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

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 implemen...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	arXiv.org 2022-01
Hauptverfasser:	Aaij, R, Adinolfi, M, Aiola, S, Akar, S, Alexander, M, Archilli, F, Bassi, G, Blago, M P, Boettcher, T, Boldyrev, A, A Brea Rodriguez, Calefice, L, M Calvo Gomez, Cardini, A, Cattaneo, M, X Cid Vidal, Cobbledick, J L, Coelho, J A B, Colombo, T, Couturier, B, Currie, R, d'Argent, P, De Cian, M, Derkach, D, Dordei, F, Dorigo, M, Dufour, L, Durante, P, Dzyuba, A, Esen, S, P Fernandez Declara, Filippov, S, Frank, M, Golobardes, E, Graziani, G, Grillo, L, Hansmann-Menzemer, S, Hennequin, A M, Hill, D, J Hu, Hulsbergen, W, Kopecna, R, P Li, M Lucio Martinez, Lupato, A, Lyu, X, Machefert, F, Madejczyk, O, Marchand, J F, Mariani, S, D Martinez Santos, F Martinez Vidal, Matev, R, Mazurek, M, Mitzel, D S, Morello, M J, Muzzetto, P, Naik, P, Neri, N, Neufeld, N, O'Hanlon, D, M Pepe Altarelli, Petrucci, S, Petruzzo, M, Piucci, A, Polci, F, Prouve, C, M Ramos Pernas, Rangel, M S, Ratnikov, F, Raven, G, Reiss, F, Renaudin, V, Robbe, P, Ryzhikov, A, Santimaria, M, Saur, M, Schiller, M, Sciascia, B, Solomin, A, Sokoloff, M D, Stevens, H, Sun, L, Szabelski, A, Szymanski, M, Tou, D Y, Tuci, G, N Valls Canudas, R Vazquez Gomez, Vecchi, S, Vesterinen, M, Wojton, T, Whitehead, M, Xie, Y, A Xu, Yin, H, Zdybal, M, Zhang, D, Zhang, L, Zhu, X
Format:	Artikel
Sprache:	eng
Schlagworte:	Graphics processing units Large Hadron Collider Physics - Instrumentation and Detectors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.
ISSN:	2331-8422
DOI:	10.48550/arxiv.2105.04031