/**

 * 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_group_norm_silu.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 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_ND,

                            shape.data(), shape.size(), *deviceAddr);

  return 0;

}



int main() {

  // 1. （固定写法）device/stream初始化, 参考acl对外接口列表

  // 根据自己的实际device填写deviceId

  int32_t deviceId = 0;

  aclrtStream stream;

  auto ret = Init(deviceId, &stream);

  // check根据自己的需要处理

  CHECK_RET(ret == 0, 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, 3, 4};

  std::vector<int64_t> gammaShape = {3};

  std::vector<int64_t> betaShape = {3};

  std::vector<int64_t> outShape = {2, 3, 4};

  std::vector<int64_t> meanOutShape = {2, 1};

  std::vector<int64_t> rstdOutShape = {2, 1};

  void* selfDeviceAddr = nullptr;

  void* gammaDeviceAddr = nullptr;

  void* betaDeviceAddr = nullptr;

  void* outDeviceAddr = nullptr;

  void* meanOutDeviceAddr = nullptr;

  void* rstdOutDeviceAddr = nullptr;

  aclTensor* self = nullptr;

  aclTensor* gamma = nullptr;

  aclTensor* beta = nullptr;

  aclTensor* out = nullptr;

  aclTensor* meanOut = nullptr;

  aclTensor* rstdOut = nullptr;

  std::vector<float> selfHostData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0,

                                     13.0, 14.0, 15.0, 16.0, 17.0, 18.0, 19.0, 20.0, 21.0, 22.0, 23.0, 24.0};

  std::vector<float> gammaHostData = {2.0, 2, 2};

  std::vector<float> betaHostData = {2.0, 2, 2};

  std::vector<float> outHostData = {1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0,

                                    13.0, 14.0, 15.0, 16.0, 17.0, 18.0, 19.0, 20.0, 21.0, 22.0, 23.0, 24.0};

  std::vector<float> meanOutHostData = {2.0, 2};

  std::vector<float> rstdOutHostData = {2.0, 2};



  int64_t group = 1;

  double eps = 0.00001;

  bool activateSilu = true;

  // 创建self aclTensor

  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> selfTensorPtr(self, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> selfDeviceAddrPtr(selfDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建gamma aclTensor

  ret = CreateAclTensor(gammaHostData, gammaShape, &gammaDeviceAddr, aclDataType::ACL_FLOAT, &gamma);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> gammaTensorPtr(gamma, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> gammaDeviceAddrPtr(gammaDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建beta aclTensor

  ret = CreateAclTensor(betaHostData, betaShape, &betaDeviceAddr, aclDataType::ACL_FLOAT, &beta);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> betaTensorPtr(beta, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> betaDeviceAddrPtr(betaDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建out aclTensor

  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> outTensorPtr(out, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> outDeviceAddrPtr(outDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建meanOut aclTensor

  ret = CreateAclTensor(meanOutHostData, meanOutShape, &meanOutDeviceAddr, aclDataType::ACL_FLOAT, &meanOut);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> meanOutTensorPtr(meanOut, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> meanOutDeviceAddrPtr(meanOutDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建rstdOut aclTensor

  ret = CreateAclTensor(rstdOutHostData, rstdOutShape, &rstdOutDeviceAddr, aclDataType::ACL_FLOAT, &rstdOut);

  std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> rstdOutTensorPtr(rstdOut, aclDestroyTensor);

  std::unique_ptr<void, aclError (*)(void *)> rstdOutDeviceAddrPtr(rstdOutDeviceAddr, aclrtFree);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  

  // 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aclnnGroupNormSiluV2第一段接口

  ret = aclnnGroupNormSiluV2GetWorkspaceSize(self, gamma, beta, group, eps, activateSilu, out, meanOut, rstdOut, &workspaceSize, &executor);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGroupNormSiluV2GetWorkspaceSize 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aclnnGroupNormSiluV2第二段接口

  ret = aclnnGroupNormSiluV2(workspaceAddr, workspaceSize, executor, stream);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGroupNormSiluV2 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(outShape);

  std::vector<float> outResultData(size, 0);

  ret = aclrtMemcpy(outResultData.data(), outResultData.size() * sizeof(outResultData[0]), outDeviceAddr, size * sizeof(float),

                    ACL_MEMCPY_DEVICE_TO_HOST);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

  for (int64_t i = 0; i < size; i++) {

    LOG_PRINT("outResultData[%ld] is: %f\n", i, outResultData[i]);

  }



  size = GetShapeSize(meanOutShape);

  std::vector<float> meanResultData(size, 0);

  ret = aclrtMemcpy(meanResultData.data(), meanResultData.size() * sizeof(meanResultData[0]), meanOutDeviceAddr, size * sizeof(float),

                    ACL_MEMCPY_DEVICE_TO_HOST);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

  for (int64_t i = 0; i < size; i++) {

    LOG_PRINT("meanResultData[%ld] is: %f\n", i, meanResultData[i]);

  }



  size = GetShapeSize(rstdOutShape);

  std::vector<float> rstdResultData(size, 0);

  ret = aclrtMemcpy(rstdResultData.data(), rstdResultData.size() * sizeof(rstdResultData[0]), rstdOutDeviceAddr, size * sizeof(float),

                    ACL_MEMCPY_DEVICE_TO_HOST);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);

  for (int64_t i = 0; i < size; i++) {

    LOG_PRINT("rstdResultData[%ld] is: %f\n", i, rstdResultData[i]);

  }



  // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改

  aclDestroyTensor(self);

  aclDestroyTensor(gamma);

  aclDestroyTensor(beta);

  aclDestroyTensor(out);

  aclDestroyTensor(meanOut);

  aclDestroyTensor(rstdOut);



  // 7. 释放device资源，需要根据具体API的接口定义修改

  aclrtFree(selfDeviceAddr);

  aclrtFree(gammaDeviceAddr);

  aclrtFree(betaDeviceAddr);

  aclrtFree(outDeviceAddr);

  aclrtFree(meanOutDeviceAddr);

  aclrtFree(rstdOutDeviceAddr);



  if (workspaceSize > 0) {

    aclrtFree(workspaceAddr);

  }

  aclrtDestroyStream(stream);

  aclrtResetDevice(deviceId);

  aclFinalize();

  return 0;

}