Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
University of California, Berkeley, California
Computational Physics (physics.comp-ph), (1 May 2020)
@misc{jia2020pushing,
title={Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning},
author={Weile Jia and Han Wang and Mohan Chen and Denghui Lu and Jiduan Liu and Lin Lin and Roberto Car and Weinan E and Linfeng Zhang},
year={2020},
eprint={2005.00223},
archivePrefix={arXiv},
primaryClass={physics.comp-ph}
}
For 35 years, ab initio molecular dynamics (AIMD) has been the method of choice for understanding complex materials and molecules at the atomic scale from first principles. However, most applications of AIMD are limited to systems with thousands of atoms due to the high computational complexity. We report that a machine learning-based molecular simulation protocol (Deep Potential Molecular Dynamics), driven by a highly optimized code (GPU DeePMD-kit) on the Summit supercomputer, has greatly expanded the capabilities of MD simulation with ab initio accuracy, pushing its limit to simulation of over 100 million atoms for one nanosecond per day. Our code can efficiently scale up to the entire Summit supercomputer, reaching 86 PFLOPS in double precision (43% of the peak) and 137 PFLOPS in mixed precision. This success opens the door to the modeling of atomic processes in realistic materials and molecular systems with ab initio accuracy.
May 10, 2020 by hgpu
