Irregular Assignment Computations on cc-NUMA Multiprocessors
This paper addresses the parallelization of loops with irregular assignment computations on cc-NUMA multiprocessors. This loop pattern is distinguished by the existence of loop-carried output data dependences that can only be detected at run-time. A parallelization technique based on the inspector-e...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Buchkapitel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 369 |
|---|---|
| container_issue | |
| container_start_page | 361 |
| container_title | |
| container_volume | 2327 |
| creator | Arenaz, Manuel Touriño, Juan Doallo, Ramón |
| description | This paper addresses the parallelization of loops with irregular assignment computations on cc-NUMA multiprocessors. This loop pattern is distinguished by the existence of loop-carried output data dependences that can only be detected at run-time. A parallelization technique based on the inspector-executor model is proposed in this paper. In the inspector, loop iterations are reordered so that they can be executed in a conflict-free manner during the executor stage. The design of the inspector ensures load-balancing and uniprocessor data write locality exploitation. Experimental results show the scalability of this technique, which is presented as a clear alternative to other existing methods. |
| doi_str_mv | 10.1007/3-540-47847-7_33 |
| format | Book Chapter |
| fullrecord | <record><control><sourceid>proquest_pasca</sourceid><recordid>TN_cdi_pascalfrancis_primary_14881168</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EBC6281858_369_377</sourcerecordid><originalsourceid>FETCH-LOGICAL-p1843-15b2584b1be655790025298e4972a225045c30f4cf65cc8e3ad93b0974752f893</originalsourceid><addsrcrecordid>eNotkDlPwzAUx80pQunOmIXRxfbzKbFUFUelFhYqsVmOcUogTYKdDnx70uMtT3r_Q08_hG4pmVBC1D1gwQnmSnOFlQU4QWOjNAzH_U2fooxKSjEAN2foei-AVPzjHGUECMNGcbhEGZNMGkq4uULjlL7JMEA1MSJDD_MYw3pbu5hPU6rWzSY0fT5rN922d33VNilvm9x7_LpaTvPltu6rLrY-pNTGdIMuSlenMD7uEVo9Pb7PXvDi7Xk-my5wRzUHTEXBhOYFLYIUQhlCmGBGB24Uc4wJwoUHUnJfSuG9DuA-DRRkeF4JVmoDI3R36O1c8q4uo2t8lWwXq42Lf5ZyrSmVevBNDr40SM06RFu07U-ylNgdTwt2IGT37OyO5xDgx-LY_m5D6m3YJfzAILraf7muDzFZyTTVQluQxoJS8A_HeHEp</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>book_chapter</recordtype><pqid>EBC6281858_369_377</pqid></control><display><type>book_chapter</type><title>Irregular Assignment Computations on cc-NUMA Multiprocessors</title><source>Springer Books</source><creator>Arenaz, Manuel ; Touriño, Juan ; Doallo, Ramón</creator><contributor>Seo, Yoshiki ; Sato, Mitsuhisa ; Zima, Hans P ; Shimasaki, Masaaki ; Joe, Kazuki ; Sato, Mitsuhisa ; Shimasaki, Masaaki ; Zima, Hans P. ; Seo, Yoshiki ; Joe, Kazuki</contributor><creatorcontrib>Arenaz, Manuel ; Touriño, Juan ; Doallo, Ramón ; Seo, Yoshiki ; Sato, Mitsuhisa ; Zima, Hans P ; Shimasaki, Masaaki ; Joe, Kazuki ; Sato, Mitsuhisa ; Shimasaki, Masaaki ; Zima, Hans P. ; Seo, Yoshiki ; Joe, Kazuki</creatorcontrib><description>This paper addresses the parallelization of loops with irregular assignment computations on cc-NUMA multiprocessors. This loop pattern is distinguished by the existence of loop-carried output data dependences that can only be detected at run-time. A parallelization technique based on the inspector-executor model is proposed in this paper. In the inspector, loop iterations are reordered so that they can be executed in a conflict-free manner during the executor stage. The design of the inspector ensures load-balancing and uniprocessor data write locality exploitation. Experimental results show the scalability of this technique, which is presented as a clear alternative to other existing methods.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 354043674X</identifier><identifier>ISBN: 9783540436744</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540478478</identifier><identifier>EISBN: 3540478477</identifier><identifier>DOI: 10.1007/3-540-47847-7_33</identifier><identifier>OCLC: 262691049</identifier><identifier>LCCallNum: QA76.6-76.66</identifier><language>eng</language><publisher>Germany: Springer Berlin / Heidelberg</publisher><subject>Applied sciences ; Array Element ; Computational Overhead ; Computer architecture & logic design ; Computer programming / software development ; Computer science; control theory; systems ; Computer systems and distributed systems. User interface ; Exact sciences and technology ; Loop Iteration ; Parallelization Technique ; Sequential Loop ; Software ; Software Engineering</subject><ispartof>High Performance Computing, 2002, Vol.2327, p.361-369</ispartof><rights>Springer-Verlag Berlin Heidelberg 2002</rights><rights>2003 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><relation>Lecture Notes in Computer Science</relation></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttps://ebookcentral.proquest.com/covers/6281858-l.jpg</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/3-540-47847-7_33$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/3-540-47847-7_33$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,789,790,793,4050,4051,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=14881168$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Seo, Yoshiki</contributor><contributor>Sato, Mitsuhisa</contributor><contributor>Zima, Hans P</contributor><contributor>Shimasaki, Masaaki</contributor><contributor>Joe, Kazuki</contributor><contributor>Sato, Mitsuhisa</contributor><contributor>Shimasaki, Masaaki</contributor><contributor>Zima, Hans P.</contributor><contributor>Seo, Yoshiki</contributor><contributor>Joe, Kazuki</contributor><creatorcontrib>Arenaz, Manuel</creatorcontrib><creatorcontrib>Touriño, Juan</creatorcontrib><creatorcontrib>Doallo, Ramón</creatorcontrib><title>Irregular Assignment Computations on cc-NUMA Multiprocessors</title><title>High Performance Computing</title><description>This paper addresses the parallelization of loops with irregular assignment computations on cc-NUMA multiprocessors. This loop pattern is distinguished by the existence of loop-carried output data dependences that can only be detected at run-time. A parallelization technique based on the inspector-executor model is proposed in this paper. In the inspector, loop iterations are reordered so that they can be executed in a conflict-free manner during the executor stage. The design of the inspector ensures load-balancing and uniprocessor data write locality exploitation. Experimental results show the scalability of this technique, which is presented as a clear alternative to other existing methods.</description><subject>Applied sciences</subject><subject>Array Element</subject><subject>Computational Overhead</subject><subject>Computer architecture & logic design</subject><subject>Computer programming / software development</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems and distributed systems. User interface</subject><subject>Exact sciences and technology</subject><subject>Loop Iteration</subject><subject>Parallelization Technique</subject><subject>Sequential Loop</subject><subject>Software</subject><subject>Software Engineering</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>354043674X</isbn><isbn>9783540436744</isbn><isbn>9783540478478</isbn><isbn>3540478477</isbn><fulltext>true</fulltext><rsrctype>book_chapter</rsrctype><creationdate>2002</creationdate><recordtype>book_chapter</recordtype><recordid>eNotkDlPwzAUx80pQunOmIXRxfbzKbFUFUelFhYqsVmOcUogTYKdDnx70uMtT3r_Q08_hG4pmVBC1D1gwQnmSnOFlQU4QWOjNAzH_U2fooxKSjEAN2foei-AVPzjHGUECMNGcbhEGZNMGkq4uULjlL7JMEA1MSJDD_MYw3pbu5hPU6rWzSY0fT5rN922d33VNilvm9x7_LpaTvPltu6rLrY-pNTGdIMuSlenMD7uEVo9Pb7PXvDi7Xk-my5wRzUHTEXBhOYFLYIUQhlCmGBGB24Uc4wJwoUHUnJfSuG9DuA-DRRkeF4JVmoDI3R36O1c8q4uo2t8lWwXq42Lf5ZyrSmVevBNDr40SM06RFu07U-ylNgdTwt2IGT37OyO5xDgx-LY_m5D6m3YJfzAILraf7muDzFZyTTVQluQxoJS8A_HeHEp</recordid><startdate>2002</startdate><enddate>2002</enddate><creator>Arenaz, Manuel</creator><creator>Touriño, Juan</creator><creator>Doallo, Ramón</creator><general>Springer Berlin / Heidelberg</general><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>FFUUA</scope><scope>IQODW</scope></search><sort><creationdate>2002</creationdate><title>Irregular Assignment Computations on cc-NUMA Multiprocessors</title><author>Arenaz, Manuel ; Touriño, Juan ; Doallo, Ramón</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p1843-15b2584b1be655790025298e4972a225045c30f4cf65cc8e3ad93b0974752f893</frbrgroupid><rsrctype>book_chapters</rsrctype><prefilter>book_chapters</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Applied sciences</topic><topic>Array Element</topic><topic>Computational Overhead</topic><topic>Computer architecture & logic design</topic><topic>Computer programming / software development</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems and distributed systems. User interface</topic><topic>Exact sciences and technology</topic><topic>Loop Iteration</topic><topic>Parallelization Technique</topic><topic>Sequential Loop</topic><topic>Software</topic><topic>Software Engineering</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Arenaz, Manuel</creatorcontrib><creatorcontrib>Touriño, Juan</creatorcontrib><creatorcontrib>Doallo, Ramón</creatorcontrib><collection>ProQuest Ebook Central - Book Chapters - Demo use only</collection><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Arenaz, Manuel</au><au>Touriño, Juan</au><au>Doallo, Ramón</au><au>Seo, Yoshiki</au><au>Sato, Mitsuhisa</au><au>Zima, Hans P</au><au>Shimasaki, Masaaki</au><au>Joe, Kazuki</au><au>Sato, Mitsuhisa</au><au>Shimasaki, Masaaki</au><au>Zima, Hans P.</au><au>Seo, Yoshiki</au><au>Joe, Kazuki</au><format>book</format><genre>bookitem</genre><ristype>CHAP</ristype><atitle>Irregular Assignment Computations on cc-NUMA Multiprocessors</atitle><btitle>High Performance Computing</btitle><seriestitle>Lecture Notes in Computer Science</seriestitle><date>2002</date><risdate>2002</risdate><volume>2327</volume><spage>361</spage><epage>369</epage><pages>361-369</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>354043674X</isbn><isbn>9783540436744</isbn><eisbn>9783540478478</eisbn><eisbn>3540478477</eisbn><abstract>This paper addresses the parallelization of loops with irregular assignment computations on cc-NUMA multiprocessors. This loop pattern is distinguished by the existence of loop-carried output data dependences that can only be detected at run-time. A parallelization technique based on the inspector-executor model is proposed in this paper. In the inspector, loop iterations are reordered so that they can be executed in a conflict-free manner during the executor stage. The design of the inspector ensures load-balancing and uniprocessor data write locality exploitation. Experimental results show the scalability of this technique, which is presented as a clear alternative to other existing methods.</abstract><cop>Germany</cop><pub>Springer Berlin / Heidelberg</pub><doi>10.1007/3-540-47847-7_33</doi><oclcid>262691049</oclcid><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | High Performance Computing, 2002, Vol.2327, p.361-369 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_14881168 |
| source | Springer Books |
| subjects | Applied sciences Array Element Computational Overhead Computer architecture & logic design Computer programming / software development Computer science control theory systems Computer systems and distributed systems. User interface Exact sciences and technology Loop Iteration Parallelization Technique Sequential Loop Software Software Engineering |
| title | Irregular Assignment Computations on cc-NUMA Multiprocessors |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T23%3A11%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=bookitem&rft.atitle=Irregular%20Assignment%20Computations%20on%20cc-NUMA%20Multiprocessors&rft.btitle=High%20Performance%20Computing&rft.au=Arenaz,%20Manuel&rft.date=2002&rft.volume=2327&rft.spage=361&rft.epage=369&rft.pages=361-369&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=354043674X&rft.isbn_list=9783540436744&rft_id=info:doi/10.1007/3-540-47847-7_33&rft_dat=%3Cproquest_pasca%3EEBC6281858_369_377%3C/proquest_pasca%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540478478&rft.eisbn_list=3540478477&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=EBC6281858_369_377&rft_id=info:pmid/&rfr_iscdi=true |