Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations

The path to the efficient exploitation of molecular dynamics simulators is strongly driven by the increasingly intensive use of accelerators. However, they suffer performance portability issues, making it necessary both to achieve technological combinations that allow taking advantage of each progra...

Descripción completa

Detalles Bibliográficos
Autores: Nozal, Raúl|||0000-0002-4927-9829, Bosque Orero, José Luis|||0000-0002-7718-8449
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/28379
Acceso en línea:https://hdl.handle.net/10902/28379
Access Level:acceso abierto
Palabra clave:Load balancing
Co-execution
Hybrid programming models
HPC
Molecular dynamics
OpenMP
OpenCL
C++
CPU-GPU-MIC
Accelerators
id ES_c6cebfc08f779a49a866238bcc1dfb4e
oai_identifier_str oai:repositorio.unican.es:10902/28379
network_acronym_str ES
network_name_str España
repository_id_str
spelling Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulationsNozal, Raúl|||0000-0002-4927-9829Bosque Orero, José Luis|||0000-0002-7718-8449Load balancingCo-executionHybrid programming modelsHPCMolecular dynamicsOpenMPOpenCLC++CPU-GPU-MICAcceleratorsThe path to the efficient exploitation of molecular dynamics simulators is strongly driven by the increasingly intensive use of accelerators. However, they suffer performance portability issues, making it necessary both to achieve technological combinations that allow taking advantage of each programming model and device, and to define more effective load distribution strategies that consider the simulation conditions. In this work, a new load balancing algorithm is presented, together with a set of optimizations to support hybrid co-execution in a runtime system for heterogeneous computing. The new extended design enables the exploitation of custom kernels and acceleration technologies altogether, being encapsulated for the rest of the runtime and its scheduling system. With this support, Mash algorithm allows to simultaneously leverage different workload distribution strategies, benefiting from the most advantageous one per device and technology. Experiments show that these proposals achieve an efficiency close to 0.90 and an energy efficiency improvement around 1.80 over the original optimized version.This work has been supported by the Spanish Ministry of Education (FPU16/03299 grant), the Spanish Science and Technology Commission under contract PID2019-105660RB-C22 and performed under the Project HPC-EUROPA3 (INFRAIA-2016-1-730897), with the support of the EC Research Innovation Action (H2020). The author gratefully acknowledges the support of the SPMT group, part of HLRS.Kluwer Academic PublishersUniversidad de Cantabria20232023-01-01journal articlehttp://purl.org/coar/resource_type/c_6501NAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/articlehttps://hdl.handle.net/10902/28379Journal of Supercomputing, 2023, 79, 1065-1080reponame:UCrea Repositorio Abierto de la Universidad de Cantabriainstname:Universidad de Cantabria (UC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositorio.unican.es:10902/283792026-06-02T12:39:31Z
dc.title.none.fl_str_mv Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
title Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
spellingShingle Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
Nozal, Raúl|||0000-0002-4927-9829
Load balancing
Co-execution
Hybrid programming models
HPC
Molecular dynamics
OpenMP
OpenCL
C++
CPU-GPU-MIC
Accelerators
title_short Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
title_full Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
title_fullStr Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
title_full_unstemmed Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
title_sort Mashing load balancing algorithm to boost hybrid kernels in molecular dynamics simulations
dc.creator.none.fl_str_mv Nozal, Raúl|||0000-0002-4927-9829
Bosque Orero, José Luis|||0000-0002-7718-8449
author Nozal, Raúl|||0000-0002-4927-9829
author_facet Nozal, Raúl|||0000-0002-4927-9829
Bosque Orero, José Luis|||0000-0002-7718-8449
author_role author
author2 Bosque Orero, José Luis|||0000-0002-7718-8449
author2_role author
dc.contributor.none.fl_str_mv Universidad de Cantabria
dc.subject.none.fl_str_mv Load balancing
Co-execution
Hybrid programming models
HPC
Molecular dynamics
OpenMP
OpenCL
C++
CPU-GPU-MIC
Accelerators
topic Load balancing
Co-execution
Hybrid programming models
HPC
Molecular dynamics
OpenMP
OpenCL
C++
CPU-GPU-MIC
Accelerators
description The path to the efficient exploitation of molecular dynamics simulators is strongly driven by the increasingly intensive use of accelerators. However, they suffer performance portability issues, making it necessary both to achieve technological combinations that allow taking advantage of each programming model and device, and to define more effective load distribution strategies that consider the simulation conditions. In this work, a new load balancing algorithm is presented, together with a set of optimizations to support hybrid co-execution in a runtime system for heterogeneous computing. The new extended design enables the exploitation of custom kernels and acceleration technologies altogether, being encapsulated for the rest of the runtime and its scheduling system. With this support, Mash algorithm allows to simultaneously leverage different workload distribution strategies, benefiting from the most advantageous one per device and technology. Experiments show that these proposals achieve an efficiency close to 0.90 and an energy efficiency improvement around 1.80 over the original optimized version.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10902/28379
url https://hdl.handle.net/10902/28379
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
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Kluwer Academic Publishers
publisher.none.fl_str_mv Kluwer Academic Publishers
dc.source.none.fl_str_mv Journal of Supercomputing, 2023, 79, 1065-1080
reponame:UCrea Repositorio Abierto de la Universidad de Cantabria
instname:Universidad de Cantabria (UC)
instname_str Universidad de Cantabria (UC)
reponame_str UCrea Repositorio Abierto de la Universidad de Cantabria
collection UCrea Repositorio Abierto de la Universidad de Cantabria
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419103942344704
score 15,300719

Similares en LA Referencia