/**
 * 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 <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_qr.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      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 shapeSize = 1;
  for (auto i : shape) {
    shapeSize *= i;
  }
  return shapeSize;
}

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_ND,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int PrepareInputAndOutput(
    std::vector<int64_t>& selfShape, std::vector<int64_t>& qShape, std::vector<int64_t>& rShape, void** selfDeviceAddr,
    aclTensor** self, void** qDeviceAddr, aclTensor** q, void** rDeviceAddr, aclTensor** r)
{
  std::vector<float> selfHostData = {1, 2, 3, 4};
  std::vector<float> qHostData = {0, 0, 0, 0};
  std::vector<float> rHostData = {0, 0, 0, 0};
  // 创建self aclTensor
  auto ret = CreateAclTensor(selfHostData, selfShape, selfDeviceAddr, aclDataType::ACL_FLOAT, self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建q,r aclTensor
  ret = CreateAclTensor(qHostData, qShape, qDeviceAddr, aclDataType::ACL_FLOAT, q);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(rHostData, rShape, rDeviceAddr, aclDataType::ACL_FLOAT, r);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  return ACL_SUCCESS;
}

void ReleaseTensorAndScalar(aclTensor* self, aclTensor* q, aclTensor* r)
{
    aclDestroyTensor(self);
    aclDestroyTensor(q);
    aclDestroyTensor(r);
}

void ReleaseDevice(
    void* selfDeviceAddr, void* qDeviceAddr, void* rDeviceAddr, uint64_t workspaceSize, void* workspaceAddr, aclrtStream stream,
    int32_t deviceId)
{
    aclrtFree(selfDeviceAddr);
    aclrtFree(qDeviceAddr);
    aclrtFree(rDeviceAddr);
    if (workspaceSize > 0) {
      aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
}

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 = Init(deviceId, &stream);
  CHECK_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> selfShape = {2, 2};
  bool some = false;
  std::vector<int64_t> qShape = {2, 2};
  std::vector<int64_t> rShape = {2, 2};
  void* selfDeviceAddr = nullptr;
  void* qDeviceAddr = nullptr;
  void* rDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* q = nullptr;
  aclTensor* r = nullptr;  
  
  ret = PrepareInputAndOutput(selfShape, qShape, rShape, &selfDeviceAddr, &self, &qDeviceAddr, &q, &rDeviceAddr, &r);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. 调用CANN算子库API，需要修改为具体的Api名称
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // 调用aclnnQr第一段接口
  ret = aclnnQrGetWorkspaceSize(self, some, q, r, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnQrGetWorkspaceSize 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;
  if (workspaceSize > 0) {
    ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
  }
  // 调用aclnnQr第二段接口
  ret = aclnnQr(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnQr 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_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(qShape);
  std::vector<float> resultQData(size, 0);
  ret = aclrtMemcpy(resultQData.data(), resultQData.size() * sizeof(resultQData[0]), qDeviceAddr,
                    size * sizeof(resultQData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result Q from device to host failed. ERROR: %d\n", ret); return ret);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result Q[%ld] is: %f\n", i, resultQData[i]);
  }

  std::vector<float> resultRData(size, 0);
  ret = aclrtMemcpy(resultRData.data(), resultRData.size() * sizeof(resultRData[0]), rDeviceAddr,
                    size * sizeof(resultRData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result R from device to host failed. ERROR: %d\n", ret); return ret);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result R[%ld] is: %f\n", i, resultRData[i]);
  }

  // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
  ReleaseTensorAndScalar(self, q, r);

  // 7. 释放device资源，需要根据具体API的接口定义参数
  ReleaseDevice(selfDeviceAddr, qDeviceAddr, rDeviceAddr, workspaceSize, workspaceAddr, stream, deviceId);

  return 0;
}