Using AI on FPGAs for the CMS Overlap Muon Track Finder for the HL-LHC

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Leguina, Pelayo, Folgueras, Santiago, Cardini, Andrea, Aller, Elena
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911183457484800
author Leguina, Pelayo
Folgueras, Santiago
Cardini, Andrea
Aller, Elena
author_facet Leguina, Pelayo
Folgueras, Santiago
Cardini, Andrea
Aller, Elena
contents Operating the CMS Level-1 trigger under the intense conditions of the High-Luminosity Large Hadron Collider -- with approximately 63~Tb/s of input and a fixed 12.5~$μ$s latency -- poses a demanding real-time reconstruction challenge. The CMS muon system is organized into three regions: a barrel, an endcap, and the intermediate barrel-endcap ``overlap'' region. In this overlap transition, the Overlap Muon Track Finder can be suboptimal for displaced-muon and long-lived-particle signatures. We present a first approach to a graph neural network tailored to these constraints, using GraphSAGE layers and a compact multi-layer perceptron to regress the inverse transverse momentum of muons. A PyTorch to C++ and high-level synthesis flow demonstrates feasibility, with initial results showing good agreement with simulation. Although a fully parallel implementation would exceed available field-programmable gate array resources, quantization, pruning, and multiplier reuse point the way toward a practical Phase-2 deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Using AI on FPGAs for the CMS Overlap Muon Track Finder for the HL-LHC
Leguina, Pelayo
Folgueras, Santiago
Cardini, Andrea
Aller, Elena
High Energy Physics - Experiment
Operating the CMS Level-1 trigger under the intense conditions of the High-Luminosity Large Hadron Collider -- with approximately 63~Tb/s of input and a fixed 12.5~$μ$s latency -- poses a demanding real-time reconstruction challenge. The CMS muon system is organized into three regions: a barrel, an endcap, and the intermediate barrel-endcap ``overlap'' region. In this overlap transition, the Overlap Muon Track Finder can be suboptimal for displaced-muon and long-lived-particle signatures. We present a first approach to a graph neural network tailored to these constraints, using GraphSAGE layers and a compact multi-layer perceptron to regress the inverse transverse momentum of muons. A PyTorch to C++ and high-level synthesis flow demonstrates feasibility, with initial results showing good agreement with simulation. Although a fully parallel implementation would exceed available field-programmable gate array resources, quantization, pruning, and multiplier reuse point the way toward a practical Phase-2 deployment.
title Using AI on FPGAs for the CMS Overlap Muon Track Finder for the HL-LHC
topic High Energy Physics - Experiment
url https://arxiv.org/abs/2509.23347