Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer

Autores
Wolfmann, Gustavo; De Giusti, Armando
Año de publicación
2014
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Fil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Multicore - MultiGPU systems are frequently used in supercomputers design. The heterogeneity between both types of processors is a source of problems for the parallel programming: disparity in processing throughput and memory availability. While some problems are faster executed in a GPGPU, when its data size exceeds the memory available, data partition must to be done in order to resolve, and become desirable to use both types of processors. In this paper we present a solution based on Petri Nets to model the algorithm and to guide the execution, balancing the load between the CPUs cores and GPGPUs. The matrix multiplication algorithm is used as testbed. Tests confirm the goodness of the model and highlight the difficulties to address the problem.
http://carla2014.hpclatam.org
Fil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Hardware y Arquitectura de Computadoras
Materia
Computadora paralela
Procesadores heterogéneos
Modelado con Redes de Petri
Multiplicación de matrices
Nivel de accesibilidad
acceso abierto
Condiciones de uso
Repositorio
Repositorio Digital Universitario (UNC)
Institución
Universidad Nacional de Córdoba
OAI Identificador
oai:rdu.unc.edu.ar:11086/28966
Acceder
id RDUUNC_36cb4b279ef98c581c6341862a0dce34
oai_identifier_str oai:rdu.unc.edu.ar:11086/28966
network_acronym_str RDUUNC
repository_id_str 2572
network_name_str Repositorio Digital Universitario (UNC)
spelling Algorithm model and execution based on Petri Nets in an heterogeneous parallel computerWolfmann, GustavoDe Giusti, ArmandoComputadora paralelaProcesadores heterogéneosModelado con Redes de PetriMultiplicación de matricesFil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Multicore - MultiGPU systems are frequently used in supercomputers design. The heterogeneity between both types of processors is a source of problems for the parallel programming: disparity in processing throughput and memory availability. While some problems are faster executed in a GPGPU, when its data size exceeds the memory available, data partition must to be done in order to resolve, and become desirable to use both types of processors. In this paper we present a solution based on Petri Nets to model the algorithm and to guide the execution, balancing the load between the CPUs cores and GPGPUs. The matrix multiplication algorithm is used as testbed. Tests confirm the goodness of the model and highlight the difficulties to address the problem.http://carla2014.hpclatam.orgFil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.Hardware y Arquitectura de Computadoras2014info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdfhttp://hdl.handle.net/11086/28966enginfo:eu-repo/semantics/openAccessreponame:Repositorio Digital Universitario (UNC)instname:Universidad Nacional de Córdobainstacron:UNC2025-09-29T13:43:22Zoai:rdu.unc.edu.ar:11086/28966Institucionalhttps://rdu.unc.edu.ar/Universidad públicaNo correspondehttp://rdu.unc.edu.ar/oai/snrdoca.unc@gmail.comArgentinaNo correspondeNo correspondeNo correspondeopendoar:25722025-09-29 13:43:22.679Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdobafalse
dc.title.none.fl_str_mv Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
title Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
spellingShingle Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
Wolfmann, Gustavo
Computadora paralela
Procesadores heterogéneos
Modelado con Redes de Petri
Multiplicación de matrices
title_short Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
title_full Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
title_fullStr Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
title_full_unstemmed Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
title_sort Algorithm model and execution based on Petri Nets in an heterogeneous parallel computer
dc.creator.none.fl_str_mv Wolfmann, Gustavo
De Giusti, Armando
author Wolfmann, Gustavo
author_facet Wolfmann, Gustavo
De Giusti, Armando
author_role author
author2 De Giusti, Armando
author2_role author
dc.subject.none.fl_str_mv Computadora paralela
Procesadores heterogéneos
Modelado con Redes de Petri
Multiplicación de matrices
topic Computadora paralela
Procesadores heterogéneos
Modelado con Redes de Petri
Multiplicación de matrices
dc.description.none.fl_txt_mv Fil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Multicore - MultiGPU systems are frequently used in supercomputers design. The heterogeneity between both types of processors is a source of problems for the parallel programming: disparity in processing throughput and memory availability. While some problems are faster executed in a GPGPU, when its data size exceeds the memory available, data partition must to be done in order to resolve, and become desirable to use both types of processors. In this paper we present a solution based on Petri Nets to model the algorithm and to guide the execution, balancing the load between the CPUs cores and GPGPUs. The matrix multiplication algorithm is used as testbed. Tests confirm the goodness of the model and highlight the difficulties to address the problem.
http://carla2014.hpclatam.org
Fil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Fil: De Giusti, Armando. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
Hardware y Arquitectura de Computadoras
description Fil: Wolfmann, Gustavo. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Físicas y Naturales. Laboratorio de Computación; Argentina.
publishDate 2014
dc.date.none.fl_str_mv 2014
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11086/28966
url http://hdl.handle.net/11086/28966
dc.language.none.fl_str_mv eng
language eng
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.source.none.fl_str_mv reponame:Repositorio Digital Universitario (UNC)
instname:Universidad Nacional de Córdoba
instacron:UNC
reponame_str Repositorio Digital Universitario (UNC)
collection Repositorio Digital Universitario (UNC)
instname_str Universidad Nacional de Córdoba
instacron_str UNC
institution UNC
repository.name.fl_str_mv Repositorio Digital Universitario (UNC) - Universidad Nacional de Córdoba
repository.mail.fl_str_mv oca.unc@gmail.com
_version_ 1844618954071343104
score 13.070432

Publicaciones similares