/**
 * 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_top_k_top_p_sample.cpp
 * \brief
 */
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_top_k_top_p_sample.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
    // 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> logitsShape = {48, 131072};
    std::vector<int64_t> topKPShape = {48};
    long long vocShapeSize = GetShapeSize(logitsShape);
    long long batchShapeSize = GetShapeSize(topKPShape);

    void* logitsDeviceAddr = nullptr;
    void* topKDeviceAddr = nullptr;
    void* topPDeviceAddr = nullptr;
    void* qDeviceAddr = nullptr;
    void* logitsSelectedIdxDeviceAddr = nullptr;
    void* logitsTopKPSelectDeviceAddr = nullptr;

    aclTensor* logits = nullptr;
    aclTensor* topK = nullptr;
    aclTensor* topP = nullptr;
    aclTensor* q = nullptr;
    aclTensor* logitsSelectedIdx = nullptr;
    aclTensor* logitsTopKPSelect = nullptr;
    std::vector<int16_t> logitsHostData(48 * 131072, 1);
    std::vector<int32_t> topKHostData(48, 128);
    std::vector<int16_t> topPHostData(48, 1);
    std::vector<float> qHostData(48 * 131072, 1.0f);

    std::vector<int64_t> logitsSelectedIdxHostData(48, 0);
    std::vector<float> logitsTopKPSelectHostData(48 * 131072, 0);

    float eps=1e-8;
    int64_t isNeedLogits=0;
    int32_t topKGuess=32;
    // 创建logitsaclTensor
    ret = CreateAclTensor(logitsHostData, logitsShape, &logitsDeviceAddr, aclDataType::ACL_BF16, &logits);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建topKaclTensor
    ret = CreateAclTensor(topKHostData, topKPShape, &topKDeviceAddr, aclDataType::ACL_INT32, &topK);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建topPaclTensor
    ret = CreateAclTensor(topPHostData, topKPShape, &topPDeviceAddr, aclDataType::ACL_BF16, &topP);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建q aclTensor
    ret = CreateAclTensor(qHostData, logitsShape, &qDeviceAddr, aclDataType::ACL_FLOAT, &q);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建logtisSelected aclTensor
    ret = CreateAclTensor(logitsSelectedIdxHostData, topKPShape, &logitsSelectedIdxDeviceAddr, aclDataType::ACL_INT64, &logitsSelectedIdx);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 创建logitsTopKPSelect aclTensor
    ret = CreateAclTensor(logitsTopKPSelectHostData, logitsShape, &logitsTopKPSelectDeviceAddr, aclDataType::ACL_FLOAT, &logitsTopKPSelect);
    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aclnnTopKTopPSample第一段接口
    ret = aclnnTopKTopPSampleGetWorkspaceSize(logits, topK, topP, q, eps, isNeedLogits, topKGuess, logitsSelectedIdx, logitsTopKPSelect, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTopKTopPSampleGetWorkspaceSize 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aclnnTopKTopPSample第二段接口
    ret = aclnnTopKTopPSample(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTopKTopPSample 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 size = GetShapeSize(topKPShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), logitsSelectedIdxDeviceAddr,
                        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: %d\n", i, resultData[i]);
    }

    // 6. 释放aclTensor，需要根据具体API的接口定义修改
    aclDestroyTensor(logits);
    aclDestroyTensor(topK);
    aclDestroyTensor(topP);
    aclDestroyTensor(q);
    aclDestroyTensor(logitsSelectedIdx);
    aclDestroyTensor(logitsTopKPSelect);
    // 7. 释放Device资源，需要根据具体API的接口定义修改
    aclrtFree(logitsDeviceAddr);
    aclrtFree(topKDeviceAddr);
    aclrtFree(topPDeviceAddr);
    aclrtFree(qDeviceAddr);
    aclrtFree(logitsSelectedIdxDeviceAddr);
    aclrtFree(logitsTopKPSelectDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
    }