Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations

Abstract

Message-passing graph neural network interatomic potentials (GNN-IPs), particularly those with equivariant representations such as NequIP, are attracting significant attention due to their data efficiency and high accuracy. However, parallelizing GNN-IPs poses challenges because multiple message-passing layers complicate data communication within the spatial decomposition method, which is preferred by many molecular dynamics (MD) packages. In this article, we propose an efficient parallelization scheme compatible with GNN-IPs and develop a package, SevenNet (Scalable EquiVariance-Enabled Neural NETwork), based on the NequIP architecture. For MD simulations, SevenNet interfaces with the LAMMPS package. Through benchmark tests on a 32-GPU cluster with examples of SiO${}_2$, SevenNet achieves over 80% parallel efficiency in weak-scaling scenarios and exhibits nearly ideal strong-scaling performance as long as GPUs are fully utilized. However, the strong-scaling performance significantly declines with suboptimal GPU utilization, particularly affecting parallel efficiency in cases involving lightweight models or simulations with small numbers of atoms. We also pre-train SevenNet with a vast dataset from the Materials Project (dubbed `SevenNet-0') and assess its performance on generating amorphous Si${}_3$N${}_4$ containing more than 100,000 atoms. By developing scalable GNN-IPs, this work aims to bridge the gap between advanced machine learning models and large-scale MD simulations, offering researchers a powerful tool to explore complex material systems with high accuracy and efficiency.

34 pages, 6 figures

References in corpus (6)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements
• Machine-learning interatomic potentials for materials science
• Graph Neural Networks Accelerated Molecular Dynamics

Cited by in corpus (18)

• A practical guide to machine learning interatomic potentials -- Status and future
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Accelerating CALPHAD-based Phase Diagram Predictions in Complex Alloys Using Universal Machine Learning Potentials: Opportunities and Challenges
• Predicting ionic conductivity in solids from the machine-learned potential energy landscape
• Universal machine learning interatomic potentials poised to supplant DFT in modeling general defects in metals and random alloys
• How Graph Neural Network Interatomic Potentials Extrapolate: Role of the Message-Passing Algorithm
• Exploration of amorphous V${}_2$O${}_5$ as cathode for magnesium batteries
• Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy
• A Comprehensive Assessment and Benchmark Study of Large Atomistic Foundation Models for Phonons
• Fine-Tuning Unifies Foundational Machine-learned Interatomic Potential Architectures at ab initio Accuracy
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Leveraging transfer learning for accurate estimation of ionic migration barriers in solids
• FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
• Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
• Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys
• High-Throughput Prediction of Exfoliable Non-van der Waals Materials from a Universal Potential
• VacHopPy: A Python package for vacancy hopping analysis based on molecular dynamics simulations
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence