/**
 * 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_cumprod.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;
}

void PrintOutResult(std::vector<int64_t> &shape, void **deviceAddr)
{
    auto size = GetShapeSize(shape);
    std::vector<int64_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("result[%ld] is: %d\n", i, resultData[i]);
    }
}

template<typename T>
void PrintOutFloatResult(std::vector<T> &shape, void **deviceAddr, const char *name)
{
    std::vector<float> resultData(shape.size(), 0);
    auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]),
                           *deviceAddr, shape.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 < shape.size(); i++)
    {
        LOG_PRINT("result var %s[%ld] is: %f\n", name, i, resultData[i]);
    }
}

int Init(int32_t deviceId, aclrtStream *stream)
{
    // 固定写法，acl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;
}

template <typename T>
int CreateAclScalar(aclDataType dataType, T &hostData, aclScalar **scalar)
{
    *scalar = aclCreateScalar(&hostData, dataType);
    if (*scalar == nullptr)
    {
        return -1;
    }
    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_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
    void *xDeviceAddr = nullptr;
    aclTensor *input = nullptr;
    std::vector<int64_t> xShape = {3};
    std::vector<int64_t> xHostData = {1,2,3};
    // 创建原始输入x
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_INT64, &input);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 创建axis aclScalar
    int32_t axis_value = 0;
    aclScalar *axis = nullptr;
    ret = CreateAclScalar(aclDataType::ACL_INT32, axis_value, &axis);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 创建result aclTensor
    std::vector<int64_t> resultHostData(3, 0);
    std::vector<int64_t> resultShape = {3};
    void *resultDeviceAddr = nullptr;
    aclTensor *result = nullptr;
    ret = CreateAclTensor(resultHostData, resultShape, &resultDeviceAddr, aclDataType::ACL_INT64, &result);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    uint64_t workspaceSize = 0;
    aclOpExecutor *executor;
    aclDataType dtype = ACL_INT64;
    void *workspaceAddr = nullptr;
    // 3.调用CANN算子库API
    // 调用aclnnCumprod第一段接口
    ret = aclnnCumprodGetWorkspaceSize(input, axis, dtype, result, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCumprodGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    
    // 根据第一段接口计算出的workspaceSize申请device内存
    if (workspaceSize > 0)
    {
        ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCumprod allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    // 调用aclnnCumprod第二段接口
    ret = aclnnCumprod(workspaceAddr, workspaceSize, executor, stream);
    // 4.(固定写法)同步等待任务执行结束
    ret = aclrtSynchronizeStream(stream);
    // 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(resultShape, &resultDeviceAddr);

    // 3.调用CANN算子库API
    // 调用aclnnInplaceCumprod第一段接口
    ret = aclnnInplaceCumprodGetWorkspaceSize(input, axis, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCumprodGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);

    // 根据第一段接口计算出的workspaceSize申请device内存
    if (workspaceSize > 0)
    {
        ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCumprod allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    // 调用aclnnInplaceCumprod第二段接口
    ret = aclnnInplaceCumprod(workspaceAddr, workspaceSize, executor, stream);
    // 4.(固定写法)同步等待任务执行结束
    ret = aclrtSynchronizeStream(stream);
    // 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(resultShape, &xDeviceAddr);

    // 6.释放aclTensor和aclScalar，需要根据具体API的接口定义修改
    aclDestroyTensor(input);
    aclDestroyScalar(axis);

    // // 7.释放device资源，需要根据具体API的接口定义修改
    aclrtFree(xDeviceAddr);
    aclrtFree(resultDeviceAddr);
    if (workspaceSize > 0)
    {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}