Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures

Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures

We present the implementation of a full electronic structure calculation code on a hybrid parallel architecture with graphic processing units (GPUs). This implementation is performed on a free software code based on Daubechies wavelets. Such code shows very good performances, systematic convergence...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of chemical physics 2009, Vol.131
Hauptverfasser: Genovese, Luigi, Ospici, Matthieu, Deutsch, Thierry, Mehaut, Jean-François, Neelov, A., Goedecker, S.
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science
Distributed, Parallel, and Cluster Computing
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title The Journal of chemical physics
container_volume 131
creator Genovese, Luigi
Ospici, Matthieu
Deutsch, Thierry
Mehaut, Jean-François
Neelov, A.
Goedecker, S.
description We present the implementation of a full electronic structure calculation code on a hybrid parallel architecture with graphic processing units (GPUs). This implementation is performed on a free software code based on Daubechies wavelets. Such code shows very good performances, systematic convergence properties, and an excellent efficiency on parallel computers. Our GPU-based acceleration fully preserves all these properties. In particular, the code is able to run on many cores which may or may not have a GPU associated, and thus on parallel and massive parallel hybrid machines. With double precision calculations, we may achieve considerable speedup, between a factor of 20 for some operations and a factor of 6 for the whole density functional theory code.
doi_str_mv 10.1063/1.3166140
format Article
fullrecord <record><control><sourceid>hal</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_00788907v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_HAL_hal_00788907v1</sourcerecordid><originalsourceid>FETCH-hal_primary_oai_HAL_hal_00788907v13</originalsourceid><addsrcrecordid>eNqVisFqg0AURYfQQmybRf5gtl1M-p7KqMtga11k4SJZy-t0ghNGDTNamL-vQn-gcODCuYexPcIBQSZveEhQSkxhwyKEvBCZLOCBRQAxikKC3LIn728AgFmcRqx514M3U-DVPKjJjANZfu706AIvyarZ0ir5Qk9DEGp02vM6fDnzzcvmIj6bCyenOjNpNc3L-cIer2S93v3tM3utPs5lLTqy7d2ZnlxoRzJtfTy1qwPI8ryA7AeT_7S_fDVHOQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures</title><source>AIP Journals Complete</source><source>AIP Digital Archive</source><source>Alma/SFX Local Collection</source><creator>Genovese, Luigi ; Ospici, Matthieu ; Deutsch, Thierry ; Mehaut, Jean-François ; Neelov, A. ; Goedecker, S.</creator><creatorcontrib>Genovese, Luigi ; Ospici, Matthieu ; Deutsch, Thierry ; Mehaut, Jean-François ; Neelov, A. ; Goedecker, S.</creatorcontrib><description>We present the implementation of a full electronic structure calculation code on a hybrid parallel architecture with graphic processing units (GPUs). This implementation is performed on a free software code based on Daubechies wavelets. Such code shows very good performances, systematic convergence properties, and an excellent efficiency on parallel computers. Our GPU-based acceleration fully preserves all these properties. In particular, the code is able to run on many cores which may or may not have a GPU associated, and thus on parallel and massive parallel hybrid machines. With double precision calculations, we may achieve considerable speedup, between a factor of 20 for some operations and a factor of 6 for the whole density functional theory code.</description><identifier>ISSN: 0021-9606</identifier><identifier>EISSN: 1089-7690</identifier><identifier>DOI: 10.1063/1.3166140</identifier><language>eng</language><publisher>American Institute of Physics</publisher><subject>Computer Science ; Distributed, Parallel, and Cluster Computing</subject><ispartof>The Journal of chemical physics, 2009, Vol.131</ispartof><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0003-1047-7462 ; 0000-0003-1747-0247 ; 0000-0001-7503-3390 ; 0000-0003-1747-0247 ; 0000-0001-7503-3390 ; 0000-0003-1047-7462</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,315,782,786,887,4026,27930,27931,27932</link.rule.ids><backlink>$$Uhttps://inria.hal.science/hal-00788907$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Genovese, Luigi</creatorcontrib><creatorcontrib>Ospici, Matthieu</creatorcontrib><creatorcontrib>Deutsch, Thierry</creatorcontrib><creatorcontrib>Mehaut, Jean-François</creatorcontrib><creatorcontrib>Neelov, A.</creatorcontrib><creatorcontrib>Goedecker, S.</creatorcontrib><title>Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures</title><title>The Journal of chemical physics</title><description>We present the implementation of a full electronic structure calculation code on a hybrid parallel architecture with graphic processing units (GPUs). This implementation is performed on a free software code based on Daubechies wavelets. Such code shows very good performances, systematic convergence properties, and an excellent efficiency on parallel computers. Our GPU-based acceleration fully preserves all these properties. In particular, the code is able to run on many cores which may or may not have a GPU associated, and thus on parallel and massive parallel hybrid machines. With double precision calculations, we may achieve considerable speedup, between a factor of 20 for some operations and a factor of 6 for the whole density functional theory code.</description><subject>Computer Science</subject><subject>Distributed, Parallel, and Cluster Computing</subject><issn>0021-9606</issn><issn>1089-7690</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2009</creationdate><recordtype>article</recordtype><recordid>eNqVisFqg0AURYfQQmybRf5gtl1M-p7KqMtga11k4SJZy-t0ghNGDTNamL-vQn-gcODCuYexPcIBQSZveEhQSkxhwyKEvBCZLOCBRQAxikKC3LIn728AgFmcRqx514M3U-DVPKjJjANZfu706AIvyarZ0ir5Qk9DEGp02vM6fDnzzcvmIj6bCyenOjNpNc3L-cIer2S93v3tM3utPs5lLTqy7d2ZnlxoRzJtfTy1qwPI8ryA7AeT_7S_fDVHOQ</recordid><startdate>2009</startdate><enddate>2009</enddate><creator>Genovese, Luigi</creator><creator>Ospici, Matthieu</creator><creator>Deutsch, Thierry</creator><creator>Mehaut, Jean-François</creator><creator>Neelov, A.</creator><creator>Goedecker, S.</creator><general>American Institute of Physics</general><scope>1XC</scope><orcidid>https://orcid.org/0000-0003-1047-7462</orcidid><orcidid>https://orcid.org/0000-0003-1747-0247</orcidid><orcidid>https://orcid.org/0000-0001-7503-3390</orcidid><orcidid>https://orcid.org/0000-0003-1747-0247</orcidid><orcidid>https://orcid.org/0000-0001-7503-3390</orcidid><orcidid>https://orcid.org/0000-0003-1047-7462</orcidid></search><sort><creationdate>2009</creationdate><title>Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures</title><author>Genovese, Luigi ; Ospici, Matthieu ; Deutsch, Thierry ; Mehaut, Jean-François ; Neelov, A. ; Goedecker, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-hal_primary_oai_HAL_hal_00788907v13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Computer Science</topic><topic>Distributed, Parallel, and Cluster Computing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Genovese, Luigi</creatorcontrib><creatorcontrib>Ospici, Matthieu</creatorcontrib><creatorcontrib>Deutsch, Thierry</creatorcontrib><creatorcontrib>Mehaut, Jean-François</creatorcontrib><creatorcontrib>Neelov, A.</creatorcontrib><creatorcontrib>Goedecker, S.</creatorcontrib><collection>Hyper Article en Ligne (HAL)</collection><jtitle>The Journal of chemical physics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Genovese, Luigi</au><au>Ospici, Matthieu</au><au>Deutsch, Thierry</au><au>Mehaut, Jean-François</au><au>Neelov, A.</au><au>Goedecker, S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures</atitle><jtitle>The Journal of chemical physics</jtitle><date>2009</date><risdate>2009</risdate><volume>131</volume><issn>0021-9606</issn><eissn>1089-7690</eissn><abstract>We present the implementation of a full electronic structure calculation code on a hybrid parallel architecture with graphic processing units (GPUs). This implementation is performed on a free software code based on Daubechies wavelets. Such code shows very good performances, systematic convergence properties, and an excellent efficiency on parallel computers. Our GPU-based acceleration fully preserves all these properties. In particular, the code is able to run on many cores which may or may not have a GPU associated, and thus on parallel and massive parallel hybrid machines. With double precision calculations, we may achieve considerable speedup, between a factor of 20 for some operations and a factor of 6 for the whole density functional theory code.</abstract><pub>American Institute of Physics</pub><doi>10.1063/1.3166140</doi><orcidid>https://orcid.org/0000-0003-1047-7462</orcidid><orcidid>https://orcid.org/0000-0003-1747-0247</orcidid><orcidid>https://orcid.org/0000-0001-7503-3390</orcidid><orcidid>https://orcid.org/0000-0003-1747-0247</orcidid><orcidid>https://orcid.org/0000-0001-7503-3390</orcidid><orcidid>https://orcid.org/0000-0003-1047-7462</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0021-9606
ispartof The Journal of chemical physics, 2009, Vol.131
issn 0021-9606
1089-7690
language eng
recordid cdi_hal_primary_oai_HAL_hal_00788907v1
source AIP Journals Complete; AIP Digital Archive; Alma/SFX Local Collection
subjects Computer Science
Distributed, Parallel, and Cluster Computing
title Density Functional Theory Calculation on many-cores Hybrid CPU-GPU architectures
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-06T19%3A58%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-hal&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Density%20Functional%20Theory%20Calculation%20on%20many-cores%20Hybrid%20CPU-GPU%20architectures&rft.jtitle=The%20Journal%20of%20chemical%20physics&rft.au=Genovese,%20Luigi&rft.date=2009&rft.volume=131&rft.issn=0021-9606&rft.eissn=1089-7690&rft_id=info:doi/10.1063/1.3166140&rft_dat=%3Chal%3Eoai_HAL_hal_00788907v1%3C/hal%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true