CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters

This paper proposes and evaluates CUDAlign 4.0, a parallel strategy to obtain the optimal alignment of huge DNA sequences in multi-GPU platforms, using the exact Smith-Waterman (SW) algorithm. In the first phase of CUDAlign 4.0, a huge Dynamic Programming (DP) matrix is computed by multiple GPUs, wh...

Descripción completa

Detalles Bibliográficos
Autores: De Sandes, Edans, Miranda, Guillermo, Martorell Bofill, Xavier|||0000-0002-0417-3430, Ayguadé Parra, Eduard|||0000-0002-5146-103X, Teodoro, George, de Melo, Alba
Tipo de recurso: artículo
Fecha de publicación:2016
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/99741
Acceso en línea:https://hdl.handle.net/2117/99741
https://dx.doi.org/10.1109/TPDS.2016.2515597
Access Level:acceso abierto
Palabra clave:Parallel programming (Computer science)
Bioinformatics
Sequence alignment
Parallel algorithms
GPU
Programació en paral·lel (Informàtica)
Bioinformàtica
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·leles
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
id ES_b3de85cbbc546e6d26d9be2e36b2ad01
oai_identifier_str oai:upcommons.upc.edu:2117/99741
network_acronym_str ES
network_name_str España
repository_id_str
spelling CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clustersDe Sandes, EdansMiranda, GuillermoMartorell Bofill, Xavier|||0000-0002-0417-3430Ayguadé Parra, Eduard|||0000-0002-5146-103XTeodoro, Georgede Melo, AlbaParallel programming (Computer science)BioinformaticsBioinformaticsSequence alignmentParallel algorithmsGPUProgramació en paral·lel (Informàtica)BioinformàticaÀrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·lelesÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::BioinformàticaThis paper proposes and evaluates CUDAlign 4.0, a parallel strategy to obtain the optimal alignment of huge DNA sequences in multi-GPU platforms, using the exact Smith-Waterman (SW) algorithm. In the first phase of CUDAlign 4.0, a huge Dynamic Programming (DP) matrix is computed by multiple GPUs, which asynchronously communicate border elements to the right neighbor in order to find the optimal score. After that, the traceback phase of SW is executed. The efficient parallelization of the traceback phase is very challenging because of the high amount of data dependency, which particularly impacts the performance and limits the application scalability. In order to obtain a multi-GPU highly parallel traceback phase, we propose and evaluate a new parallel traceback algorithm called Incremental Speculative Traceback (IST), which pipelines the traceback phase, speculating incrementally over the values calculated so far, producing results in advance. With CUDAlign 4.0, we were able to calculate SW matrices with up to 60 Peta cells, obtaining the optimal local alignments of all Human and Chimpanzee homologous chromosomes, whose sizes range from 26 Millions of Base Pairs (MBP) up to 249 MBP. As far as we know, this is the first time such comparison was made with the SW exact method. We also show that the IST algorithm is able to reduce the traceback time from 2.15¿ up to 21.03¿, when compared with the baseline traceback algorithm. The human¿chimpanzee chromosome 5 comparison (180 MBP¿183 MBP) attained 10,370.00 GCUPS (Billions of Cells Updated per Second) using 384 GPUs, with a speculation hit ratio of 98.2%.Peer Reviewed20162016-10-0120172017-01-20journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/99741https://dx.doi.org/10.1109/TPDS.2016.2515597reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengMinisterio de Economía y Competitividad http://doi.org/10.13039/501100003329 TIN2015-65316-P COMPUTACION DE ALTAS PRESTACIONES VIIMinisterio de Economía y Competitividad http://doi.org/10.13039/501100003329 SEV-2015-0493 BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACIONopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/997412026-05-27T15:37:01Z
dc.title.none.fl_str_mv CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
title CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
spellingShingle CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
De Sandes, Edans
Parallel programming (Computer science)
Bioinformatics
Bioinformatics
Sequence alignment
Parallel algorithms
GPU
Programació en paral·lel (Informàtica)
Bioinformàtica
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·leles
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
title_short CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
title_full CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
title_fullStr CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
title_full_unstemmed CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
title_sort CUDAlign 4.0: incremental speculative traceback for exact chromosome-wide alignment in GPU clusters
dc.creator.none.fl_str_mv De Sandes, Edans
Miranda, Guillermo
Martorell Bofill, Xavier|||0000-0002-0417-3430
Ayguadé Parra, Eduard|||0000-0002-5146-103X
Teodoro, George
de Melo, Alba
author De Sandes, Edans
author_facet De Sandes, Edans
Miranda, Guillermo
Martorell Bofill, Xavier|||0000-0002-0417-3430
Ayguadé Parra, Eduard|||0000-0002-5146-103X
Teodoro, George
de Melo, Alba
author_role author
author2 Miranda, Guillermo
Martorell Bofill, Xavier|||0000-0002-0417-3430
Ayguadé Parra, Eduard|||0000-0002-5146-103X
Teodoro, George
de Melo, Alba
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Parallel programming (Computer science)
Bioinformatics
Bioinformatics
Sequence alignment
Parallel algorithms
GPU
Programació en paral·lel (Informàtica)
Bioinformàtica
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·leles
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
topic Parallel programming (Computer science)
Bioinformatics
Bioinformatics
Sequence alignment
Parallel algorithms
GPU
Programació en paral·lel (Informàtica)
Bioinformàtica
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors::Arquitectures paral·leles
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica
description This paper proposes and evaluates CUDAlign 4.0, a parallel strategy to obtain the optimal alignment of huge DNA sequences in multi-GPU platforms, using the exact Smith-Waterman (SW) algorithm. In the first phase of CUDAlign 4.0, a huge Dynamic Programming (DP) matrix is computed by multiple GPUs, which asynchronously communicate border elements to the right neighbor in order to find the optimal score. After that, the traceback phase of SW is executed. The efficient parallelization of the traceback phase is very challenging because of the high amount of data dependency, which particularly impacts the performance and limits the application scalability. In order to obtain a multi-GPU highly parallel traceback phase, we propose and evaluate a new parallel traceback algorithm called Incremental Speculative Traceback (IST), which pipelines the traceback phase, speculating incrementally over the values calculated so far, producing results in advance. With CUDAlign 4.0, we were able to calculate SW matrices with up to 60 Peta cells, obtaining the optimal local alignments of all Human and Chimpanzee homologous chromosomes, whose sizes range from 26 Millions of Base Pairs (MBP) up to 249 MBP. As far as we know, this is the first time such comparison was made with the SW exact method. We also show that the IST algorithm is able to reduce the traceback time from 2.15¿ up to 21.03¿, when compared with the baseline traceback algorithm. The human¿chimpanzee chromosome 5 comparison (180 MBP¿183 MBP) attained 10,370.00 GCUPS (Billions of Cells Updated per Second) using 384 GPUs, with a speculation hit ratio of 98.2%.
publishDate 2016
dc.date.none.fl_str_mv 2016
2016-10-01
2017
2017-01-20
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/99741
https://dx.doi.org/10.1109/TPDS.2016.2515597
url https://hdl.handle.net/2117/99741
https://dx.doi.org/10.1109/TPDS.2016.2515597
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://doi.org/10.13039/501100003329 TIN2015-65316-P COMPUTACION DE ALTAS PRESTACIONES VII
Ministerio de Economía y Competitividad http://doi.org/10.13039/501100003329 SEV-2015-0493 BARCELONA SUPERCOMPUTING CENTER - CENTRO. NACIONAL DE SUPERCOMPUTACION
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417213403856896
score 15.301629

Similares en LA Referencia