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 Time | Wednesday, March 22, 2023 12:00-12:25 JST |
| Speakers | Zijian Xu, Engineer, Preferred Networks |
| place | online |
| Title | Running 100,000-Atom Molecular Dynamics with Accurate NN Potential on a GPU using Automatic Recomputation |
| Overview of the Webinar | Accurate 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. |
公開日：2023.03.13
-
URL
Copied
New Events and Seminars
NEW
Video Streaming
Webinars
OnlineOn-Demand
[On-Demand Webinar] Matlantis: Universal Atomistic Simulation for AI-Driven Materials Discovery
NEW
Upcoming events
exhibition
Tokyo Big Sight2026.1.28-30 (JPN)
[Exhibition Notice] We will be exhibiting at nano tech 2026
Past News
exhibition
Tokyo Big Sight2025.12.17 - 19 (JPN)
[Exhibition Announcement] Matlantis will co-exhibit at SEMICON Japan 2025
Past News
Webinars
Online2025.12.12 (JPN)
Participating in the Process Informatics Seminar | Revolutionizing materials development with the potential of general-purpose machine learning
Past News
Conferences and lectures
Pacifico Yokohama・ JPN2025.12.8 - 13
Matlantis will be speaking at MRM2025 @ Pacifico Yokohama
