The Association for Computing Machinery named a U.S.-Chinese team of nine researchers as recipients of the 2020 ACM Gordon Bell Prize for Deep Potential Molecular Dynamics (DPMD), a machine learning-based protocol that can simulate a more than 1 nanosecond-long trajectory of over 100 million atoms per day. The team claimed its method realizes the first efficient MD simulation of 100 million atoms with ab initio accuracy.
The researchers developed a highly optimized code (GPU Deep MD-Kit), which they ran on Oak Ridge National Laboratory's Summit supercomputer. GPU Deep MD-Kit efficiently scaled up Summit, achieving 91 petaflops in double precision and 162/275 petaflops 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," the authors say in "Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to 100 million Atoms with Machine Learning," from SC'20, the International Conference for High Performance Computing, Networking, Storage and Analysis. "It also poses new challenges to the next-generation supercomputer for a better integration of machine learning and physical modeling."
From Association for Computing Machinery
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA