GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger

Mostrar otras versiones (1)

Results on the performance and viability of data-parallel algorithms on Graphics Processing Units (GPUs) in the ATLAS Level 2 trigger system are presented. We describe the existing trigger data preparation and track reconstruction algorithms, motivation for their optimization, GPU-parallelized versi...

Descripción completa

Detalles Bibliográficos
Autores principales: Emeliyanov, D, Howard, J
Lenguaje:eng
Publicado: 2012
Materias:
Detectors and Experimental Techniques
Acceso en línea:https://dx.doi.org/10.1088/1742-6596/396/1/012018
http://cds.cern.ch/record/1450130
_version_ 1780924907070160896
author Emeliyanov, D
Howard, J
author_facet Emeliyanov, D
Howard, J
author_sort Emeliyanov, D
collection CERN
description Results on the performance and viability of data-parallel algorithms on Graphics Processing Units (GPUs) in the ATLAS Level 2 trigger system are presented. We describe the existing trigger data preparation and track reconstruction algorithms, motivation for their optimization, GPU-parallelized versions of these algorithms, and a "client-server" solution for hybrid CPU/GPU event processing used for integration of the GPU-oriented algorithms into existing ATLAS trigger software. The resulting speed-up of event processing times obtained with high-luminosity simulated data is presented and discussed.
id cern-1450130
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2012
record_format invenio
spelling cern-14501302019-09-30T06:29:59Zdoi:10.1088/1742-6596/396/1/012018http://cds.cern.ch/record/1450130engEmeliyanov, DHoward, JGPU-Based Tracking Algorithms for the ATLAS High-Level TriggerDetectors and Experimental TechniquesResults on the performance and viability of data-parallel algorithms on Graphics Processing Units (GPUs) in the ATLAS Level 2 trigger system are presented. We describe the existing trigger data preparation and track reconstruction algorithms, motivation for their optimization, GPU-parallelized versions of these algorithms, and a "client-server" solution for hybrid CPU/GPU event processing used for integration of the GPU-oriented algorithms into existing ATLAS trigger software. The resulting speed-up of event processing times obtained with high-luminosity simulated data is presented and discussed.ATL-DAQ-PROC-2012-006oai:cds.cern.ch:14501302012-05-21
spellingShingle Detectors and Experimental Techniques
Emeliyanov, D
Howard, J
GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title_full GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title_fullStr GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title_full_unstemmed GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title_short GPU-Based Tracking Algorithms for the ATLAS High-Level Trigger
title_sort gpu-based tracking algorithms for the atlas high-level trigger
topic Detectors and Experimental Techniques
url https://dx.doi.org/10.1088/1742-6596/396/1/012018
http://cds.cern.ch/record/1450130
work_keys_str_mv AT emeliyanovd gpubasedtrackingalgorithmsfortheatlashighleveltrigger
AT howardj gpubasedtrackingalgorithmsfortheatlashighleveltrigger

Ejemplares similares