A Comparison of CPU and GPU implementations for the LHCb Experiment Run   3 Trigger

R. Aaij; M. Adinolfi; S. Aiola; S. Akar; J. Albrecht; M. Alexander; S.; Amato; Y. Amhis; F. Archilli; M. Bala; G. Bassi; L. Bian; M.P. Blago; T.; Boettcher; A. Boldyrev; S. Borghi; A. Brea Rodriguez; L. Calefice; M. Calvo; Gomez; D.H. C\'ampora P\'erez; A. Cardini; M. Cattaneo; V. Chobanova; G.; Ciezarek; X. Cid Vidal; J.L. Cobbledick; J.A.B. Coelho; T. Colombo; A. Contu,; B. Couturier; D.C. Craik; R. Currie; P. d'Argent; M. De Cian; D. Derkach; F.; Dordei; M. Dorigo; L. Dufour; P. Durante; A. Dziurda; A. Dzyuba; S. Easo; S.; Esen; P. Fernandez Declara; S. Filippov; C. Fitzpatrick; M. Frank; P.; Gandini; V.V. Gligorov; E. Golobardes; G. Graziani; L. Grillo; P. A.; G\"unther; S. Hansmann-Menzemer; A.M. Hennequin; L. Henry; D. Hill; S.E.; Hollitt; J. Hu; W. Hulsbergen; R.J. Hunter; M. Hushchyn; B.K. Jashal; C.R.; Jones; S. Klaver; K. Klimaszewski; R. Kopecna; W. Krzemien; M. Kucharczyk; R.; Lane; F. Lazzari; R. Le Gac; P. Li; J.H. Lopes; M. Lucio Martinez; A. Lupato,; O. Lupton; X. Lyu; F. Machefert; O. Madejczyk; S. Malde; J.F. Marchand; S.; Mariani; C. Marin Benito; D. Martinez Santos; F. Martinez Vidal; R. Matev; M.; Mazurek; B. Mitreska; D.S. Mitzel; M.J. Morello; H. Mu; P. Muzzetto; P. Naik,; M. Needham; N. Neri; N. Neufeld; N.S. Nolte; D. O'Hanlon; A. Oyanguren; M.; Pepe Altarelli; S. Petrucci; M. Petruzzo; L. Pica; F. Pisani; A. Piucci; F.; Polci; A. Poluektov; E. Polycarpo; C. Prouve; G. Punzi; R. Quagliani; R.I.; Rabadan Trejo; M. Ramos Pernas; M.S. Rangel; F. Ratnikov; G. Raven; F. Reiss,; V. Renaudin; P. Robbe; A. Ryzhikov; M. Santimaria; M. Saur; M. Schiller; R.; Schwemmer; B. Sciascia; A. Solomin; F. Suljik; N. Skidmore; M.D. Sokoloff; P.; Spradlin; M. Stahl; S. Stahl; H. Stevens; L. Sun; A. Szabelski; T. Szumlak,; M. Szymanski; D.Y. Tou; G. Tuci; A. Usachov; N. Valls Canudas; R. Vazquez; Gomez; S. Vecchi; M. Vesterinen; X. Vilasis-Cardona; D. Vom Bruch; Z. Wang,; T. Wojton; M. Whitehead; M. Williams; M. Witek; Y. Xie; A. Xu; H. Yin; M.; Zdybal; O. Zenaiev; D. Zhang; L. Zhang; X. Zhu

arXiv:2105.04031·physics.ins-det·January 6, 2022·Comput. Softw. Big Sci.

A Comparison of CPU and GPU implementations for the LHCb Experiment Run 3 Trigger

R. Aaij, M. Adinolfi, S. Aiola, S. Akar, J. Albrecht, M. Alexander, S., Amato, Y. Amhis, F. Archilli, M. Bala, G. Bassi, L. Bian, M.P. Blago, T., Boettcher, A. Boldyrev, S. Borghi, A. Brea Rodriguez, L. Calefice, M. Calvo, Gomez, D.H. C\'ampora P\'erez, A. Cardini, M. Cattaneo

PDF

TL;DR

This paper compares CPU and GPU implementations of the LHCb experiment's trigger system for Run 3, evaluating performance to determine the most effective approach for the upgraded fully software-based trigger.

Contribution

It provides a detailed comparison and evaluation of CPU and GPU implementations for the LHCb trigger, leading to the selection of GPU as the baseline.

Findings

01

Both CPU and GPU options are viable for the trigger system.

02

The GPU implementation was chosen as the baseline after evaluation.

03

Performance details support the upgrade to a fully software-based trigger.

Abstract

The LHCb experiment at CERN is undergoing an upgrade in preparation for the Run 3 data taking period of the LHC. As part of this upgrade the trigger is moving to a fully software implementation operating at the LHC bunch crossing rate. We present an evaluation of a CPU-based and a GPU-based implementation of the first stage of the High Level Trigger. After a detailed comparison both options are found to be viable. This document summarizes the performance and implementation details of these options, the outcome of which has led to the choice of the GPU-based implementation as the baseline.

Peer Reviews

No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.

Videos

No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.