Unifying and optimizing parallel linear algebra algorithms
Two issues in linear algebra algorithms for multicomputers are addressed. First, how to unify parallel implementations of the same algorithm in a decomposition-independent way. Second, how to optimize naive parallel programs maintaining the decomposition independence. Several matrix decompositions a...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on parallel and distributed systems 1993-12, Vol.4 (12), p.1382-1397 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1397 |
|---|---|
| container_issue | 12 |
| container_start_page | 1382 |
| container_title | IEEE transactions on parallel and distributed systems |
| container_volume | 4 |
| creator | Angelaccio, M. Colajanni, M. |
| description | Two issues in linear algebra algorithms for multicomputers are addressed. First, how to unify parallel implementations of the same algorithm in a decomposition-independent way. Second, how to optimize naive parallel programs maintaining the decomposition independence. Several matrix decompositions are viewed as instances of a more general allocation function called subcube matrix decomposition. By this meta-decomposition, a programming environment characterized by general primitives that allow one to design meta-algorithms independently of a particular decomposition. The authors apply such a framework to the parallel solution of dense matrices. This demonstrates that most of the existing algorithms can be derived by suitably setting the primitives used in the meta-algorithm. A further application of this programming style concerns the optimization of parallel algorithms. The idea to overlap communication and computation has been extended from 1-D decompositions to 2-D decompositions. Thus, a first attempt towards a decomposition-independent definition of such optimization strategies is provided.< > |
| doi_str_mv | 10.1109/71.250119 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_71_250119</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>250119</ieee_id><sourcerecordid>28426841</sourcerecordid><originalsourceid>FETCH-LOGICAL-c221t-84174d8e5a1f757c40dd7ee2456b6f5cb60b9bf85da87459263007a51499ec7f3</originalsourceid><addsrcrecordid>eNo9kL1PwzAQxS0EEqUwsDJlQEgMKT7Hjm02VPElVWKhc3Rx7GLkfGCnA_z1pGrV6d3pfvee9Ai5BroAoPpBwoIJCqBPyAyEUDkDVZxOM-Ui1wz0OblI6ZtS4ILyGXlcd979-m6TYddk_TD61v_t1gEjhmBDFnxnMWYYNraOuNM--vGrTZfkzGFI9uqgc7J-ef5cvuWrj9f35dMqN4zBmCsOkjfKCgQnhTScNo20lnFR1qUTpi5prWunRINKcqFZWVAqUQDX2hrpijm52_sOsf_Z2jRWrU_GhoCd7bepYoqzckqZwPs9aGKfUrSuGqJvMf5WQKtdO5WEat_OxN4eTDEZDC5iZ3w6PhSaaqGKCbvZY95ae7wePP4B5phrNg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>28426841</pqid></control><display><type>article</type><title>Unifying and optimizing parallel linear algebra algorithms</title><source>IEEE Electronic Library (IEL)</source><creator>Angelaccio, M. ; Colajanni, M.</creator><creatorcontrib>Angelaccio, M. ; Colajanni, M.</creatorcontrib><description>Two issues in linear algebra algorithms for multicomputers are addressed. First, how to unify parallel implementations of the same algorithm in a decomposition-independent way. Second, how to optimize naive parallel programs maintaining the decomposition independence. Several matrix decompositions are viewed as instances of a more general allocation function called subcube matrix decomposition. By this meta-decomposition, a programming environment characterized by general primitives that allow one to design meta-algorithms independently of a particular decomposition. The authors apply such a framework to the parallel solution of dense matrices. This demonstrates that most of the existing algorithms can be derived by suitably setting the primitives used in the meta-algorithm. A further application of this programming style concerns the optimization of parallel algorithms. The idea to overlap communication and computation has been extended from 1-D decompositions to 2-D decompositions. Thus, a first attempt towards a decomposition-independent definition of such optimization strategies is provided.< ></description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/71.250119</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Algorithm design and analysis ; Applied sciences ; Computer science; control theory; systems ; Computer systems and distributed systems. User interface ; Concurrent computing ; Exact sciences and technology ; Hypercubes ; Linear algebra ; Linear programming ; Matrix decomposition ; Parallel algorithms ; Parallel programming ; Performance analysis ; Programming environments ; Software</subject><ispartof>IEEE transactions on parallel and distributed systems, 1993-12, Vol.4 (12), p.1382-1397</ispartof><rights>1994 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c221t-84174d8e5a1f757c40dd7ee2456b6f5cb60b9bf85da87459263007a51499ec7f3</citedby><cites>FETCH-LOGICAL-c221t-84174d8e5a1f757c40dd7ee2456b6f5cb60b9bf85da87459263007a51499ec7f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/250119$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/250119$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=3909583$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Angelaccio, M.</creatorcontrib><creatorcontrib>Colajanni, M.</creatorcontrib><title>Unifying and optimizing parallel linear algebra algorithms</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>Two issues in linear algebra algorithms for multicomputers are addressed. First, how to unify parallel implementations of the same algorithm in a decomposition-independent way. Second, how to optimize naive parallel programs maintaining the decomposition independence. Several matrix decompositions are viewed as instances of a more general allocation function called subcube matrix decomposition. By this meta-decomposition, a programming environment characterized by general primitives that allow one to design meta-algorithms independently of a particular decomposition. The authors apply such a framework to the parallel solution of dense matrices. This demonstrates that most of the existing algorithms can be derived by suitably setting the primitives used in the meta-algorithm. A further application of this programming style concerns the optimization of parallel algorithms. The idea to overlap communication and computation has been extended from 1-D decompositions to 2-D decompositions. Thus, a first attempt towards a decomposition-independent definition of such optimization strategies is provided.< ></description><subject>Algorithm design and analysis</subject><subject>Applied sciences</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems and distributed systems. User interface</subject><subject>Concurrent computing</subject><subject>Exact sciences and technology</subject><subject>Hypercubes</subject><subject>Linear algebra</subject><subject>Linear programming</subject><subject>Matrix decomposition</subject><subject>Parallel algorithms</subject><subject>Parallel programming</subject><subject>Performance analysis</subject><subject>Programming environments</subject><subject>Software</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1993</creationdate><recordtype>article</recordtype><recordid>eNo9kL1PwzAQxS0EEqUwsDJlQEgMKT7Hjm02VPElVWKhc3Rx7GLkfGCnA_z1pGrV6d3pfvee9Ai5BroAoPpBwoIJCqBPyAyEUDkDVZxOM-Ui1wz0OblI6ZtS4ILyGXlcd979-m6TYddk_TD61v_t1gEjhmBDFnxnMWYYNraOuNM--vGrTZfkzGFI9uqgc7J-ef5cvuWrj9f35dMqN4zBmCsOkjfKCgQnhTScNo20lnFR1qUTpi5prWunRINKcqFZWVAqUQDX2hrpijm52_sOsf_Z2jRWrU_GhoCd7bepYoqzckqZwPs9aGKfUrSuGqJvMf5WQKtdO5WEat_OxN4eTDEZDC5iZ3w6PhSaaqGKCbvZY95ae7wePP4B5phrNg</recordid><startdate>19931201</startdate><enddate>19931201</enddate><creator>Angelaccio, M.</creator><creator>Colajanni, M.</creator><general>IEEE</general><general>IEEE Computer Society</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19931201</creationdate><title>Unifying and optimizing parallel linear algebra algorithms</title><author>Angelaccio, M. ; Colajanni, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c221t-84174d8e5a1f757c40dd7ee2456b6f5cb60b9bf85da87459263007a51499ec7f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1993</creationdate><topic>Algorithm design and analysis</topic><topic>Applied sciences</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems and distributed systems. User interface</topic><topic>Concurrent computing</topic><topic>Exact sciences and technology</topic><topic>Hypercubes</topic><topic>Linear algebra</topic><topic>Linear programming</topic><topic>Matrix decomposition</topic><topic>Parallel algorithms</topic><topic>Parallel programming</topic><topic>Performance analysis</topic><topic>Programming environments</topic><topic>Software</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Angelaccio, M.</creatorcontrib><creatorcontrib>Colajanni, M.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Angelaccio, M.</au><au>Colajanni, M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unifying and optimizing parallel linear algebra algorithms</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>1993-12-01</date><risdate>1993</risdate><volume>4</volume><issue>12</issue><spage>1382</spage><epage>1397</epage><pages>1382-1397</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>Two issues in linear algebra algorithms for multicomputers are addressed. First, how to unify parallel implementations of the same algorithm in a decomposition-independent way. Second, how to optimize naive parallel programs maintaining the decomposition independence. Several matrix decompositions are viewed as instances of a more general allocation function called subcube matrix decomposition. By this meta-decomposition, a programming environment characterized by general primitives that allow one to design meta-algorithms independently of a particular decomposition. The authors apply such a framework to the parallel solution of dense matrices. This demonstrates that most of the existing algorithms can be derived by suitably setting the primitives used in the meta-algorithm. A further application of this programming style concerns the optimization of parallel algorithms. The idea to overlap communication and computation has been extended from 1-D decompositions to 2-D decompositions. Thus, a first attempt towards a decomposition-independent definition of such optimization strategies is provided.< ></abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><doi>10.1109/71.250119</doi><tpages>16</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1045-9219 |
| ispartof | IEEE transactions on parallel and distributed systems, 1993-12, Vol.4 (12), p.1382-1397 |
| issn | 1045-9219 1558-2183 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_71_250119 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithm design and analysis Applied sciences Computer science control theory systems Computer systems and distributed systems. User interface Concurrent computing Exact sciences and technology Hypercubes Linear algebra Linear programming Matrix decomposition Parallel algorithms Parallel programming Performance analysis Programming environments Software |
| title | Unifying and optimizing parallel linear algebra algorithms |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T13%3A58%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Unifying%20and%20optimizing%20parallel%20linear%20algebra%20algorithms&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Angelaccio,%20M.&rft.date=1993-12-01&rft.volume=4&rft.issue=12&rft.spage=1382&rft.epage=1397&rft.pages=1382-1397&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/71.250119&rft_dat=%3Cproquest_RIE%3E28426841%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=28426841&rft_id=info:pmid/&rft_ieee_id=250119&rfr_iscdi=true |