/**

 * This file is part of the OpenBOAT project at Harbin Institute of Technology (HIT)

 * and is contributed to the CANN Open Software.

 *

 * Copyright (c) 2025 AISS Group, Harbin Institute of Technology (HIT).

 * All Rights Reserved.

 *

 * Authors (accounts):

 * - Cao Xiaojuan <@c15503545287>

 * - Su Tonghua <@sutonghua>

 *

 * This program is free software: you can redistribute it and/or modify it.

 * Licensed under the CANN Open Software License Agreement Version 2.0 (the "License").

 * You may not use this file except in compliance with the License.

 * See the LICENSE file at the root of the repository for the full text of the License.

 *

 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED,

 * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.

 */



#include <iostream>

#include <vector>

#include "acl/acl.h"

#include "aclnnop/aclnn_slice_v3.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);

  

  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> inputShape = {4, 3};

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



  void* inputDeviceAddr = nullptr;

  void* outputDeviceAddr = nullptr;



  aclTensor* input = nullptr;

  aclTensor* output = nullptr;



  std::vector<int8_t> inputHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11};

  std::vector<int8_t> outputHostData = {1, 2, 3, 4};

  std::vector<int64_t> beginData = {1, 0};

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

 

  // 创建input aclTensor

  ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_INT8, &input);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建inputValue aclTensor

  ret = CreateAclTensor(outputHostData, outputShape, &outputDeviceAddr, aclDataType::ACL_INT8, &output);

  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建begin aclIntArray

  aclIntArray *begin = aclCreateIntArray(beginData.data(), beginData.size());

  // 创建size aclIntArray

  aclIntArray *outsize = aclCreateIntArray(outsizeData.data(), outsizeData.size());



  // 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aclnnslice_v3第一段接口

  ret = aclnnSliceV3GetWorkspaceSize(input, begin, outsize, output, &workspaceSize, &executor);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSlice_v3GetWorkspaceSize 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aclnnslice_v3第二段接口

  ret = aclnnSliceV3(workspaceAddr, workspaceSize, executor, stream);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnndSlice_v3 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(outputShape);

  std::vector<int8_t> resultData(size, 0);

  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outputDeviceAddr, size * sizeof(int8_t), 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("result[%ld] is: %d\n", i, resultData[i]);

  }



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

  aclDestroyTensor(input);

  aclDestroyTensor(output);

  aclDestroyIntArray(begin);

  aclDestroyIntArray(outsize);

 

  // 7. 释放device资源，需要根据具体API的接口定义修改

  aclrtFree(inputDeviceAddr);

  aclrtFree(outputDeviceAddr);

  if (workspaceSize > 0) {

    aclrtFree(workspaceAddr);

  }

  aclrtDestroyStream(stream);

  aclrtResetDevice(deviceId);

  aclFinalize();

  return 0;

}