Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications

Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications

IntroductionReconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.T...

Full description

Bibliographic Details
Main Authors: Claire Songhyun Lee, V. Hewes, Giuseppe Cerati, Kewei Wang, Adam Aurisano, Ankit Agrawal, Alok Choudhary, Wei-Keng Liao
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-09-01
Series:Frontiers in High Performance Computing
Subjects:
high-performance computing
scientific workflows
graph neural networks
supercomputing
graphic processing units
deep learning
Online Access:https://www.frontiersin.org/articles/10.3389/fhpcp.2024.1458674/full

Internet

https://www.frontiersin.org/articles/10.3389/fhpcp.2024.1458674/full

Similar Items