Accelerated GNN Tracking
The tracking of charged particles produced in collisions at colliders is a crucial aspect of the science program in the experiments. One of the primary challenges for the HL-LHC is the ability to efficiently, accurately, and rapidly perform tracking in collision events with large interaction pile-up. This project aims to improve charged-particle tracking in the ATLAS and CMS experiments through the use of accelerators such as field-programmable gate arrays (FPGAs) and machine learning algorithms such as Graph Neural Networks (GNNs).
A poster
Markus Atkinson made this poster on GNN-based Tracking and FPGA Acceleration
Team
- Markus Atkinson
- Gage DeZoort
- Lindsey Gray
- Mark Neubauer
- Isobel Ojalvo
- Savannah Thais
Publications
- Physics and Computing Performance of the Exa.TrkX TrackML Pipeline, X. Ju et. al., arXiv 2103.06995 (11 Mar 2021).