/**

 * 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 <cmath>

#include <algorithm>

#include <cstdint>

#include <iostream>

#include <vector>

#include <sys/types.h>

#include <sys/stat.h>

#include <unistd.h>

#include <fstream>

#include <fcntl.h>



#include "acl/acl.h"

#include "aclnn_arange.h"





#define SUCCESS 0

#define FAILED 1



#define INFO_LOG(fmt, args...) fprintf(stdout, "[INFO]  " fmt "\n", ##args)

#define WARN_LOG(fmt, args...) fprintf(stdout, "[WARN]  " fmt "\n", ##args)

#define ERROR_LOG(fmt, args...) fprintf(stderr, "[ERROR]  " fmt "\n", ##args)



#define CHECK_RET(cond, return_expr) \

  do {                               \

    if (!(cond)) {                   \

      return_expr;                   \

    }                                \

  } while (0)



#define LOG_PRINT(message, ...)     \

  do {                              \

    printf(message, ##__VA_ARGS__); \

  } while (0)



enum ArgName : int {

    ARANGE_START,

    ARANGE_END,

    ARANGE_STEP,

    ARANGE_COUNT

};



bool ReadFile(const std::string &filePath, size_t fileSize, void *buffer, size_t bufferSize)

{

    struct stat sBuf;

    int fileStatus = stat(filePath.data(), &sBuf);

    if (fileStatus == -1) {

        ERROR_LOG("failed to get file %s", filePath.c_str());

        return false;

    }

    if (S_ISREG(sBuf.st_mode) == 0) {

        ERROR_LOG("%s is not a file, please enter a file", filePath.c_str());

        return false;

    }



    std::ifstream file;

    file.open(filePath, std::ios::binary);

    if (!file.is_open()) {

        ERROR_LOG("Open file failed. path = %s", filePath.c_str());

        return false;

    }



    std::filebuf *buf = file.rdbuf();

    size_t size = buf->pubseekoff(0, std::ios::end, std::ios::in);

    if (size == 0) {

        ERROR_LOG("file size is 0");

        file.close();

        return false;

    }

    if (size > bufferSize) {

        ERROR_LOG("file size is larger than buffer size");

        file.close();

        return false;

    }

    buf->pubseekpos(0, std::ios::in);

    buf->sgetn(static_cast<char *>(buffer), size);

    fileSize = size;

    file.close();

    return true;

}



bool WriteFile(const std::string &filePath, const void *buffer, size_t size)

{

    if (buffer == nullptr) {

        ERROR_LOG("Write file failed. buffer is nullptr");

        return false;

    }



    int fd = open(filePath.c_str(), O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWRITE);

    if (fd < 0) {

        ERROR_LOG("Open file failed. path = %s", filePath.c_str());

        return false;

    }



    auto writeSize = write(fd, buffer, size);

    (void) close(fd);

    if (writeSize != size) {

        ERROR_LOG("Write file Failed.");

        return false;

    }



    return true;

}



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<int32_t> 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: %d\n", i, resultData[i]);

    }

}



int Init(int32_t deviceId, aclrtStream* stream) {

  // 固定写法，AscendCL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. device/stream初始化，参考AscendCL对外接口列表

  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

  void* outDeviceAddr = nullptr;

  aclScalar* start = nullptr;

  aclScalar* end = nullptr;

  aclScalar* step = nullptr;

  aclTensor* out = nullptr;

  

  std::vector<int32_t> inputDataHostData = {1, -1113, -5};

  int32_t startValue = inputDataHostData[ARANGE_START];

  int32_t endValue = inputDataHostData[ARANGE_END];

  int32_t stepValue = inputDataHostData[ARANGE_STEP];



  double size_arange = ceil(static_cast<double>(endValue - startValue) / stepValue);

  int64_t size_value = static_cast<int64_t>(size_arange);

  std::vector<int64_t> outShape = {size_value};

  std::vector<int32_t> outHostData(size_value, 0);



  // 创建start aclScalar

  start = aclCreateScalar(&inputDataHostData[ARANGE_START], aclDataType::ACL_INT32);

  CHECK_RET(start != nullptr, return ret);

  // 创建end aclScalar

  end = aclCreateScalar(&inputDataHostData[ARANGE_END], aclDataType::ACL_INT32);

  CHECK_RET(end != nullptr, return ret);

  // 创建step aclScalar

  step = aclCreateScalar(&inputDataHostData[ARANGE_STEP], aclDataType::ACL_INT32);

  CHECK_RET(step != nullptr, return ret);

  // 创建out aclTensor

  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_INT32, &out);

  CHECK_RET(ret == ACL_SUCCESS, return ret);



  // 3. 调用CANN算子库API

  uint64_t workspaceSize = 0;

  aclOpExecutor* executor;

  // 调用aclnnArange第一段接口

  ret = aclnnArangeGetWorkspaceSize(start, end, step, out, &workspaceSize, &executor);

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnArangeGetWorkspaceSize 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aclnnArange第二段接口

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

  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnArange failed. ERROR: %d\n", ret); return ret);



  // 4. 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

  PrintOutResult(outShape, &outDeviceAddr);



  // 6. 释放aclTensor和aclScalar

  aclDestroyScalar(start);

  aclDestroyScalar(end);

  aclDestroyScalar(step);

  aclDestroyTensor(out);

  

  // 7. 释放device资源，需要根据具体API的接口定义修改

  aclrtFree(outDeviceAddr);

  if (workspaceSize > 0) {

    aclrtFree(workspaceAddr);

  }

  aclrtDestroyStream(stream);

  aclrtResetDevice(deviceId);

  aclFinalize();

  return 0;

}