Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

08/26/2020
by   Wenqian Dong, et al.
0

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 Smartfluidnet, a framework that automates model generation and application. Given an existing neural network as input, Smartfluidnet generates multiple neural networks before the simulation to meet the execution time and simulation quality requirement. During the simulation, Smartfluidnet dynamically switches the neural networks to make the best efforts to reach the user requirement on simulation quality. Evaluating with 20,480 input problems, we show that Smartfluidnet 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/14/2021

Partitioned Deep Learning of Fluid-Structure Interaction

We present a partitioned neural network-based framework for learning of ...
research
08/26/2020

Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation

The optimal power flow (OPF) problem is one of the most important optimi...
research
06/15/2018

SPNets: Differentiable Fluid Dynamics for Deep Neural Networks

In this paper we introduce Smooth Particle Networks (SPNets), a framewor...
research
12/18/2018

A Preliminary Study of Neural Network-based Approximation for HPC Applications

Machine learning, as a tool to learn and model complicated (non)linear r...
research
01/26/2019

Neural Networks Predict Fluid Dynamics Solutions from Tiny Datasets

In computational fluid dynamics, it often takes days or weeks to simulat...
research
05/05/2022

Towards Fast Simulation of Environmental Fluid Mechanics with Multi-Scale Graph Neural Networks

Numerical simulators are essential tools in the study of natural fluid-s...
research
08/16/2016

Adaptive Position-Based Fluids: Improving Performance of Fluid Simulations for Real-Time Applications

The Position Based Fluids (PBF) method is a state-of-the-art approach fo...

Please sign up or login with your details

Forgot password? Click here to reset