Loading…
A decomposition method for efficient use of distributed supercomputers for finite element applications
The interconnection of geographically distributed supercomputers via highspeed networks makes available the needed compute power for large-scale scientific applications, such as finite element applications. In this paper we propose a two-level data decomposition method for efficient execution of fin...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 24 |
| container_issue | |
| container_start_page | 12 |
| container_title | |
| container_volume | |
| creator | Taylor, V.E. Chen, J. Canfield, T. Stevens, R. |
| description | The interconnection of geographically distributed supercomputers via highspeed networks makes available the needed compute power for large-scale scientific applications, such as finite element applications. In this paper we propose a two-level data decomposition method for efficient execution of finite element applications on a network of supercomputers. Our method exploits the following features that may be different for each supercomputer in the system: processor speed, number of processors used from each supercomputer, local network performance, wide area network performance and wide area topology. Preliminary experiments involving a nonlinear, finite element application executed on a network of two supercomputers, one located at Argonne National Laboratory and the other one at the Cornell Theory Center, demonstrate a 20% reduction in execution time when the proposed decomposition is used as compared with naively applying conventional decompositions that are applicable to single supercomputers. |
| doi_str_mv | 10.1109/ASAP.1996.542797 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_542797</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>542797</ieee_id><sourcerecordid>542797</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-c298873cd650c3a48faa2852d164bfedf40f9e950ecabee83aca32226f6c87853</originalsourceid><addsrcrecordid>eNo9UEtLxDAYDD7Add27eMofaE3SJk2OZdFVWFBQYW9LmnzBSF8k6cF_b-uKcxmGeRwGoVtKckqJuq_f6tecKiVyXrJKVWdoxaggGeHscI6uiaRSVLN1uPg3KL1Cmxi_yAzOKyXICrkaWzBDNw7RJz_0uIP0OVjshoDBOW889AlPEfDgsPUxBd9MCSyO0whhKc4qxN-8871PgKGFbinpcWy90ctqvEGXTrcRNn-8Rh-PD-_bp2z_snve1vvMU1KmzDAlZVUYKzgxhS6l05pJziwVZePAupI4BYoTMLoBkIU2umCMCSeMrCQv1ujutOsB4DgG3-nwfTw9VPwAvEpbIA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A decomposition method for efficient use of distributed supercomputers for finite element applications</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Taylor, V.E. ; Chen, J. ; Canfield, T. ; Stevens, R.</creator><creatorcontrib>Taylor, V.E. ; Chen, J. ; Canfield, T. ; Stevens, R.</creatorcontrib><description>The interconnection of geographically distributed supercomputers via highspeed networks makes available the needed compute power for large-scale scientific applications, such as finite element applications. In this paper we propose a two-level data decomposition method for efficient execution of finite element applications on a network of supercomputers. Our method exploits the following features that may be different for each supercomputer in the system: processor speed, number of processors used from each supercomputer, local network performance, wide area network performance and wide area topology. Preliminary experiments involving a nonlinear, finite element application executed on a network of two supercomputers, one located at Argonne National Laboratory and the other one at the Cornell Theory Center, demonstrate a 20% reduction in execution time when the proposed decomposition is used as compared with naively applying conventional decompositions that are applicable to single supercomputers.</description><identifier>ISSN: 2160-0511</identifier><identifier>ISBN: 081867542X</identifier><identifier>ISBN: 9780818675423</identifier><identifier>EISSN: 2160-052X</identifier><identifier>DOI: 10.1109/ASAP.1996.542797</identifier><language>eng</language><publisher>IEEE</publisher><subject>Delay ; Distributed computing ; Finite element methods ; Laboratories ; Large-scale systems ; Network topology ; Supercomputers ; Virtual prototyping ; Visualization ; Wide area networks</subject><ispartof>Proceedings of International Conference on Application Specific Systems, Architectures and Processors: ASAP '96, 1996, p.12-24</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/542797$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,4036,4037,27906,54536,54901,54913</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/542797$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Taylor, V.E.</creatorcontrib><creatorcontrib>Chen, J.</creatorcontrib><creatorcontrib>Canfield, T.</creatorcontrib><creatorcontrib>Stevens, R.</creatorcontrib><title>A decomposition method for efficient use of distributed supercomputers for finite element applications</title><title>Proceedings of International Conference on Application Specific Systems, Architectures and Processors: ASAP '96</title><addtitle>ASAP</addtitle><description>The interconnection of geographically distributed supercomputers via highspeed networks makes available the needed compute power for large-scale scientific applications, such as finite element applications. In this paper we propose a two-level data decomposition method for efficient execution of finite element applications on a network of supercomputers. Our method exploits the following features that may be different for each supercomputer in the system: processor speed, number of processors used from each supercomputer, local network performance, wide area network performance and wide area topology. Preliminary experiments involving a nonlinear, finite element application executed on a network of two supercomputers, one located at Argonne National Laboratory and the other one at the Cornell Theory Center, demonstrate a 20% reduction in execution time when the proposed decomposition is used as compared with naively applying conventional decompositions that are applicable to single supercomputers.</description><subject>Delay</subject><subject>Distributed computing</subject><subject>Finite element methods</subject><subject>Laboratories</subject><subject>Large-scale systems</subject><subject>Network topology</subject><subject>Supercomputers</subject><subject>Virtual prototyping</subject><subject>Visualization</subject><subject>Wide area networks</subject><issn>2160-0511</issn><issn>2160-052X</issn><isbn>081867542X</isbn><isbn>9780818675423</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1996</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo9UEtLxDAYDD7Add27eMofaE3SJk2OZdFVWFBQYW9LmnzBSF8k6cF_b-uKcxmGeRwGoVtKckqJuq_f6tecKiVyXrJKVWdoxaggGeHscI6uiaRSVLN1uPg3KL1Cmxi_yAzOKyXICrkaWzBDNw7RJz_0uIP0OVjshoDBOW889AlPEfDgsPUxBd9MCSyO0whhKc4qxN-8871PgKGFbinpcWy90ctqvEGXTrcRNn-8Rh-PD-_bp2z_snve1vvMU1KmzDAlZVUYKzgxhS6l05pJziwVZePAupI4BYoTMLoBkIU2umCMCSeMrCQv1ujutOsB4DgG3-nwfTw9VPwAvEpbIA</recordid><startdate>1996</startdate><enddate>1996</enddate><creator>Taylor, V.E.</creator><creator>Chen, J.</creator><creator>Canfield, T.</creator><creator>Stevens, R.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1996</creationdate><title>A decomposition method for efficient use of distributed supercomputers for finite element applications</title><author>Taylor, V.E. ; Chen, J. ; Canfield, T. ; Stevens, R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-c298873cd650c3a48faa2852d164bfedf40f9e950ecabee83aca32226f6c87853</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1996</creationdate><topic>Delay</topic><topic>Distributed computing</topic><topic>Finite element methods</topic><topic>Laboratories</topic><topic>Large-scale systems</topic><topic>Network topology</topic><topic>Supercomputers</topic><topic>Virtual prototyping</topic><topic>Visualization</topic><topic>Wide area networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Taylor, V.E.</creatorcontrib><creatorcontrib>Chen, J.</creatorcontrib><creatorcontrib>Canfield, T.</creatorcontrib><creatorcontrib>Stevens, R.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Taylor, V.E.</au><au>Chen, J.</au><au>Canfield, T.</au><au>Stevens, R.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A decomposition method for efficient use of distributed supercomputers for finite element applications</atitle><btitle>Proceedings of International Conference on Application Specific Systems, Architectures and Processors: ASAP '96</btitle><stitle>ASAP</stitle><date>1996</date><risdate>1996</risdate><spage>12</spage><epage>24</epage><pages>12-24</pages><issn>2160-0511</issn><eissn>2160-052X</eissn><isbn>081867542X</isbn><isbn>9780818675423</isbn><abstract>The interconnection of geographically distributed supercomputers via highspeed networks makes available the needed compute power for large-scale scientific applications, such as finite element applications. In this paper we propose a two-level data decomposition method for efficient execution of finite element applications on a network of supercomputers. Our method exploits the following features that may be different for each supercomputer in the system: processor speed, number of processors used from each supercomputer, local network performance, wide area network performance and wide area topology. Preliminary experiments involving a nonlinear, finite element application executed on a network of two supercomputers, one located at Argonne National Laboratory and the other one at the Cornell Theory Center, demonstrate a 20% reduction in execution time when the proposed decomposition is used as compared with naively applying conventional decompositions that are applicable to single supercomputers.</abstract><pub>IEEE</pub><doi>10.1109/ASAP.1996.542797</doi><tpages>13</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2160-0511 |
| ispartof | Proceedings of International Conference on Application Specific Systems, Architectures and Processors: ASAP '96, 1996, p.12-24 |
| issn | 2160-0511 2160-052X |
| language | eng |
| recordid | cdi_ieee_primary_542797 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Delay Distributed computing Finite element methods Laboratories Large-scale systems Network topology Supercomputers Virtual prototyping Visualization Wide area networks |
| title | A decomposition method for efficient use of distributed supercomputers for finite element applications |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T00%3A02%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20decomposition%20method%20for%20efficient%20use%20of%20distributed%20supercomputers%20for%20finite%20element%20applications&rft.btitle=Proceedings%20of%20International%20Conference%20on%20Application%20Specific%20Systems,%20Architectures%20and%20Processors:%20ASAP%20'96&rft.au=Taylor,%20V.E.&rft.date=1996&rft.spage=12&rft.epage=24&rft.pages=12-24&rft.issn=2160-0511&rft.eissn=2160-052X&rft.isbn=081867542X&rft.isbn_list=9780818675423&rft_id=info:doi/10.1109/ASAP.1996.542797&rft_dat=%3Cieee_6IE%3E542797%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i104t-c298873cd650c3a48faa2852d164bfedf40f9e950ecabee83aca32226f6c87853%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=542797&rfr_iscdi=true |