/**
 * 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_flat_quant.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 shape_size = 1;
    for (auto i : shape) {
        shape_size *= i;
    }
    return shape_size;
}

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侧数据复制到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> xShape = {16, 16, 16};
    std::vector<int64_t> kroneckerP1Shape = {16, 16};
    std::vector<int64_t> kroneckerP2Shape = {16, 16};
    std::vector<int64_t> outShape = {16, 16, 2};
    std::vector<int64_t> quantScaleShape = {16};
    void* xDeviceAddr = nullptr;
    void* kroneckerP1DeviceAddr = nullptr;
    void* kroneckerP2DeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    void* quantScaleDeviceAddr = nullptr;
    aclTensor* x = nullptr;
    aclTensor* kroneckerP1 = nullptr;
    aclTensor* kroneckerP2 = nullptr;
    aclTensor* out = nullptr;
    aclTensor* quantScale = nullptr;
    double clipRatio = 1.0;
    std::vector<aclFloat16> xHostData(16 * 16 * 16, aclFloatToFloat16(1));
    std::vector<aclFloat16> kroneckerP1HostData(16 * 16, aclFloatToFloat16(1));
    std::vector<aclFloat16> kroneckerP2HostData(16 * 16, aclFloatToFloat16(1));
    std::vector<int32_t> outHostData(16 * 16 * 2, 1);
    std::vector<float> quantScaleHostData(16, 0);
    // 创建x aclTensor
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT16, &x);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 创建kroneckerP1 aclTensor
    ret = CreateAclTensor(kroneckerP1HostData, kroneckerP1Shape, &kroneckerP1DeviceAddr, aclDataType::ACL_FLOAT16,
                          &kroneckerP1);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建kroneckerP2 aclTensor
    ret = CreateAclTensor(kroneckerP2HostData, kroneckerP2Shape, &kroneckerP2DeviceAddr, aclDataType::ACL_FLOAT16,
                          &kroneckerP2);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 创建out aclTensor
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_INT32, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建quantScale aclTensor
    ret = CreateAclTensor(quantScaleHostData, quantScaleShape, &quantScaleDeviceAddr, aclDataType::ACL_FLOAT,
                          &quantScale);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 3. 调用CANN算子库API，需要修改为具体的API
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // 调用aclnnFlatQuant第一段接口
    ret = aclnnFlatQuantGetWorkspaceSize(x, kroneckerP1, kroneckerP2, clipRatio, out, quantScale, &workspaceSize,
                                         &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlatQuantGetWorkspaceSize 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aclnnFlatQuant第二段接口
    ret = aclnnFlatQuant(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlatQuant 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侧内存上的结果复制至host侧，需要根据具体API的接口定义修改
    auto size = GetShapeSize(outShape);
    std::vector<int32_t> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                      size * sizeof(int32_t), 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: %d\n", i, resultData[i]);
    }

    auto quantScaleSize = GetShapeSize(quantScaleShape);
    std::vector<float> quantScaleResultData(quantScaleSize, 0);
    ret = aclrtMemcpy(quantScaleResultData.data(), quantScaleResultData.size() * sizeof(quantScaleResultData[0]),
                      quantScaleDeviceAddr, quantScaleSize * sizeof(float), 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 < quantScaleSize; i++) {
        LOG_PRINT("result[%ld] is: %f\n", i, quantScaleResultData[i]);
    }

    // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
    aclDestroyTensor(x);
    aclDestroyTensor(kroneckerP1);
    aclDestroyTensor(kroneckerP2);
    aclDestroyTensor(out);
    aclDestroyTensor(quantScale);

    // 7. 释放device资源，需要根据具体API的接口定义修改
    aclrtFree(xDeviceAddr);
    aclrtFree(kroneckerP1DeviceAddr);
    aclrtFree(kroneckerP2DeviceAddr);
    aclrtFree(outDeviceAddr);
    aclrtFree(quantScaleDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}