Scaling Neural-Network-Based Molecular Dynamics with Long-Range Electrostatic Interactions to 51 Nanoseconds per Day
By: Jianxiong Li , Beining Zhang , Mingzhen Li and more
Potential Business Impact:
Makes computer models of molecules run 37x faster.
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.
Similar Papers
Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations
Chemical Physics
Helps computers understand how molecules move and change.
On the Connection Between Diffusion Models and Molecular Dynamics
Machine Learning (CS)
Makes computer models of atoms work better.
Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations
Machine Learning (CS)
Makes computer models of materials run faster.