/**
 * 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.
 */

 /*!
 * \file test_aclnn_grouped_dynamic_mx_quant.cpp
 * \brief
 */

#include <iostream>
#include <memory>
#include <vector>

#include "acl/acl.h"
#include "aclnnop/aclnn_grouped_dynamic_mx_quant.h"

#define CHECK_RET(cond, return_expr) \
    do {                             \
        if (!(cond)) {               \
            return_expr;             \
        }                            \
    } while (0)

#define CHECK_FREE_RET(cond, return_expr) \
    do {                                  \
        if (!(cond)) {                    \
            Finalize(deviceId, stream);   \
            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;
}

void Finalize(int32_t deviceId, aclrtStream stream)
{
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
}

int aclnnGroupedDynamicMxQuantTest(int32_t deviceId, 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 = {8, 1};
    std::vector<int64_t> groupedIndexShape = {2};
    std::vector<int64_t> yOutShape = {8, 1};
    std::vector<int64_t> mxscaleOutShape = {2, 1, 2};
    void* xDeviceAddr = nullptr;
    void* groupedIndexDeviceAddr = nullptr;
    void* yOutDeviceAddr = nullptr;
    void* mxscaleOutDeviceAddr = nullptr;
    aclTensor* x = nullptr;
    aclTensor* groupedIndex = nullptr;
    aclTensor* yOut = nullptr;
    aclTensor* mxscaleOut = nullptr;
    //对应BF16的值(0, 8, 64, 512)
    std::vector<uint16_t> xHostData = {{0}, {16640}, {17024}, {17408}, {0}, {16640}, {17024}, {17408}};
    
    std::vector<uint32_t> groupedIndexHostData = {4,8};
    //对应float8_e4m3的值(0, 4, 32, 256)
    std::vector<uint8_t> yOutHostData = {{0}, {72}, {96}, {120}, {0}, {72}, {96}, {120}};
    //对应float8_e8m0的值(2)
    std::vector<std::vector<uint8_t>> mxscaleOutHostData = {{{128, 0}}, {{128, 0}}};
    const char* roundModeOptional = "rint";
    int64_t dstType = 36;
    int64_t blocksize = 32;
    // 创建x aclTensor
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_BF16, &x);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor*)> xTensorPtr(x, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void*)> xDeviceAddrPtr(xDeviceAddr, aclrtFree);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建groudedIndex aclTensor
    ret = CreateAclTensor(groupedIndexHostData, groupedIndexShape, &groupedIndexDeviceAddr, aclDataType::ACL_INT32, &groupedIndex);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor*)> groupedIndexTensorPtr(groupedIndex, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void*)> groupedIndexDeviceAddrPtr(groupedIndexDeviceAddr, aclrtFree);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建yOut aclTensor
    ret = CreateAclTensor(yOutHostData, yOutShape, &yOutDeviceAddr, aclDataType::ACL_FLOAT8_E4M3FN, &yOut);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor*)> yOutTensorPtr(yOut, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void*)> yOutDeviceAddrPtr(yOutDeviceAddr, aclrtFree);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建mxscaleOut aclTensor
    ret = CreateAclTensor(mxscaleOutHostData, mxscaleOutShape, &mxscaleOutDeviceAddr, aclDataType::ACL_FLOAT8_E8M0, &mxscaleOut);
    std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor*)> mxscaleOutTensorPtr(mxscaleOut, aclDestroyTensor);
    std::unique_ptr<void, aclError (*)(void*)> mxscaleOutDeviceAddrPtr(mxscaleOutDeviceAddr, aclrtFree);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    
    // 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aclnnGroupedDynamicMxQuant第一段接口
    ret = aclnnGroupedDynamicMxQuantGetWorkspaceSize(x, groupedIndex, roundModeOptional, dstType, blocksize, yOut, mxscaleOut, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGroupedDynamicMxQuantGetWorkspaceSize 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;
    std::unique_ptr<void, aclError (*)(void*)> workspaceAddrPtr(nullptr, aclrtFree);
    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);
        workspaceAddrPtr.reset(workspaceAddr);
    }
    // 调用aclnnGroupedDynamicMxQuant第二段接口
    ret = aclnnGroupedDynamicMxQuant(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGroupedDynamicMxQuant failed. ERROR: %d\n", ret); return ret);

    //（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);

    // 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 size = GetShapeSize(yOutShape);
    std::vector<uint8_t> yOutData(
        size, 0);  // C语言中无法直接打印fp4的数据，需要用uint8读出来，自行通过二进制转成fp4
    ret = aclrtMemcpy(yOutData.data(), yOutData.size() * sizeof(yOutData[0]), yOutDeviceAddr,
                    size * sizeof(yOutData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy yOut from device to host failed. ERROR: %d\n", ret);
            return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("y[%ld] is: %d\n", i, yOutData[i]);
    }
    size = GetShapeSize(mxscaleOutShape);
    std::vector<uint8_t> mxscaleOutData(
        size, 0);  // C语言中无法直接打印fp8的数据，需要用uint8读出来，自行通过二进制转成fp8
    ret = aclrtMemcpy(mxscaleOutData.data(), mxscaleOutData.size() * sizeof(mxscaleOutData[0]), mxscaleOutDeviceAddr,
                    size * sizeof(mxscaleOutData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy mxscaleOut from device to host failed. ERROR: %d\n", ret);
            return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("mxscaleOut[%ld] is: %d\n", i, mxscaleOutData[i]);
    }
    return ACL_SUCCESS;
}

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 = aclnnGroupedDynamicMxQuantTest(deviceId, stream);
    CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGroupedDynamicMxQuantTest failed. ERROR: %d\n", ret); return ret);

    Finalize(deviceId, stream);
    return 0;
}