Graph Neural Network-Based Pipeline for Track Finding in the Velo at LHCb - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Graph Neural Network-Based Pipeline for Track Finding in the Velo at LHCb

Résumé

Over the next decade, increases in instantaneous luminosity and detector granularity will amplify the amount of data that has to be analysed by high-energy physics experiments, whether in real time or offline, by an order of magnitude. The reconstruction of charged particle tracks, which has always been a crucial element of offline data processing pipelines, must increasingly be deployed from the very first stages of the real time processing to enable experiments to achieve their physics goals. Graph Neural Networks (GNNs) have received a great deal of attention in the community because their computational complexity scales nearly linearly with the number of hits in the detector, unlike conventional algorithms which often scale quadratically or worse. This paper presents \texttt{ETX4VELO}, a GNN-based track-finding pipeline tailored for the Run 3 LHCb experiment's Vertex Locator, in the context of LHCb's fully GPU-based first-level trigger system, Allen. Currently implemented in Python, \texttt{ETX4VELO} offers the ability to reconstruct tracks with shared hits using a novel triplet-based method. When benchmarked against the traditional track-finding algorithm in Allen, this GNN-based approach not only matches but occasionally surpasses its physics performance. In particular, the fraction of fake tracks is reduced from over 2\% to below 1\% and the efficiency to reconstruct electrons is improved. While achieving comparable physics performance is a milestone, the immediate priority remains implementing \texttt{ETX4VELO} in Allen in order to determine and optimise its throughput, to meet the demands of this high-rate environment.
Fichier principal
Vignette du fichier
proceedings_etx4velo_ctd2023.pdf (658.39 Ko) Télécharger le fichier
Makefile (828 B) Télécharger le fichier
pictures/articulation.pdf (5.82 Ko) Télécharger le fichier
pictures/efficiency_vs_squared_maximal_distance_minbias-sim10b-xdigi_v2_4_1498.pdf (133.89 Ko) Télécharger le fichier
pictures/gnn.pdf (106.66 Ko) Télécharger le fichier
pictures/graph_size_vs_squared_maximal_distance_minbias-sim10b-xdigi_v2_4_1498.pdf (130.64 Ko) Télécharger le fichier
pictures/left_elbow.pdf (6.05 Ko) Télécharger le fichier
pictures/lhcb_tracking_system.pdf (28.33 Ko) Télécharger le fichier
pictures/pipeline.pdf (49.97 Ko) Télécharger le fichier
pictures/right_elbow.pdf (6.04 Ko) Télécharger le fichier
pictures/track_building.pdf (30.67 Ko) Télécharger le fichier
pictures/tracks.pdf (2.74 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04614040 , version 1 (17-06-2024)

Licence

Identifiants

Citer

Anthony Correia, Fotis I Giasemis, Nabil Garroum, Vladimir Vava Gligorov, Bertrand Granado. Graph Neural Network-Based Pipeline for Track Finding in the Velo at LHCb. Connecting The Dots 2023 (CTD 2023), Oct 2023, Toulouse, France. pp.PROC-CTD2023-34. ⟨hal-04614040⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More