Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning

Weile Jia, Han Wang, Mohan Chen, Denghui Lu, Lin Lin, Roberto Car, E. Weinan, Linfeng Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

159 Scopus citations

Abstract

For 35 years, ab initio molecular dynamics (AIMD) has been the method of choice for modeling complex atomistic phenomena from first principles. However, most AIMD applications are limited by computational cost to systems with thousands of atoms at most. We report that a machine learningbased simulation protocol (Deep Potential Molecular Dynamics), while retaining ab initio accuracy, can simulate more than 1 nanosecond-long trajectory of over 100 million atoms per day, using a highly optimized code (GPU DeePMD-kit) on the Summit supercomputer. Our code can efficiently scale up to the entire Summit supercomputer, attaining 91 PFLOPS in double precision (45.5% of the peak) and 162/275 PFLOPS in mixed-single/half precision. The great accomplishment of this work is that it opens the door to simulating unprecedented size and time scales with ab initio accuracy. It also poses new challenges to the next-generation supercomputer for a better integration of machine learning and physical modeling.

Original languageEnglish (US)
Title of host publicationProceedings of SC 2020
Subtitle of host publicationInternational Conference for High Performance Computing, Networking, Storage and Analysis
PublisherIEEE Computer Society
ISBN (Electronic)9781728199986
DOIs
StatePublished - Nov 2020
Event2020 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020 - Virtual, Atlanta, United States
Duration: Nov 9 2020Nov 19 2020

Publication series

NameInternational Conference for High Performance Computing, Networking, Storage and Analysis, SC
Volume2020-November
ISSN (Print)2167-4329
ISSN (Electronic)2167-4337

Conference

Conference2020 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020
Country/TerritoryUnited States
CityVirtual, Atlanta
Period11/9/2011/19/20

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Keywords

  • Deep potential molecular dynamics
  • GPU
  • Summit
  • ab initio molecular dynamics
  • heterogeneous architecture
  • machine learning

Fingerprint

Dive into the research topics of 'Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning'. Together they form a unique fingerprint.

Cite this