Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461
Autor(a) principal: | |
---|---|
Data de Publicação: | 2008 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Acta scientiarum. Technology (Online) |
Texto Completo: | http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/5461 |
Resumo: | Computer cluster performance is directly related to how the workload is distributed among its nodes. Task scheduling techniques are employed to optimize the usage of system resources, thus improving the performance of parallel applications. This work presents an extension to the LAM/MPI library that allows process scheduling to be done more efficiently than in its original implementation. Tests performed with three MPI applications, running on an 8-node cluster, show that our solutions can reduce execution time by over 50% in most cases. |
id |
UEM-6_8cef3abbcf59f085f34a506e34ad1e85 |
---|---|
oai_identifier_str |
oai:periodicos.uem.br/ojs:article/5461 |
network_acronym_str |
UEM-6 |
network_name_str |
Acta scientiarum. Technology (Online) |
repository_id_str |
|
spelling |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461Estendendo o escalonamento de tarefas da biblioteca LAM/MPI - DOI: 10.4025/actascitechnol.v30i2.5461task schedulingdistributed applicationsLAM/MPIescalonamento de tarefasaplicações distribuídasLAM/MPI.Computer cluster performance is directly related to how the workload is distributed among its nodes. Task scheduling techniques are employed to optimize the usage of system resources, thus improving the performance of parallel applications. This work presents an extension to the LAM/MPI library that allows process scheduling to be done more efficiently than in its original implementation. Tests performed with three MPI applications, running on an 8-node cluster, show that our solutions can reduce execution time by over 50% in most cases.O desempenho dos clusters de computadores está diretamente relacionado à forma como a carga de trabalho é distribuída entre os nós. Neste sentido, técnicas de escalonamento de tarefas são usadas para otimizar o uso dos recursos do sistema, aumentando o desempenho das aplicações paralelas. Este trabalho apresenta uma extensão da biblioteca LAM/MPI (Local Area Multicomputer MPI), que permite escalonar processos de forma mais eficiente do que o método original. Testes realizados em três aplicações MPI, em um cluster de oito nós, mostraram que nossos mecanismos podem reduzir o tempo de execução em mais de 50% em várias situações.Universidade Estadual De Maringá2008-10-20info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/546110.4025/actascitechnol.v30i2.5461Acta Scientiarum. Technology; Vol 30 No 2 (2008); 125-133Acta Scientiarum. Technology; v. 30 n. 2 (2008); 125-1331806-25631807-8664reponame:Acta scientiarum. Technology (Online)instname:Universidade Estadual de Maringá (UEM)instacron:UEMporhttp://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/5461/5461Valle Rego Gorino, FabioMartini, João Angelode Lara Gonçalves, Ronaldo Augustoinfo:eu-repo/semantics/openAccess2024-05-17T13:03:03Zoai:periodicos.uem.br/ojs:article/5461Revistahttps://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/indexPUBhttps://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/oai||actatech@uem.br1807-86641806-2563opendoar:2024-05-17T13:03:03Acta scientiarum. Technology (Online) - Universidade Estadual de Maringá (UEM)false |
dc.title.none.fl_str_mv |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 Estendendo o escalonamento de tarefas da biblioteca LAM/MPI - DOI: 10.4025/actascitechnol.v30i2.5461 |
title |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
spellingShingle |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 Valle Rego Gorino, Fabio task scheduling distributed applications LAM/MPI escalonamento de tarefas aplicações distribuídas LAM/MPI. |
title_short |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
title_full |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
title_fullStr |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
title_full_unstemmed |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
title_sort |
Extending the task scheduling of the LAM/MPI library - DOI: 10.4025/actascitechnol.v30i2.5461 |
author |
Valle Rego Gorino, Fabio |
author_facet |
Valle Rego Gorino, Fabio Martini, João Angelo de Lara Gonçalves, Ronaldo Augusto |
author_role |
author |
author2 |
Martini, João Angelo de Lara Gonçalves, Ronaldo Augusto |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Valle Rego Gorino, Fabio Martini, João Angelo de Lara Gonçalves, Ronaldo Augusto |
dc.subject.por.fl_str_mv |
task scheduling distributed applications LAM/MPI escalonamento de tarefas aplicações distribuídas LAM/MPI. |
topic |
task scheduling distributed applications LAM/MPI escalonamento de tarefas aplicações distribuídas LAM/MPI. |
description |
Computer cluster performance is directly related to how the workload is distributed among its nodes. Task scheduling techniques are employed to optimize the usage of system resources, thus improving the performance of parallel applications. This work presents an extension to the LAM/MPI library that allows process scheduling to be done more efficiently than in its original implementation. Tests performed with three MPI applications, running on an 8-node cluster, show that our solutions can reduce execution time by over 50% in most cases. |
publishDate |
2008 |
dc.date.none.fl_str_mv |
2008-10-20 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/5461 10.4025/actascitechnol.v30i2.5461 |
url |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/5461 |
identifier_str_mv |
10.4025/actascitechnol.v30i2.5461 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://www.periodicos.uem.br/ojs/index.php/ActaSciTechnol/article/view/5461/5461 |
dc.rights.driver.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 |
Universidade Estadual De Maringá |
publisher.none.fl_str_mv |
Universidade Estadual De Maringá |
dc.source.none.fl_str_mv |
Acta Scientiarum. Technology; Vol 30 No 2 (2008); 125-133 Acta Scientiarum. Technology; v. 30 n. 2 (2008); 125-133 1806-2563 1807-8664 reponame:Acta scientiarum. Technology (Online) instname:Universidade Estadual de Maringá (UEM) instacron:UEM |
instname_str |
Universidade Estadual de Maringá (UEM) |
instacron_str |
UEM |
institution |
UEM |
reponame_str |
Acta scientiarum. Technology (Online) |
collection |
Acta scientiarum. Technology (Online) |
repository.name.fl_str_mv |
Acta scientiarum. Technology (Online) - Universidade Estadual de Maringá (UEM) |
repository.mail.fl_str_mv |
||actatech@uem.br |
_version_ |
1799315333220139008 |