/**
 * 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):
 * - Tu Yuanhang <@TuYHAAAAAA>
 * - 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 "aclnn_mul_v2.h"
// 修改测试数据类型
using DataType = float;
#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<DataType> 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: %f\n", i, resultData[i]);       // float
    }
}

int Init(int32_t deviceId, aclrtStream* stream)
{
    // 固定写法，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);
    // 2. 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);
    // 3. 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. 调用acl进行device/stream初始化
    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，需要根据API的接口自定义构造
    aclTensor* selfX = nullptr;
    void* selfXDeviceAddr = nullptr;
    std::vector<int64_t> selfXShape = {1, 1, 3, 4};
    std::vector<DataType> selfXHostData(12, 7.0);
    ret = CreateAclTensor(selfXHostData, selfXShape, &selfXDeviceAddr, aclDataType::ACL_FLOAT, &selfX);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    aclTensor* selfY = nullptr;
    void* selfYDeviceAddr = nullptr;
    std::vector<int64_t> selfYShape = {1, 1, 3, 4};
    std::vector<DataType> selfYHostData(12, 9.0);
    ret = CreateAclTensor(selfYHostData, selfYShape, &selfYDeviceAddr, aclDataType::ACL_FLOAT, &selfY);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    aclTensor* out = nullptr;
    void* outDeviceAddr = nullptr;
    std::vector<int64_t> outShape = {1, 1, 3, 4};
    std::vector<DataType> outHostData(12, 3.0);
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3. 调用CANN算子库API，需要修改为具体的Api名称
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;

    LOG_PRINT("Before GetWorkspaceSize: selfX=%p, selfY=%p, out=%p\n", (void*)selfX, (void*)selfY, (void*)out);
    LOG_PRINT("Before GetWorkspaceSize: selfXDeviceAddr=%p, selfYDeviceAddr=%p, outDeviceAddr=%p\n",
          selfXDeviceAddr, selfYDeviceAddr, outDeviceAddr);
    // 4. 调用aclnnAddExample第一段接口
    ret = aclnnMulV2GetWorkspaceSize(selfX, selfY, out, &workspaceSize, &executor);
    LOG_PRINT("aclnnMulV2GetWorkspaceSize returned %d, workspaceSize=%llu, executor=%p\n",
          ret, (unsigned long long)workspaceSize, (void*)executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMulV2ExampleGetWorkspaceSize 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 > static_cast<uint64_t>(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);
    }

    // 5. 调用aclnnAddExample第二段接口
    ret = aclnnMulV2(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMulExample failed. ERROR: %d\n", ret); return ret);

    // 6. （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
    std::vector<int64_t> outShape1 = {8};
    PrintOutResult(outShape1, &outDeviceAddr);

    // 7. 释放aclTensor，需要根据具体API的接口定义修改
    aclDestroyTensor(selfX);
    aclDestroyTensor(selfY);
    aclDestroyTensor(out);

    // 8. 释放device资源
    aclrtFree(selfXDeviceAddr);
    aclrtFree(selfYDeviceAddr);
    aclrtFree(outDeviceAddr);
    if (workspaceSize > static_cast<uint64_t>(0)) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);

    // 9. acl去初始化
    aclFinalize();

    return 0;
}