Cargando…

Optimizing Graph Neural Networks for Jet Tagging in Particle Physics on FPGAs

This work proposes a novel reconfigurable architecture for reducing the latency of JEDI-net, a Graph Neural Network (GNN) based algorithm for jet tagging in particle physics, which achieves state-of-the-art accuracy. Accelerating JEDI-net is challenging since it requires low latency to deploy the ne...

Descripción completa

Detalles Bibliográficos
Autores principales: Que, Zhiqiang, Loo, Marcus, Fan, Hongxiang, Pierini, Maurizio, Tapper, Alexander, Luk, Wayne
Lenguaje:eng
Publicado: 2022
Materias:
Acceso en línea:https://dx.doi.org/10.1109/FPL57034.2022.00057
http://cds.cern.ch/record/2861082