/**
 * 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_fused_floyd_attention.cpp
 * \brief
 */

#include <iostream>
#include <vector>
#include <cstdint>
#include <cmath>
#include "acl/acl.h"
#include "aclnnop/aclnn_fused_floyd_attention.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;
}

void PrintOutResult(std::vector<int64_t> &shape, void** deviceAddr) {
  auto size = GetShapeSize(shape);
  std::vector<float> 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);
  size = size > 1000 ? 1000 : size; // 打印数据个数小于等于1000
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("mean result[%ld] is: %f\n", i, resultData[i]);
  }
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // 固定写法，AscendCL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AscendCL对外接口列表
  // 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
  int64_t B = 1;
  int64_t H = 32;
  int64_t N = 128;
  int64_t M = 128;
  int64_t K = 128;
  int64_t D = 32;
  double scaleValue = 1.0;

  int64_t q_size = B * H * N * M * D;
  int64_t kv_size = B * H * N * K * D;
  int64_t k1v1_size = B * H * K * M * D;
  int64_t atten_mask_size = B * 1 * N * 1 * K;

  std::vector<int64_t> qShape = {B, H, N, M, D};
  std::vector<int64_t> kShape = {B, H, N, K, D};
  std::vector<int64_t> k1Shape = {B, H, K, M, D};
  std::vector<int64_t> vShape = {B, H, N, K, D};
  std::vector<int64_t> v1Shape = {B, H, K, M, D};
  std::vector<int64_t> attenmaskShape = {B, 1, N, 1, K};
  std::vector<int64_t> attentionOutShape = {B, H, N, M, D};
  std::vector<int64_t> softmaxMaxShape = {B, H, N, M, 8};
  std::vector<int64_t> softmaxSumShape = {B, H, N, M, 8};

  void *qDeviceAddr = nullptr;
  void *kDeviceAddr = nullptr;
  void *vDeviceAddr = nullptr;
  void *k1DeviceAddr = nullptr;
  void *v1DeviceAddr = nullptr;
  void *attenmaskDeviceAddr = nullptr;
  void *attentionOutDeviceAddr = nullptr;
  void *softmaxMaxDeviceAddr = nullptr;
  void *softmaxSumDeviceAddr = nullptr;

  aclTensor *q = nullptr;
  aclTensor *k = nullptr;
  aclTensor *v = nullptr;
  aclTensor *k1 = nullptr;
  aclTensor *v1 = nullptr;
  aclTensor *attenMask = nullptr;
  aclTensor *softmaxMax = nullptr;
  aclTensor *softmaxSum = nullptr;
  aclTensor *attentionOut = nullptr;

  std::vector<float> qHostData(q_size, 1.0);
  std::vector<float> kHostData(kv_size, 1.0);
  std::vector<float> vHostData(kv_size, 1.0);
  std::vector<float> k1HostData(k1v1_size, 1.0);
  std::vector<float> v1HostData(k1v1_size, 1.0);
  std::vector<uint8_t> attenmaskHostData(atten_mask_size, 0);
  std::vector<float> attentionOutHostData(B*H*N*M*D, 0.0);
  std::vector<float> softmaxMaxHostData(B*H*N*M*8, 0.0);
  std::vector<float> softmaxSumHostData(B*H*N*M*8, 0.0);

  ret = CreateAclTensor(qHostData, qShape, &qDeviceAddr, aclDataType::ACL_FLOAT16, &q);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(kHostData, kShape, &kDeviceAddr, aclDataType::ACL_FLOAT16, &k);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(vHostData, vShape, &vDeviceAddr, aclDataType::ACL_FLOAT16, &v);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(k1HostData, k1Shape, &k1DeviceAddr, aclDataType::ACL_FLOAT16, &k1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(v1HostData, v1Shape, &v1DeviceAddr, aclDataType::ACL_FLOAT16, &v1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(attenmaskHostData, attenmaskShape, &attenmaskDeviceAddr, aclDataType::ACL_UINT8, &attenMask);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(attentionOutHostData, attentionOutShape , &attentionOutDeviceAddr, aclDataType::ACL_FLOAT16, &attentionOut);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(softmaxMaxHostData, softmaxMaxShape, &softmaxMaxDeviceAddr, aclDataType::ACL_FLOAT, &softmaxMax);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(softmaxSumHostData, softmaxSumShape, &softmaxSumDeviceAddr, aclDataType::ACL_FLOAT, &softmaxSum);
  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aclnnFusedFloydAttention第一段接口
  ret = aclnnFusedFloydAttentionGetWorkspaceSize(
      q, k, v, k1, v1, attenMask, scaleValue, softmaxMax, softmaxSum, attentionOut, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFusedFloydAttentionGetWorkspaceSize 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aclnnFusedFloydAttention第二段接口
  ret = aclnnFusedFloydAttention(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFusedFloydAttention 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
  PrintOutResult(attentionOutShape, &attentionOutDeviceAddr);
  PrintOutResult(softmaxMaxShape, &softmaxMaxDeviceAddr);
  PrintOutResult(softmaxSumShape, &softmaxSumDeviceAddr);
  
  // 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
  aclDestroyTensor(q);
  aclDestroyTensor(k);
  aclDestroyTensor(v);
  aclDestroyTensor(k1);
  aclDestroyTensor(v1);
  aclDestroyTensor(attenMask);
  aclDestroyTensor(attentionOut);
  aclDestroyTensor(softmaxMax);
  aclDestroyTensor(softmaxSum);
  
  // 7. 释放device资源
  aclrtFree(qDeviceAddr);
  aclrtFree(kDeviceAddr);
  aclrtFree(vDeviceAddr);
  aclrtFree(k1DeviceAddr);
  aclrtFree(v1DeviceAddr);
  aclrtFree(attenmaskDeviceAddr);
  aclrtFree(attentionOutDeviceAddr);
  aclrtFree(softmaxMaxDeviceAddr);
  aclrtFree(softmaxSumDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  
  return 0;
}