Performance of a geometric deep learning pipeline for HL-LHC particle tracking

Creators: Ju, Xiangyang; Murnane, Daniel; Calafiura, Paolo; Choma, Nicholas; Conlon, Sean; Farrell, Steven; Xu, Yaoyuan; Spiropulu, Maria; Vlimant, Jean-Roch; Aurisano, Adam; Hewes, Jeremy; Cerati, Giuseppe; Gray, Lindsey; Klijnsma, Thomas; Kowalkowski, Jim; Atkinson, Markus; Neubauer, Mark; DeZoort, Gage; Thais, Savannah; Chauhan, Aditi; Schuy, Alex; Hsu, Shih-Chieh; Ballow, Alex; Lazar, Alina

Style

An error occurred while generating the citation.

Abstract

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX's tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

Additional Information

© The Author(s) 2021. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Received 03 May 2021; Accepted 21 September 2021; Published 06 October 2021. This research was supported in part by: − the U.S. Department of Energy's Office of Science, Office of High Energy Physics, under Contracts No. DE-AC02-05CH11231 (CompHEP Exa.TrkX) and No. DE-AC02-07CH11359 (FNAL LDRD 2019.017); − the Exascale Computing Project (17-SC-20-SC), a joint project of DOE's Office of Science and the National Nuclear Security Administration; the National Science Foundation under Cooperative Agreement OAC-1836650. This research used resources of the National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility located at Lawrence Berkeley National Laboratory, operated under Contract No. DE-AC02-05CH11231. We are grateful to Google Co. for providing early access to Nvidia A100 instances in the context of the US ATLAS/Google Cloud Platform collaboration. Finally, we thank Marcin Wolter (IFJ PAN), Ben Nachman, Alex Sim and Kesheng Wu (LBNL) for the useful discussions. Data Availability Statement: This manuscript has associated data in a data repository. [Authors' comment: https://competitions.codalab.org/competitions/20112.]

Attached Files

Published - Ju2021_Article_PerformanceOfAGeometricDeepLea.pdf

Accepted Version - 2103.06995.pdf

Files

2103.06995.pdf

Files (8.8 MB)

Name	Size	Download all
2103.06995.pdf md5:f5acd0962b2ee0b3185c0b36d6b979be	2.7 MB	Preview Download
Ju2021_Article_PerformanceOfAGeometricDeepLea.pdf md5:067e108e8df55fe501517f211ff94e34	6.0 MB	Preview Download

Additional details

	All versions	This version
Views	0	0
Downloads	0	0
Data volume	0 Bytes	0 Bytes