DeepAI AI Chat
Log In Sign Up

Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

by   Wenqian Dong, et al.

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.


page 1

page 2

page 3

page 4


Partitioned Deep Learning of Fluid-Structure Interaction

We present a partitioned neural network-based framework for learning of ...

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...

SPNets: Differentiable Fluid Dynamics for Deep Neural Networks

In this paper we introduce Smooth Particle Networks (SPNets), a framewor...

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

Machine learning, as a tool to learn and model complicated (non)linear r...

Neural Networks Predict Fluid Dynamics Solutions from Tiny Datasets

In computational fluid dynamics, it often takes days or weeks to simulat...

Calibration of a Fluid-Structure Problem with Keras

In this short paper we report on an inverse problem issued from a physic...

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...