Loop transformations to prevent false sharing
To date, page management in shared virtual memory (SVM) systems has been primarily the responsibility of the run-time system. However, there are some problems that are difficult to resolve efficiently at run time. Chief among these is false sharing. A loop transformation theory is developed for iden...
Gespeichert in:
Veröffentlicht in: | International Journal of Parallel Programming 1995-08, Vol.23 (4), p.263-301 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 301 |
---|---|
container_issue | 4 |
container_start_page | 263 |
container_title | International Journal of Parallel Programming |
container_volume | 23 |
creator | GRANSTON, E. D MONTAUT, T BODIN, F |
description | To date, page management in shared virtual memory (SVM) systems has been primarily the responsibility of the run-time system. However, there are some problems that are difficult to resolve efficiently at run time. Chief among these is false sharing. A loop transformation theory is developed for identifying and eliminating potential sources of multiple-writer false sharing and other sources of page migration resulting from regular references in numerical applications. Loop nests of one and 2 dimensions (before blocking) with single-level, DOALL-style parallelism are covered. The potential of these transformations is demonstrated experimentally. |
doi_str_mv | 10.1007/BF02577768 |
format | Article |
fullrecord | <record><control><sourceid>proquest_osti_</sourceid><recordid>TN_cdi_proquest_miscellaneous_743266114</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>743266114</sourcerecordid><originalsourceid>FETCH-LOGICAL-c374t-7af927a6b9f92b7e60ffa99618d93a8497001d5ad117064881dffbcfc33698123</originalsourceid><addsrcrecordid>eNp90UtLAzEQAOAgCtbqxV-wiigIq5NNNo-jFqtCwYueQ5pN7JbtZk1SwX9vbEXBg6dh4JthHggdY7jCAPz6dgpVzTlnYgeNcM1JyRmFXTQCIeqS01rso4MYlwAguRAjVM68H4oUdB-dDyudWt_HIvliCPbd9qlwuou2iAsd2v71EO1t8qPvOEYv07vnyUM5e7p_nNzMSkM4TSXXTlZcs7nMcc4tA-e0lAyLRhItqOQAuKl1gzEHRoXAjXNz4wwhTApckTE62fb1MbUqmjZZszC-761JCjOgG3OxNUPwb2sbk1q10diu073166g4JRVjGNMsz_-VFad5DikyPP0Dl34d-rypqoBWktKaZXS5RSb4GIN1agjtSocPhUF9PUH9PiHjs--OOhrduXxn08afCpIHJCDJJ48jgwg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>204294456</pqid></control><display><type>article</type><title>Loop transformations to prevent false sharing</title><source>SpringerLink Journals - AutoHoldings</source><creator>GRANSTON, E. D ; MONTAUT, T ; BODIN, F</creator><creatorcontrib>GRANSTON, E. D ; MONTAUT, T ; BODIN, F</creatorcontrib><description>To date, page management in shared virtual memory (SVM) systems has been primarily the responsibility of the run-time system. However, there are some problems that are difficult to resolve efficiently at run time. Chief among these is false sharing. A loop transformation theory is developed for identifying and eliminating potential sources of multiple-writer false sharing and other sources of page migration resulting from regular references in numerical applications. Loop nests of one and 2 dimensions (before blocking) with single-level, DOALL-style parallelism are covered. The potential of these transformations is demonstrated experimentally.</description><identifier>ISSN: 0885-7458</identifier><identifier>EISSN: 1573-7640</identifier><identifier>DOI: 10.1007/BF02577768</identifier><identifier>CODEN: IJPPE5</identifier><language>eng</language><publisher>New York, NY: Plenum Press</publisher><subject>ALGORITHMS ; Applied sciences ; Computer memory ; Computer programming ; Computer science; control theory; systems ; Computer systems and distributed systems. User interface ; EFFICIENCY ; Exact sciences and technology ; Loops ; MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS ; Memory and file management (including protection and security) ; MEMORY MANAGEMENT ; Memory organisation. Data processing ; PARALLEL PROCESSING ; Programming theory ; Software ; Studies ; TASK SCHEDULING ; Theoretical computing</subject><ispartof>International Journal of Parallel Programming, 1995-08, Vol.23 (4), p.263-301</ispartof><rights>1995 INIST-CNRS</rights><rights>Copyright Plenum Publishing Corporation Aug 1995</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c374t-7af927a6b9f92b7e60ffa99618d93a8497001d5ad117064881dffbcfc33698123</citedby><cites>FETCH-LOGICAL-c374t-7af927a6b9f92b7e60ffa99618d93a8497001d5ad117064881dffbcfc33698123</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=3661309$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.osti.gov/biblio/160412$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>GRANSTON, E. D</creatorcontrib><creatorcontrib>MONTAUT, T</creatorcontrib><creatorcontrib>BODIN, F</creatorcontrib><title>Loop transformations to prevent false sharing</title><title>International Journal of Parallel Programming</title><description>To date, page management in shared virtual memory (SVM) systems has been primarily the responsibility of the run-time system. However, there are some problems that are difficult to resolve efficiently at run time. Chief among these is false sharing. A loop transformation theory is developed for identifying and eliminating potential sources of multiple-writer false sharing and other sources of page migration resulting from regular references in numerical applications. Loop nests of one and 2 dimensions (before blocking) with single-level, DOALL-style parallelism are covered. The potential of these transformations is demonstrated experimentally.</description><subject>ALGORITHMS</subject><subject>Applied sciences</subject><subject>Computer memory</subject><subject>Computer programming</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems and distributed systems. User interface</subject><subject>EFFICIENCY</subject><subject>Exact sciences and technology</subject><subject>Loops</subject><subject>MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS</subject><subject>Memory and file management (including protection and security)</subject><subject>MEMORY MANAGEMENT</subject><subject>Memory organisation. Data processing</subject><subject>PARALLEL PROCESSING</subject><subject>Programming theory</subject><subject>Software</subject><subject>Studies</subject><subject>TASK SCHEDULING</subject><subject>Theoretical computing</subject><issn>0885-7458</issn><issn>1573-7640</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1995</creationdate><recordtype>article</recordtype><recordid>eNp90UtLAzEQAOAgCtbqxV-wiigIq5NNNo-jFqtCwYueQ5pN7JbtZk1SwX9vbEXBg6dh4JthHggdY7jCAPz6dgpVzTlnYgeNcM1JyRmFXTQCIeqS01rso4MYlwAguRAjVM68H4oUdB-dDyudWt_HIvliCPbd9qlwuou2iAsd2v71EO1t8qPvOEYv07vnyUM5e7p_nNzMSkM4TSXXTlZcs7nMcc4tA-e0lAyLRhItqOQAuKl1gzEHRoXAjXNz4wwhTApckTE62fb1MbUqmjZZszC-761JCjOgG3OxNUPwb2sbk1q10diu073166g4JRVjGNMsz_-VFad5DikyPP0Dl34d-rypqoBWktKaZXS5RSb4GIN1agjtSocPhUF9PUH9PiHjs--OOhrduXxn08afCpIHJCDJJ48jgwg</recordid><startdate>19950801</startdate><enddate>19950801</enddate><creator>GRANSTON, E. D</creator><creator>MONTAUT, T</creator><creator>BODIN, F</creator><general>Plenum Press</general><general>Springer Nature B.V</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><scope>OTOTI</scope></search><sort><creationdate>19950801</creationdate><title>Loop transformations to prevent false sharing</title><author>GRANSTON, E. D ; MONTAUT, T ; BODIN, F</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c374t-7af927a6b9f92b7e60ffa99618d93a8497001d5ad117064881dffbcfc33698123</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1995</creationdate><topic>ALGORITHMS</topic><topic>Applied sciences</topic><topic>Computer memory</topic><topic>Computer programming</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems and distributed systems. User interface</topic><topic>EFFICIENCY</topic><topic>Exact sciences and technology</topic><topic>Loops</topic><topic>MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS</topic><topic>Memory and file management (including protection and security)</topic><topic>MEMORY MANAGEMENT</topic><topic>Memory organisation. Data processing</topic><topic>PARALLEL PROCESSING</topic><topic>Programming theory</topic><topic>Software</topic><topic>Studies</topic><topic>TASK SCHEDULING</topic><topic>Theoretical computing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>GRANSTON, E. D</creatorcontrib><creatorcontrib>MONTAUT, T</creatorcontrib><creatorcontrib>BODIN, F</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><collection>OSTI.GOV</collection><jtitle>International Journal of Parallel Programming</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>GRANSTON, E. D</au><au>MONTAUT, T</au><au>BODIN, F</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Loop transformations to prevent false sharing</atitle><jtitle>International Journal of Parallel Programming</jtitle><date>1995-08-01</date><risdate>1995</risdate><volume>23</volume><issue>4</issue><spage>263</spage><epage>301</epage><pages>263-301</pages><issn>0885-7458</issn><eissn>1573-7640</eissn><coden>IJPPE5</coden><abstract>To date, page management in shared virtual memory (SVM) systems has been primarily the responsibility of the run-time system. However, there are some problems that are difficult to resolve efficiently at run time. Chief among these is false sharing. A loop transformation theory is developed for identifying and eliminating potential sources of multiple-writer false sharing and other sources of page migration resulting from regular references in numerical applications. Loop nests of one and 2 dimensions (before blocking) with single-level, DOALL-style parallelism are covered. The potential of these transformations is demonstrated experimentally.</abstract><cop>New York, NY</cop><pub>Plenum Press</pub><doi>10.1007/BF02577768</doi><tpages>39</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0885-7458 |
ispartof | International Journal of Parallel Programming, 1995-08, Vol.23 (4), p.263-301 |
issn | 0885-7458 1573-7640 |
language | eng |
recordid | cdi_proquest_miscellaneous_743266114 |
source | SpringerLink Journals - AutoHoldings |
subjects | ALGORITHMS Applied sciences Computer memory Computer programming Computer science control theory systems Computer systems and distributed systems. User interface EFFICIENCY Exact sciences and technology Loops MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS Memory and file management (including protection and security) MEMORY MANAGEMENT Memory organisation. Data processing PARALLEL PROCESSING Programming theory Software Studies TASK SCHEDULING Theoretical computing |
title | Loop transformations to prevent false sharing |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T08%3A19%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Loop%20transformations%20to%20prevent%20false%20sharing&rft.jtitle=International%20Journal%20of%20Parallel%20Programming&rft.au=GRANSTON,%20E.%20D&rft.date=1995-08-01&rft.volume=23&rft.issue=4&rft.spage=263&rft.epage=301&rft.pages=263-301&rft.issn=0885-7458&rft.eissn=1573-7640&rft.coden=IJPPE5&rft_id=info:doi/10.1007/BF02577768&rft_dat=%3Cproquest_osti_%3E743266114%3C/proquest_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=204294456&rft_id=info:pmid/&rfr_iscdi=true |