Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
Name
fdata-03-598927.pdf
Description
Published version
Size
1.56 MB
Format
Adobe PDF
Checksum (MD5)
befa19fb8d009e773fa499ad728346bf
Author(s)
Iiyama, Yutaro
Cerminara, Gianluca
Gupta, Abhijay
Kieseler, Jan
Loncar, Vladimir
Pierini, Maurizio
Qasim, Shah Rukh
Rieger, Marcel
Summers, Sioni
Van Onsem, Gerrit
Date Issued
2021
Journal
Frontiers in Big Data
Publisher
Frontiers Media SA
Citation
Iiyama, Yutaro, Cerminara, Gianluca, Gupta, Abhijay, Kieseler, Jan, Loncar, Vladimir et al. 2021. "Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics." Frontiers in Big Data, 3.
Version
Final published version
Abstract
Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.
MIT Department
Massachusetts Institute of Technology. Laboratory for Nuclear Science
Massachusetts Institute of Technology. Department of Physics
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3389/FDATA.2020.598927
