/**
 * 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.
 */

#include <iostream>
#include <memory>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_convolution.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)

#define CHECK_FREE_RET(cond, return_expr) \
  do {                                    \
    if (!(cond)) {                        \
      Finalize(deviceId, stream);         \
      return_expr;                        \
    }                                     \
  } while (0)

#define LOG_PRINT(message, ...)      \
  do {                               \
    printf(message, ##__VA_ARGS__);  \
  } while (0)

int64_t GetShapeSize(const std::vector<int64_t>& shape) {
  int64_t shape_size = 1;
  for (auto i: shape) {
    shape_size *= i;
  }
  return shape_size;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // 固定写法，资源初始化
  auto ret = aclInit(nullptr);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
  ret = aclrtSetDevice(deviceId);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
  ret = aclrtCreateStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
  return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
  auto size = GetShapeSize(shape) * sizeof(T);
  // 调用aclrtMalloc申请device侧内存
  auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);

  // 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
  ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

  // 计算连续tensor的strides
  std::vector<int64_t> strides(shape.size(), 1);
  for (int64_t i = shape.size() - 2; i >= 0; i--) {
    strides[i] = shape[i + 1] * strides[i + 1];
  }

  // 调用aclCreateTensor接口创建aclTensor
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_NCL,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

void Finalize(int32_t deviceId, aclrtStream& stream)
{
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
}

int aclnnConvolutionTest(int32_t deviceId, aclrtStream& stream)
{
  auto ret = Init(deviceId, &stream);
  // check根据自己的需要处理
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. 构造输入与输出，需要根据API的接口自定义构造
  std::vector<int64_t> shapeInput = {1, 16, 2};
  std::vector<int64_t> shapeWeight = {16, 16, 2};
  std::vector<int64_t> shapeResult = {1, 16, 3};
  std::vector<int64_t> convStrides;
  std::vector<int64_t> convPads;
  std::vector<int64_t> convOutPads;
  std::vector<int64_t> convDilations;

  void* deviceDataA = nullptr;
  void* deviceDataB = nullptr;
  void* deviceDataResult = nullptr;

  aclTensor* input = nullptr;
  aclTensor* weight = nullptr;
  aclTensor* result = nullptr;
  std::vector<float> inputData(GetShapeSize(shapeInput), 1);
  std::vector<float> weightData(GetShapeSize(shapeWeight), 1);
  std::vector<float> outputData(GetShapeSize(shapeResult), 1);
  convStrides = {1};
  convPads = {0};
  convOutPads = {0};
  convDilations = {1};

  // 创建input aclTensor
  ret = CreateAclTensor(inputData, shapeInput, &deviceDataA, aclDataType::ACL_FLOAT, &input);
  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> inputTensorPtr(input, aclDestroyTensor);
  std::unique_ptr<void, aclError (*)(void *)> deviceDataAPtr(deviceDataA, aclrtFree);
  CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

  // 创建weight aclTensor
  ret = CreateAclTensor(weightData, shapeWeight, &deviceDataB, aclDataType::ACL_FLOAT, &weight);
  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> weightTensorPtr(weight, aclDestroyTensor);
  std::unique_ptr<void, aclError (*)(void *)> deviceDataBPtr(deviceDataB, aclrtFree);
  CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

  // 创建out aclTensor
  ret = CreateAclTensor(outputData, shapeResult, &deviceDataResult, aclDataType::ACL_FLOAT, &result);
  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> outputTensorPtr(result, aclDestroyTensor);
  std::unique_ptr<void, aclError (*)(void *)> deviceDataResultPtr(deviceDataResult, aclrtFree);
  CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);

  aclIntArray *strides = aclCreateIntArray(convStrides.data(), 1);
  std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> stridesPtr(strides, aclDestroyIntArray);
  CHECK_FREE_RET(strides != nullptr, return ACL_ERROR_INTERNAL_ERROR);
  aclIntArray *pads = aclCreateIntArray(convPads.data(), 1);
  std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> padsPtr(pads, aclDestroyIntArray);
  CHECK_FREE_RET(pads != nullptr, return ACL_ERROR_INTERNAL_ERROR);
  aclIntArray *outPads = aclCreateIntArray(convOutPads.data(), 1);
  std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> outPadsPtr(outPads, aclDestroyIntArray);
  CHECK_FREE_RET(outPads != nullptr, return ACL_ERROR_INTERNAL_ERROR);
  aclIntArray *dilations = aclCreateIntArray(convDilations.data(), 1);
  std::unique_ptr<aclIntArray, aclnnStatus (*)(const aclIntArray *)> dilationsPtr(dilations, aclDestroyIntArray);
  CHECK_FREE_RET(dilations != nullptr, return ACL_ERROR_INTERNAL_ERROR);

  // 3. 调用CANN算子库API，需要修改为具体的API
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // 调用aclnnConvolution第一段接口
  ret = aclnnConvolutionGetWorkspaceSize(input, weight, nullptr, strides, pads, dilations, true, outPads, 1, result, 0,
                                         &workspaceSize, &executor);
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolutionGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存
  void* workspaceAddr = nullptr;
  std::unique_ptr<void, aclError (*)(void *)> workspaceAddrPtr(nullptr, aclrtFree);
  if (workspaceSize > 0) {
    ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    workspaceAddrPtr.reset(workspaceAddr);
  }
  // 调用aclnnConvolution第二段接口
  ret = aclnnConvolution(workspaceAddr, workspaceSize, executor, stream);
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolution failed. ERROR: %d\n", ret); return ret);

  // 4. （固定写法）同步等待任务执行结束
  ret = aclrtSynchronizeStream(stream);
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. 获取输出的值，将device侧内存上的结果拷贝至host侧，需要根据具体API的接口定义修改
  auto size = GetShapeSize(shapeResult);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), deviceDataResult,
                    size * sizeof(float), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
  int64_t printSize = size > 10 ? 10 : size;
  for (int64_t i = 0; i < printSize; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }

  return ACL_SUCCESS;
}

int main() {
  // 1. （固定写法）device/stream初始化，参考acl API手册
  // 根据自己的实际device填写deviceId
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = aclnnConvolutionTest(deviceId, stream);
  CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvolutionTest failed. ERROR: %d\n", ret); return ret);

  Finalize(deviceId, stream);
  return 0;
}