Graph Neural Network-Based Track Finding in the LHCb Vertex Detector

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Correia, Anthony, Giasemis, Fotis I., Garroum, Nabil, Gligorov, Vladimir Vava, Granado, Bertrand
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912445341106176
author Correia, Anthony
Giasemis, Fotis I.
Garroum, Nabil
Gligorov, Vladimir Vava
Granado, Bertrand
author_facet Correia, Anthony
Giasemis, Fotis I.
Garroum, Nabil
Gligorov, Vladimir Vava
Granado, Bertrand
contents The next decade will see an order of magnitude increase in data collected by high-energy physics experiments, driven by the High-Luminosity LHC (HL-LHC). The reconstruction of charged particle trajectories (tracks) has always been a critical part of offline data processing pipelines. The complexity of HL-LHC data will however increasingly mandate track finding in all stages of an experiment's real-time processing. This paper presents a GNN-based track-finding pipeline tailored for the Run 3 LHCb experiment's vertex detector and benchmarks its physics performance and computational cost against existing classical algorithms on GPU architectures. A novelty of our work compared to existing GNN tracking pipelines is batched execution, in which the GPU evaluates the pipeline on hundreds of events in parallel. We evaluate the impact of neural-network quantisation on physics and computational performance, and comment on the outlook for GNN tracking algorithms for other parts of the LHCb track-finding pipeline.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Neural Network-Based Track Finding in the LHCb Vertex Detector
Correia, Anthony
Giasemis, Fotis I.
Garroum, Nabil
Gligorov, Vladimir Vava
Granado, Bertrand
Instrumentation and Detectors
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
The next decade will see an order of magnitude increase in data collected by high-energy physics experiments, driven by the High-Luminosity LHC (HL-LHC). The reconstruction of charged particle trajectories (tracks) has always been a critical part of offline data processing pipelines. The complexity of HL-LHC data will however increasingly mandate track finding in all stages of an experiment's real-time processing. This paper presents a GNN-based track-finding pipeline tailored for the Run 3 LHCb experiment's vertex detector and benchmarks its physics performance and computational cost against existing classical algorithms on GPU architectures. A novelty of our work compared to existing GNN tracking pipelines is batched execution, in which the GPU evaluates the pipeline on hundreds of events in parallel. We evaluate the impact of neural-network quantisation on physics and computational performance, and comment on the outlook for GNN tracking algorithms for other parts of the LHCb track-finding pipeline.
title Graph Neural Network-Based Track Finding in the LHCb Vertex Detector
topic Instrumentation and Detectors
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2407.12119