/**
 * Copyright (c) 2026 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_silent_check.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<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("result[%ld] is: %d\n", 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;
}

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> valShape = {};
    std::vector<int64_t> inputGradShape = {4, 2};
    std::vector<int64_t> sfdaShape = {3};
    std::vector<int64_t> stepShape = {1};
    std::vector<int64_t> resultShape = {1};
    void* valDeviceAddr = nullptr;
    void* inputGradDeviceAddr = nullptr;
    void* sfdaDeviceAddr = nullptr;
    void* stepDeviceAddr = nullptr;
    void* resultDeviceAddr = nullptr;
    aclTensor* val = nullptr;
    aclTensor* inputGrad = nullptr;
    aclTensor* sfda = nullptr;
    aclTensor* step = nullptr;
    aclTensor* result = nullptr;
    std::vector<float> valHostData = {160.0};
    std::vector<float> inputGradHostData = {0, 1, 2, 3, 4, 5, 6, 7};
    std::vector<float> sfdaHostData = {70.0, 200.0, 400.0};
    std::vector<int64_t> stepHostData = {7};
    std::vector<int32_t> resultHostData = {0};
    int32_t c_min_steps = 7;
    float c_thresh_l1 = 1000000;
    float c_coeff_l1 = 100000;
    float c_thresh_l2 = 10000;
    float c_coeff_l2 = 5000;
    int32_t npu_asd_detect = 3;

    // 创建val aclTensor
    ret = CreateAclTensor(valHostData, valShape, &valDeviceAddr, aclDataType::ACL_FLOAT, &val);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建input_grad aclTensor
    ret = CreateAclTensor(inputGradHostData, inputGradShape, &inputGradDeviceAddr, aclDataType::ACL_FLOAT, &inputGrad);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建sfda aclTensor
    ret = CreateAclTensor(sfdaHostData, sfdaShape, &sfdaDeviceAddr, aclDataType::ACL_FLOAT, &sfda);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建step aclTensor
    ret = CreateAclTensor(stepHostData, stepShape, &stepDeviceAddr, aclDataType::ACL_INT64, &step);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建result aclTensor
    ret = CreateAclTensor(resultHostData, resultShape, &resultDeviceAddr, aclDataType::ACL_INT32, &result);
    if (result == nullptr) {
        std::cout << "result is nullptr!" << std::endl;
        return 0;
    }
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3.调用CANN算子库API,需要修改为具体的HostApi
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // 调用aclnnSilentCheck第一段接口
    ret = aclnnSilentCheckGetWorkspaceSize(val, inputGrad, sfda, step, c_min_steps, c_thresh_l1, c_coeff_l1,
                                           c_thresh_l2, c_coeff_l2, npu_asd_detect, result, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSilentCheckGetWorkspaceSize 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aclnnSilentCheck第二段接口
    ret = aclnnSilentCheck(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSilentCheck 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(resultShape, &resultDeviceAddr);

    // 6.释放aclTensor和aclScalar,需要根据具体API的接口定义修改
    aclDestroyTensor(val);
    aclDestroyTensor(inputGrad);
    aclDestroyTensor(sfda);
    aclDestroyTensor(step);
    aclDestroyTensor(result);

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