/**
* 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 copy.asc
 * \brief
 */

#include "acl/acl.h"
#include "data_utils.h"
#include "kernel_operator.h"
class KernelCopy {
public:
    __aicore__ inline KernelCopy() {}
    __aicore__ inline void Init(__gm__ uint8_t* srcGm, __gm__ uint8_t* dstGm, AscendC::TPipe* pipeIn)
    {
        pipe = pipeIn;
        srcGlobal.SetGlobalBuffer((__gm__ int32_t*)srcGm);
        dstGlobal.SetGlobalBuffer((__gm__ int32_t*)dstGm);
        pipe->InitBuffer(inQueueSrc, 1, 512 * sizeof(int32_t));
        pipe->InitBuffer(outQueueDst, 1, 512 * sizeof(int32_t));
    }
    __aicore__ inline void Process()
    {
        CopyIn();
        Compute();
        CopyOut();
    }
private:
    __aicore__ inline void CopyIn()
    {
        AscendC::LocalTensor<int32_t> srcLocal = inQueueSrc.AllocTensor<int32_t>();
        AscendC::DataCopy(srcLocal, srcGlobal, 512);
        inQueueSrc.EnQue(srcLocal);
    }
    __aicore__ inline void Compute()
    {
        AscendC::LocalTensor<int32_t> srcLocal = inQueueSrc.DeQue<int32_t>();
        AscendC::LocalTensor<int32_t> dstLocal = outQueueDst.AllocTensor<int32_t>();
        uint64_t mask = 64;
        AscendC::Copy(dstLocal, srcLocal, mask, 8, { 1, 1, 8, 8 });
        outQueueDst.EnQue<int32_t>(dstLocal);
        inQueueSrc.FreeTensor(srcLocal);
    }
    __aicore__ inline void CopyOut()
    {
        AscendC::LocalTensor<int32_t> dstLocal = outQueueDst.DeQue<int32_t>();
        AscendC::DataCopy(dstGlobal, dstLocal, 512);
        outQueueDst.FreeTensor(dstLocal);
    }
private:
    AscendC::TPipe* pipe;
    AscendC::TQue<AscendC::TPosition::VECIN, 1> inQueueSrc;
    AscendC::TQue<AscendC::TPosition::VECOUT, 1> outQueueDst;
    AscendC::GlobalTensor<int32_t> srcGlobal, dstGlobal;
};

__global__ __aicore__ void copy_custom(GM_ADDR x, GM_ADDR z) 
{
    KERNEL_TASK_TYPE_DEFAULT(KERNEL_TYPE_AIV_ONLY);
    AscendC::TPipe pipe;
    KernelCopy op;
    op.Init(x, z, &pipe);
    op.Process();
}

int32_t main(int32_t argc, char* argv[]) 
{
    uint32_t numBlocks = 1;
    size_t inputByteSize = 512 * sizeof(uint32_t);
    size_t outputByteSize = inputByteSize;

    int32_t deviceId = 0;
    aclrtSetDevice(deviceId);
    aclrtStream stream = nullptr;
    aclrtCreateStream(&stream);

    uint8_t *xHost, *zHost;
    uint8_t *xDevice, *zDevice;

    aclrtMallocHost((void **)(&xHost), inputByteSize);
    aclrtMallocHost((void **)(&zHost), outputByteSize);
    aclrtMalloc((void **)&xDevice, inputByteSize, ACL_MEM_MALLOC_HUGE_FIRST);
    aclrtMalloc((void **)&zDevice, outputByteSize, ACL_MEM_MALLOC_HUGE_FIRST);

    ReadFile("./input/input_x.bin", inputByteSize, xHost, inputByteSize);

    aclrtMemcpy(xDevice, inputByteSize, xHost, inputByteSize,
                ACL_MEMCPY_HOST_TO_DEVICE);

    copy_custom<<<numBlocks, nullptr, stream>>>(xDevice, zDevice);
    aclrtSynchronizeStream(stream);

    aclrtMemcpy(zHost, outputByteSize, zDevice, outputByteSize,
                ACL_MEMCPY_DEVICE_TO_HOST);
    WriteFile("./output/output.bin", zHost, outputByteSize);

    aclrtFree(xDevice);
    aclrtFree(zDevice);
    aclrtFreeHost(xHost);
    aclrtFreeHost(zHost);

    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();

    return 0;
}