LHCb GPU Acceleration Project

The LHCb detector is due to be upgraded for processing high-luminosity collisions, which will increase the load on its computation infrastructure from 100 GB/s to 4 TB/s, encouraging us to look for new ways of accelerating the Online reconstruction. The Coprocessor Manager is our new framework for i...

Descripción completa

Detalles Bibliográficos
Autores principales: Badalov, Alexey, Campora Perez, Daniel Hugo, Neufeld, Niko, Vilasis Cardona, Xavier
Lenguaje:eng
Publicado: 2015
Materias:
Particle Physics - Experiment
Acceso en línea:https://dx.doi.org/10.1088/1748-0221/11/01/P01001
http://cds.cern.ch/record/2049247
_version_ 1780948030009114624
author Badalov, Alexey
Campora Perez, Daniel Hugo
Neufeld, Niko
Vilasis Cardona, Xavier
author_facet Badalov, Alexey
Campora Perez, Daniel Hugo
Neufeld, Niko
Vilasis Cardona, Xavier
author_sort Badalov, Alexey
collection CERN
description The LHCb detector is due to be upgraded for processing high-luminosity collisions, which will increase the load on its computation infrastructure from 100 GB/s to 4 TB/s, encouraging us to look for new ways of accelerating the Online reconstruction. The Coprocessor Manager is our new framework for integrating LHCb’s existing computation pipelines with massively parallel algorithms running on GPUs and other accelerators. This paper describes the system and analyzes its performance.
id cern-2049247
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2015
record_format invenio
spelling cern-20492472022-08-10T12:45:22Zdoi:10.1088/1748-0221/11/01/P01001http://cds.cern.ch/record/2049247engBadalov, AlexeyCampora Perez, Daniel HugoNeufeld, NikoVilasis Cardona, XavierLHCb GPU Acceleration ProjectParticle Physics - ExperimentThe LHCb detector is due to be upgraded for processing high-luminosity collisions, which will increase the load on its computation infrastructure from 100 GB/s to 4 TB/s, encouraging us to look for new ways of accelerating the Online reconstruction. The Coprocessor Manager is our new framework for integrating LHCb’s existing computation pipelines with massively parallel algorithms running on GPUs and other accelerators. This paper describes the system and analyzes its performance.LHCb-PUB-2015-021CERN-LHCb-PUB-2015-021oai:cds.cern.ch:20492472015-09-04
spellingShingle Particle Physics - Experiment
Badalov, Alexey
Campora Perez, Daniel Hugo
Neufeld, Niko
Vilasis Cardona, Xavier
LHCb GPU Acceleration Project
title LHCb GPU Acceleration Project
title_full LHCb GPU Acceleration Project
title_fullStr LHCb GPU Acceleration Project
title_full_unstemmed LHCb GPU Acceleration Project
title_short LHCb GPU Acceleration Project
title_sort lhcb gpu acceleration project
topic Particle Physics - Experiment
url https://dx.doi.org/10.1088/1748-0221/11/01/P01001
http://cds.cern.ch/record/2049247
work_keys_str_mv AT badalovalexey lhcbgpuaccelerationproject
AT camporaperezdanielhugo lhcbgpuaccelerationproject
AT neufeldniko lhcbgpuaccelerationproject
AT vilasiscardonaxavier lhcbgpuaccelerationproject

Ejemplares similares