TY - JOUR
T1 - Performance of a geometric deep learning pipeline for HL-LHC particle tracking
AU - Ju, Xiangyang
AU - Murnane, Daniel
AU - Calafiura, Paolo
AU - Choma, Nicholas
AU - Conlon, Sean
AU - Farrell, Steven
AU - Xu, Yaoyuan
AU - Spiropulu, Maria
AU - Vlimant, Jean Roch
AU - Aurisano, Adam
AU - Hewes, Jeremy
AU - Cerati, Giuseppe
AU - Gray, Lindsey
AU - Klijnsma, Thomas
AU - Kowalkowski, Jim
AU - Atkinson, Markus
AU - Neubauer, Mark
AU - DeZoort, Gage
AU - Thais, Savannah
AU - Chauhan, Aditi
AU - Schuy, Alex
AU - Hsu, Shih Chieh
AU - Ballow, Alex
AU - Lazar, Alina
N1 - Funding Information:
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.
Funding Information:
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.
Publisher Copyright:
© 2021, The Author(s).
PY - 2021/10
Y1 - 2021/10
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85116468566&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116468566&partnerID=8YFLogxK
U2 - 10.1140/epjc/s10052-021-09675-8
DO - 10.1140/epjc/s10052-021-09675-8
M3 - Article
AN - SCOPUS:85116468566
SN - 1434-6044
VL - 81
JO - European Physical Journal C
JF - European Physical Journal C
IS - 10
M1 - 876
ER -