Adaptive neural network-based approximation to accelerate eulerian fluid simulation
Adaptive neural network-based approximation to accelerate eulerian fluid simulation
复制标题
DOI：
10.1145/3295500.3356147
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Wenqian Dong;Jie Liu;Zhen Xie;Dong Li
中科院分区：
文献类型：
--
作者：
Wenqian Dong;Jie Liu;Zhen Xie;Dong Li
欧拉流体模拟是高性能计算的一个重要应用。目前的神经网络流体模拟加速方法缺乏灵活性和通用性。在本文中，我们解决了上述限制，旨在提高神经网络在欧拉流体模拟的适用性。我们介绍智能流体网络，一个框架，自动化模型生成和应用程序。给定一个已有的神经网络作为输入，Smart-fluidnet在仿真前生成多个神经网络，以满足执行时间和仿真质量的要求。在仿真过程中，Smart-fluidnet动态切换神经网络，尽最大努力达到用户对仿真质量的要求。通过对20，480个输入问题的评估，我们发现Smart-fluidnet在NVIDIA Titan X Pascal GPU上分别实现了与最先进的神经网络模型和原始流体模拟相比的1.46倍和590倍加速，同时提供了比最先进模型更好的模拟质量。
The Eulerian fluid simulation is an important HPC application. The neural network has been applied to accelerate it. The current methods that accelerate the fluid simulation with neural networks lack flexibility and generalization. In this paper, we tackle the above limitation and aim to enhance the applicability of neural networks in the Eulerian fluid simulation. We introduce Smart-fluidnet, a framework that automates model generation and application. Given an existing neural network as input, Smart-fluidnet generates multiple neural networks before the simulation to meet the execution time and simulation quality requirement. During the simulation, Smart-fluidnet dynamically switches the neural networks to make best efforts to reach the user's requirement on simulation quality. Evaluating with 20,480 input problems, we show that Smart-fluidnet achieves 1.46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.