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.
Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys
State Key Laboratory of Nonlinear Mechanics, Institute of Mechanics, Chinese Academy of Sciences(中国科学院力学研究所非线性力学国家重点实验室);Department of Materials Science and Engineering, Faculty of Mechanical Engineering, Delft University of Technology(代尔夫特理工大学机械工程学院材料科学与工程系);Faculty of Engineering Technology, University of Twente(特温特大学工程技术学院);Laboratory for multiscale mechanics and medical science, SV LAB, School of Aerospace, Xi’an Jiaotong University(西安交通大学航天学院SV多尺度力学与医学科学实验室);College of Physical Science and Technology, Bohai University(渤海大学物理科学与技术学院)
Towards Accurate and Scalable High-throughput MOF Adsorption Screening: Merging Classical Force Fields and Universal Machine Learned Interatomic Potentials
Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials
Department of Materials Science and Engineering, Seoul National University(首尔大学材料科学与工程系);Research Institute of Advanced Materials, Seoul National University(首尔大学先进材料研究所);Department of Computer Science and Engineering, Seoul National University(首尔大学计算机工程系);AI Center, Samsung Electronics(三星电子人工智能中心);Center for AI and Natural Sciences, Korea Institute of Advanced Study(韩国高级研究院人工智能与自然科学中心)
An Active Learning Interatomic Potential For Defect-Engineered CoCrFeMnNi High-Entropy Alloy
University of Tokyo(东京大学);Indian Institute of Technology Gandhinagar(甘地纳加尔印度理工学院);Herbert Gleiter International Institute, Liaoning Academy of Materials(赫伯特·盖勒国际研究所,辽宁材料研究院);Regional Institute of Education(地区教育学院)