Adaptive Neural Network-Based Approximation to Accelerate Eulerian Fluid Simulation

TL;DR

This paper presents Smartfluidnet, a neural network framework that dynamically adapts and switches models during Eulerian fluid simulation to improve speed and quality, addressing flexibility and generalization issues.

Contribution

Smartfluidnet automates neural network generation and dynamic switching to enhance applicability and performance in Eulerian fluid simulation.

Findings

Achieves 1.46x speedup over state-of-the-art neural models

Reaches 590x speedup compared to original simulation

Provides better simulation quality than existing neural approaches

Abstract

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.