Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria

Producción Científica

Detalles Bibliográficos
Autores: Ortega Arranz, Héctor, Torres de la Sierra, Yuri, González Escribano, Arturo, Llanos Ferraris, Diego Rafael
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:España
Institución:Universidad de Valladolid
Repositorio:UVaDOC. Repositorio Documental de la Universidad de Valladolid
OAI Identifier:oai:uvadoc.uva.es:10324/70416
Acceso en línea:https://doi.org/10.1007/s11227-014-1212-z
https://uvadoc.uva.es/handle/10324/70416
Access Level:acceso abierto
Palabra clave:Informática
APSP
Cache configuration
Concurrent kernel
GPU
Kernel characterization
Threadblock size
1203 Ciencia de Los Ordenadores
3304 Tecnología de Los Ordenadores
id ES_d413ecd2e75a31d0263a9912d2fd7c42
oai_identifier_str oai:uvadoc.uva.es:10324/70416
network_acronym_str ES
network_name_str España
repository_id_str
spelling Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteriaOrtega Arranz, HéctorTorres de la Sierra, YuriGonzález Escribano, ArturoLlanos Ferraris, Diego RafaelInformáticaAPSPCache configurationConcurrent kernelGPUKernel characterizationThreadblock size1203 Ciencia de Los Ordenadores3304 Tecnología de Los OrdenadoresProducción CientíficaDuring the last years, GPU manycore devices have demonstrated their usefulness to accelerate computationally intensive problems. Although arriving at a parallelization of a highly parallel algorithm is an affordable task, the optimization of GPU codes is a challenging activity. The main reason for this is the number of parameters, programming choices, and tuning techniques available, many of them related with complex and sometimes hidden architecture details. A useful strategy to systematically attack these optimization problems is to characterize the different kernels of the application, and use this knowledge to select appropriate configuration parameters. The All-Pair Shortest-Path (APSP) problem is a well-known problem in graph theory whose objective is to find the shortest paths between any pairs of nodes in a graph. This problem can be solved by highly parallel and computational intensive tasks, being a good candidate to be exploited by manycore devices. In this paper, we use kernel characterization criteria to optimize an APSP algorithm implementation for NVIDIA GPUs. Our experimental results show that the combined use of proper configuration policies, and the concurrent kernels capability of new CUDA architectures, leads to a performance improvement of up to 62 % with respect to one of the possible configurations recommended by CUDA, considered as baseline.This research has been partially supported by Ministerio de Economía y Competitividad (Spain) and ERDF program of the European Union: CAPAP-H4 network (TIN2011-15734-E), MOGECOPP project (TIN2011-25639); and Junta de Castilla y León (Spain) ATLAS project (VA172A12-2).Springer2014info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://doi.org/10.1007/s11227-014-1212-zhttps://uvadoc.uva.es/handle/10324/70416reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolidinstname:Universidad de ValladolidIngléshttps://link.springer.com/article/10.1007/s11227-014-1212-zinfo:eu-repo/semantics/openAccessoai:uvadoc.uva.es:10324/704162026-06-13T12:44:47Z
dc.title.none.fl_str_mv Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
title Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
spellingShingle Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
Ortega Arranz, Héctor
Informática
APSP
Cache configuration
Concurrent kernel
GPU
Kernel characterization
Threadblock size
1203 Ciencia de Los Ordenadores
3304 Tecnología de Los Ordenadores
title_short Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
title_full Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
title_fullStr Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
title_full_unstemmed Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
title_sort Optimizing an APSP implementation for NVIDIA GPUs using kernel characterization criteria
dc.creator.none.fl_str_mv Ortega Arranz, Héctor
Torres de la Sierra, Yuri
González Escribano, Arturo
Llanos Ferraris, Diego Rafael
author Ortega Arranz, Héctor
author_facet Ortega Arranz, Héctor
Torres de la Sierra, Yuri
González Escribano, Arturo
Llanos Ferraris, Diego Rafael
author_role author
author2 Torres de la Sierra, Yuri
González Escribano, Arturo
Llanos Ferraris, Diego Rafael
author2_role author
author
author
dc.subject.none.fl_str_mv Informática
APSP
Cache configuration
Concurrent kernel
GPU
Kernel characterization
Threadblock size
1203 Ciencia de Los Ordenadores
3304 Tecnología de Los Ordenadores
topic Informática
APSP
Cache configuration
Concurrent kernel
GPU
Kernel characterization
Threadblock size
1203 Ciencia de Los Ordenadores
3304 Tecnología de Los Ordenadores
description Producción Científica
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://doi.org/10.1007/s11227-014-1212-z
https://uvadoc.uva.es/handle/10324/70416
url https://doi.org/10.1007/s11227-014-1212-z
https://uvadoc.uva.es/handle/10324/70416
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv https://link.springer.com/article/10.1007/s11227-014-1212-z
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:UVaDOC. Repositorio Documental de la Universidad de Valladolid
instname:Universidad de Valladolid
instname_str Universidad de Valladolid
reponame_str UVaDOC. Repositorio Documental de la Universidad de Valladolid
collection UVaDOC. Repositorio Documental de la Universidad de Valladolid
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420515564716032
score 15,811543

Similares en LA Referencia