/**
 * 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_quantize.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()
{
    // 1. （固定写法）device/stream初始化，参考acl API手册
    // 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 == 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
    std::vector<int64_t> xShape = {4, 2};
    std::vector<int64_t> scalesShape = {2};
    std::vector<int64_t> zeroPointsShape = {2};
    std::vector<int64_t> outShape = {4, 2};
    void* xDeviceAddr = nullptr;
    void* scalesDeviceAddr = nullptr;
    void* zeroPointsDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    aclTensor* x = nullptr;
    aclTensor* scales = nullptr;
    aclTensor* zeroPoints = nullptr;
    aclTensor* out = nullptr;

    aclDataType dataType = ACL_INT32;
    int32_t axis = 1;
    std::vector<float> scalesHostData = {1.0, -3.0};
    std::vector<int32_t> zeroPointsData = {2, 10};
    std::vector<float> xHostData = {0.3382, -0.0919, 0.7564, 0.0234, 3.1024, 1.0761, 0.4228, 1.4621};
    std::vector<int32_t> outHostData = {8, 0};

    // 创建x aclTensor
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建scales aclTensor
    ret = CreateAclTensor(scalesHostData, scalesShape, &scalesDeviceAddr, aclDataType::ACL_FLOAT, &scales);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建zeroPoints aclTensor
    ret = CreateAclTensor(zeroPointsData, zeroPointsShape, &zeroPointsDeviceAddr, aclDataType::ACL_INT32, &zeroPoints);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建out aclTensor
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, dataType, &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;
    // 调用aclnnQuantize第一段接口
    ret = aclnnQuantizeGetWorkspaceSize(x, scales, zeroPoints, dataType, axis, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnQuantizeGetWorkspaceSize 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aclnnQuantize第二段接口
    ret = aclnnQuantize(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnQuantize 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
    auto outSize = GetShapeSize(outShape);
    std::vector<int32_t> outData(outSize, 0);
    ret = aclrtMemcpy(
        outData.data(), outData.size() * sizeof(outData[0]), outDeviceAddr, outSize * sizeof(outData[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 < outSize; i++) {
        LOG_PRINT("out[%ld] is: %d\n", i, outData[i]);
    }

    // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
    aclDestroyTensor(x);
    aclDestroyTensor(scales);
    aclDestroyTensor(zeroPoints);
    aclDestroyTensor(out);

    // 7. 释放device资源，需要根据具体API的接口定义修改
    aclrtFree(xDeviceAddr);
    aclrtFree(scalesDeviceAddr);
    aclrtFree(zeroPointsDeviceAddr);
    aclrtFree(outDeviceAddr);

    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}