/**
 * 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 "acl/acl_op.h"
#include "aclnn/aclnn_base.h"
#include "aclnnop/aclnn_add_n.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;
}

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() 
{
    // 固定写法 device/stream初始化
    int32_t deviceId = 0; //根据实际情况修改
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 申请输入输出tensor的device侧内存
    std::vector<int64_t> inputShape1 = {4, 2};
    std::vector<int64_t> inputShape2 = {4, 2};
    std::vector<int64_t> outputShape = {4, 2};
    void* inputDeviceAddr1 = nullptr;
    void* inputDeviceAddr2 = nullptr;
    void* outputDeviceAddr = nullptr;
    aclTensor* input1 = nullptr;
    aclTensor* input2 = nullptr;
    aclTensor* output = nullptr;
    std::vector<float> inputHostData1 = {0, 1, 2, 3, 4, 5, 6, 7};
    std::vector<float> inputHostData2 = {1, 1, 1, 2, 2, 2, 3, 3};
    std::vector<float> outputHostData = {0, 0, 0, 0, 0, 0, 0, 0};
    aclDataType dtype = aclDataType::ACL_FLOAT;
    
    // 创建输入输出
    ret = CreateAclTensor(inputHostData1, inputShape1, &inputDeviceAddr1, dtype, &input1);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    
    ret = CreateAclTensor(inputHostData2, inputShape2, &inputDeviceAddr2, dtype, &input2);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    ret = CreateAclTensor(outputHostData, outputShape, &outputDeviceAddr, dtype, &output);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    std::vector<aclTensor*> tmp{input1, input2};
    aclTensorList* inputList = aclCreateTensorList(tmp.data(), tmp.size());
    CHECK_RET(inputList != nullptr, LOG_PRINT("aclCreateTensorList failed. ERROR: %d\n", ret); return ret);
    
    LOG_PRINT("Test aclnnAddN\n");
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    
    // 调用aclnnAddN的第一段接口
    ret = aclnnAddNGetWorkspaceSize(inputList, output, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAddNGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    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aclnnAddN的第二段接口
    ret = aclnnAddN(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAddN failed. ERROR: %d\n", ret); return ret);

    // 同步等待stream执行完毕
    ret = aclrtSynchronizeStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

    auto size = GetShapeSize(outputShape);
    std::vector<float> resultData(size, 0);

    // 从device侧内存拷贝结果到host侧内存
    ret = aclrtMemcpy(
        resultData.data(), resultData.size() * sizeof(resultData[0]), outputDeviceAddr, 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 ret);
    
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
    }

    // 释放aclTensor和aclTensorList
    aclDestroyTensor(input1);
    aclDestroyTensor(input2);
    aclDestroyTensor(output);
    aclDestroyTensorList(inputList);

    // 释放device资源
    aclrtFree(inputDeviceAddr1);
    aclrtFree(inputDeviceAddr2);
    aclrtFree(outputDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}