Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms

Data- parallel applications running on heterogeneous high-performance computing platforms require a nonuniform distribution of the workload between available processes. Data partitioning algorithms are formulated as an optimization problem. Departing from the computational performance models of the...

Full description

Bibliographic Details
Authors: Rico Gallego, Juan Antonio, Díaz Martín, Juan Carlos, Moreno Álvarez, Sergio, Calvo Jurado, Carmen, García Zapata, Juan Luis
Format: article
Publication Date:2019
Country:España
Institution:Universidad Nacional de Educación a Distancia
Repository:e-spacio. Repositorio Institucional de la UNED
Language:English
OAI Identifier:oai:e-spacio.uned.es:20.500.14468/24383
Online Access:https://hdl.handle.net/20.500.14468/24383
Access Level:Open access
Keyword:12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
communication optimization
communication performance models
data-parallel kernels
heterogeneous platforms
partitioning algorithms
id ES_b9cd18b8d776fbc64e19f2c152f209e9
oai_identifier_str oai:e-spacio.uned.es:20.500.14468/24383
network_acronym_str ES
network_name_str España
repository_id_str
spelling Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platformsRico Gallego, Juan AntonioDíaz Martín, Juan CarlosMoreno Álvarez, SergioCalvo Jurado, CarmenGarcía Zapata, Juan Luis12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informáticacommunication optimizationcommunication performance modelsdata-parallel kernelsheterogeneous platformspartitioning algorithmsData- parallel applications running on heterogeneous high-performance computing platforms require a nonuniform distribution of the workload between available processes. Data partitioning algorithms are formulated as an optimization problem. Departing from the computational performance models of the processes, the goal is to find the partition that minimizes the communication cost. Traditionally, communication volume is the metric used to guide the partitioning. This metric, however, is unable to capture the complexity of current heterogeneous systems, which show uneven communication channels and execute applications with different communication patterns. In this paper, we discuss the role of analytical communication performance models as a metric in partitioning algorithms. First, we describe a method to programmatically predict the communication cost of a data-parallel kernel based on the τ-Lop analytical model. We show that this figure better captures the communication features of applications and platforms. We present results showing that this approach builds partitions that equal or improve the performance of data parallel applications on heterogeneous platforms with respect to previous volume-based strategies.Wileyhttps://orcid.org/0000-0002-4264-7473https://orcid.org/0000-0002-8435-3844https://orcid.org/0000-0001-9842-081Xhttps://orcid.org/0000-0003-1419-1672e-Spacio UNED20242024-11-1520192019-01-0120192019-01-01journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14468/24383reponame:e-spacio. Repositorio Institucional de la UNEDinstname:Universidad Nacional de Educación a DistanciaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.esoai:e-spacio.uned.es:20.500.14468/243832026-06-06T12:38:31Z
dc.title.none.fl_str_mv Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
title Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
spellingShingle Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
Rico Gallego, Juan Antonio
12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
communication optimization
communication performance models
data-parallel kernels
heterogeneous platforms
partitioning algorithms
title_short Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
title_full Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
title_fullStr Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
title_full_unstemmed Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
title_sort Performance evaluation of model-driven partitioning algorithms for data-parallel kernels on heterogeneous platforms
dc.creator.none.fl_str_mv Rico Gallego, Juan Antonio
Díaz Martín, Juan Carlos
Moreno Álvarez, Sergio
Calvo Jurado, Carmen
García Zapata, Juan Luis
author Rico Gallego, Juan Antonio
author_facet Rico Gallego, Juan Antonio
Díaz Martín, Juan Carlos
Moreno Álvarez, Sergio
Calvo Jurado, Carmen
García Zapata, Juan Luis
author_role author
author2 Díaz Martín, Juan Carlos
Moreno Álvarez, Sergio
Calvo Jurado, Carmen
García Zapata, Juan Luis
author2_role author
author
author
author
dc.contributor.none.fl_str_mv https://orcid.org/0000-0002-4264-7473
https://orcid.org/0000-0002-8435-3844
https://orcid.org/0000-0001-9842-081X
https://orcid.org/0000-0003-1419-1672
e-Spacio UNED
dc.subject.none.fl_str_mv 12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
communication optimization
communication performance models
data-parallel kernels
heterogeneous platforms
partitioning algorithms
topic 12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
communication optimization
communication performance models
data-parallel kernels
heterogeneous platforms
partitioning algorithms
description Data- parallel applications running on heterogeneous high-performance computing platforms require a nonuniform distribution of the workload between available processes. Data partitioning algorithms are formulated as an optimization problem. Departing from the computational performance models of the processes, the goal is to find the partition that minimizes the communication cost. Traditionally, communication volume is the metric used to guide the partitioning. This metric, however, is unable to capture the complexity of current heterogeneous systems, which show uneven communication channels and execute applications with different communication patterns. In this paper, we discuss the role of analytical communication performance models as a metric in partitioning algorithms. First, we describe a method to programmatically predict the communication cost of a data-parallel kernel based on the τ-Lop analytical model. We show that this figure better captures the communication features of applications and platforms. We present results showing that this approach builds partitions that equal or improve the performance of data parallel applications on heterogeneous platforms with respect to previous volume-based strategies.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-01-01
2019
2019-01-01
2024
2024-11-15
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14468/24383
url https://hdl.handle.net/20.500.14468/24383
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Wiley
publisher.none.fl_str_mv Wiley
dc.source.none.fl_str_mv reponame:e-spacio. Repositorio Institucional de la UNED
instname:Universidad Nacional de Educación a Distancia
instname_str Universidad Nacional de Educación a Distancia
reponame_str e-spacio. Repositorio Institucional de la UNED
collection e-spacio. Repositorio Institucional de la UNED
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417803625267200
score 15,81155

Similar Items