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

#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;
}

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

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 main() {
  // 1. （固定写法）device/stream初始化，参考acl API
  // 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
  // input
  std::vector<float> gradHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> varHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> mHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> vHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> sHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> stepHostData = {10, 10, 10, 10};
  std::vector<int64_t> inputShape = {2, 2, 2};
  std::vector<int64_t> stepShape = {2, 2};
  void *gradDeviceAddr = nullptr;
  void *varDeviceAddr = nullptr;
  void *mDeviceAddr = nullptr;
  void *vDeviceAddr = nullptr;
  void *sDeviceAddr = nullptr;
  void *stepDeviceAddr = nullptr;
  aclTensor *grad = nullptr;
  aclTensor *var = nullptr;
  aclTensor *m = nullptr;
  aclTensor *v = nullptr;
  aclTensor *s = nullptr;
  aclTensor *step = nullptr;
  ret = CreateAclTensor(gradHostData, inputShape, &gradDeviceAddr, aclDataType::ACL_FLOAT, &grad);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(varHostData, inputShape, &varDeviceAddr, aclDataType::ACL_FLOAT, &var);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(mHostData, inputShape, &mDeviceAddr, aclDataType::ACL_FLOAT, &m);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(vHostData, inputShape, &vDeviceAddr, aclDataType::ACL_FLOAT, &v);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(sHostData, inputShape, &sDeviceAddr, aclDataType::ACL_FLOAT, &s);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(stepHostData, stepShape, &stepDeviceAddr, aclDataType::ACL_INT64, &step);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // out, inplace
  std::vector<int64_t> outShape = {2, 2, 2};

  // attr
  float lr = 0.001f;
  float emaDecay = 0.5f;
  float beta1 = 0.9f;
  float beta2 = 0.999f;
  float eps = 1e-8f;
  int64_t mode = 1;
  bool bias = true;
  float weightDecay = 0.5f;

  uint64_t workspaceSize = 0;
  aclOpExecutor *executor;

  // 3. 调用CANN算子库API，需要修改为具体的Api名称
  // 调用aclnnApplyFusedEmaAdam第一段接口
  ret = aclnnApplyFusedEmaAdamGetWorkspaceSize(grad, var, m, v, s, step, lr, emaDecay, beta1, beta2, eps,
                                               mode, bias, weightDecay, &workspaceSize, &executor);
  CHECK_RET(
      ret == ACL_SUCCESS,
      LOG_PRINT("aclnnApplyFusedEmaAdamGetWorkspaceSize 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aclnnApplyFusedEmaAdam第二段接口
  ret = aclnnApplyFusedEmaAdam(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS,
            LOG_PRINT("aclnnApplyFusedEmaAdam 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
  PrintOutResult(outShape, &varDeviceAddr);
  PrintOutResult(outShape, &mDeviceAddr);
  PrintOutResult(outShape, &vDeviceAddr);
  PrintOutResult(outShape, &sDeviceAddr);

  // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
  aclDestroyTensor(grad);
  aclDestroyTensor(var);
  aclDestroyTensor(m);
  aclDestroyTensor(v);
  aclDestroyTensor(s);
  aclDestroyTensor(step);

  // 7. 释放device资源
  aclrtFree(gradDeviceAddr);
  aclrtFree(varDeviceAddr);
  aclrtFree(mDeviceAddr);
  aclrtFree(vDeviceAddr);
  aclrtFree(sDeviceAddr);
  aclrtFree(stepDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}