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, this->tileLength);
        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 * this->tileLength], zLocal, this->tileLength);
        outQueueZ.FreeTensor(zLocal);
    }

private:
    AscendC::TPipe pipe;
    AscendC::TQue<AscendC::QuePosition::VECIN, BUFFER_NUM> inQueueX;
    AscendC::TQue<AscendC::QuePosition::VECIN, BUFFER_NUM> inQueueY;
    AscendC::TQue<AscendC::QuePosition::VECOUT, BUFFER_NUM> outQueueZ;
    AscendC::GlobalTensor<half> xGm;
    AscendC::GlobalTensor<half> yGm;
    AscendC::GlobalTensor<half> 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__ int32_t* tilingLength, __gm__ int32_t* tilingNum)
{
    KernelAdd op;
    uint32_t tileLength = *tilingLength;
    uint32_t tileNum = *tilingNum;
    op.Init(x, y, z, tileLength, tileNum);
    op.Process();
}