Past News

Conferences and lectures

Online2023.3.22 (JPN)

Scheduled to be presented at "NVIDIA GTC 2023 (GPU Technology Conference)"

Zijian Xu, an engineer at Preferred Networks, will be speaking at NVIDIA GTC 2023 (GPU Technology Conference), which will be held from March 21st (Tue) to 24th (Fri), 2023.

In order to handle a large structure of 100,000 atoms using Neural Network Potential, a technique called recomputation is used to make memory usage more efficient.

For more details, please click here. You can watch the lectures and recordings by registering for free.
https://www.nvidia.com/gtc/session-catalog/?tab.catalogallsessionstab=16566177511100015Kus&search=running#/session/1666600863417001yG53

Details of the talk

Date and TimeWednesday, March 22, 2023 12:00-12:25 JST
SpeakersZijian Xu, Engineer, Preferred Networks
placeonline
TitleRunning 100,000-Atom Molecular Dynamics with Accurate NN Potential on a GPU using Automatic Recomputation
Overview of the WebinarAccurate and large scale atomistic simulation allows a new way of material discovery. Although neural network potential (NNP), a deep learning-based force field, dramatically accelerates computation time compared to conventional DFT methods, the amount of GPU memory often becomes a bottleneck to running large-scale simulations. Supporting a larger number of atoms in such simulations greatly increases the range of structures and phenomena that can be reproduced, including large molecules like proteins, heterogeneous systems like composites, additives, and lattice-mismatched interfaces. To overcome this issue, our method analyzes and reorganizes the computation graph of the neural network model to achieve exactly the same outputs with a smaller memory budget. The basic idea here is known as “recomputation,” which wipes out less frequently referenced large data from GPU memory and recomputes them from smaller values when necessary. Our experiments have shown that it is possible to run up to 5x larger simulations with only a 25% execution time overhead using the same amount of GPU memory.

New Events and Seminars

NEW

Video Streaming

Webinars

Online (Zoom)2025.3.26 (JPN)

[Archived] Strategy for strengthening the ability to generate new themes in materials development - How to cross the devil's river in the age of AI - Event report

Video Streaming

Webinars

Online2025.5.20 (JPN)

[Archived] Lecture by Professor Yosuke Harashima, Nara Institute of Science and Technology Event Report

Upcoming Events

User Community

Tokyo Conference Center, Shinagawa2025.10.8 (JPN)

Announcement of Matlantis User Conference 2025 to be held

Past News

Webinars

Online2025.5.20 (JPN)

[PFCC Webinar] Professor Yosuke Harashima from Nara Institute of Science and Technology will be presenting ~Material Discovery Using Neural Network Potential~

Past News

Conferences and lectures

Tokyo University of Science Noda Campus & Online2025.3.14-17 (JPN)

PFCC to Present at the 72nd Japan Society of Applied Physics  Spring Meeting