Score: 2

Scaling Neural-Network-Based Molecular Dynamics with Long-Range Electrostatic Interactions to 51 Nanoseconds per Day

Published: April 22, 2025 | arXiv ID: 2504.15508v1

By: Jianxiong Li , Beining Zhang , Mingzhen Li and more

Potential Business Impact:

Makes computer models of molecules run 37x faster.

Business Areas:
Nanotechnology Science and Engineering

Neural network-based molecular dynamics (NNMD) simulations incorporating long-range electrostatic interactions have significantly extended the applicability to heterogeneous and ionic systems, enabling effective modeling critical physical phenomena such as protein folding and dipolar surface and maintaining ab initio accuracy. However, neural network inference and long-range force computation remain the major bottlenecks, severely limiting simulation speed. In this paper, we target DPLR, a state-of-the-art NNMD package that supports long-range electrostatics, and propose a set of comprehensive optimizations to enhance computational efficiency. We introduce (1) a hardware-offloaded FFT method to reduce the communication overhead; (2) an overlapping strategy that hides long-range force computations using a single core per node, and (3) a ring-based load balancing method that enables atom-level task evenly redistribution with minimal communication overhead. Experimental results on the Fugaku supercomputer show that our work achieves a 37x performance improvement, reaching a maximum simulation speed of 51 ns/day.

Country of Origin
🇨🇳 🇯🇵 Japan, China

Page Count
12 pages

Category
Computer Science:
Distributed, Parallel, and Cluster Computing