/**
* 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 brcb.asc
 * \brief
 */

#include "acl/acl.h"
#include "data_utils.h"
#include "kernel_operator.h"
class KernelBrcb {
public:
    __aicore__ inline KernelBrcb()
    {}
    __aicore__ inline void Init(__gm__ uint8_t *x, __gm__ uint8_t *y, AscendC::TPipe* pipeIn)
    {
      pipe = pipeIn;
      x_gm.SetGlobalBuffer(reinterpret_cast<__gm__ uint16_t *>(x));
      y_gm.SetGlobalBuffer(reinterpret_cast<__gm__ uint16_t *>(y));
      pipe->InitBuffer(vecIn, 1, 16 * sizeof(uint16_t));
      pipe->InitBuffer(vecOut, 1, 256 * sizeof(uint16_t));
    }
    __aicore__ inline void Process()
    {
      CopyIn();
      Compute();
      CopyOut();
    }
    __aicore__ inline void CopyIn()
    {
      auto x_buf = vecIn.AllocTensor<uint16_t>();
      AscendC::DataCopy(x_buf, x_gm, 16);
      vecIn.EnQue(x_buf);
    }
    __aicore__ inline void Compute()
    {
      auto x_buf = vecIn.DeQue<uint16_t>();
      auto y_buf = vecOut.AllocTensor<uint16_t>();
      AscendC::Brcb(y_buf, x_buf, 2, {1,8});
      vecOut.EnQue(y_buf);
      vecIn.FreeTensor(x_buf);
    }
    __aicore__ inline void CopyOut()
    {
      auto y_buf = vecOut.DeQue<uint16_t>();
      AscendC::DataCopy(y_gm, y_buf, 256);
      vecOut.FreeTensor(y_buf);
    }
private:
    AscendC::GlobalTensor<uint16_t> x_gm;
    AscendC::GlobalTensor<uint16_t> y_gm;
    AscendC::TPipe* pipe;
    AscendC::TQue<AscendC::TPosition::VECIN, 1> vecIn;
    AscendC::TQue<AscendC::TPosition::VECOUT, 1> vecOut;
};

__global__ __aicore__ void brcb_custom(GM_ADDR x, GM_ADDR y)
{
  KERNEL_TASK_TYPE_DEFAULT(KERNEL_TYPE_AIV_ONLY);
  KernelBrcb op;
  AscendC::TPipe pipe;
  op.Init(x, y, &pipe);
  op.Process();
}

int32_t main(int32_t argc, char* argv[]) 
{
  size_t inputByteSize = 16 * sizeof(uint16_t);
  size_t outputByteSize = 256 * sizeof(uint16_t);

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

  uint8_t *xHost, *outHost;
  uint8_t *xDevice, *outDevice;

  aclrtMallocHost((void **)(&xHost), inputByteSize);
  aclrtMallocHost((void **)(&outHost), outputByteSize);
  aclrtMalloc((void **)&xDevice, inputByteSize, ACL_MEM_MALLOC_HUGE_FIRST);
  aclrtMalloc((void **)&outDevice, outputByteSize, ACL_MEM_MALLOC_HUGE_FIRST);

  ReadFile("./input/input_x.bin", inputByteSize, xHost, inputByteSize);
  aclrtMemcpy(xDevice, inputByteSize, xHost, inputByteSize,
              ACL_MEMCPY_HOST_TO_DEVICE);
  brcb_custom<<<1, nullptr, stream>>>(xDevice, outDevice);
  aclrtSynchronizeStream(stream);

  aclrtMemcpy(outHost, outputByteSize, outDevice, outputByteSize,
              ACL_MEMCPY_DEVICE_TO_HOST);
  WriteFile("./output/output.bin", outHost, outputByteSize);

  aclrtFree(xDevice);
  aclrtFree(outDevice);
  aclrtFreeHost(xHost);
  aclrtFreeHost(outHost);

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

  return 0;
}