Scheduling of OR-parallel Prolog on a scalable, reconfigurable, distributed-memory multiprocessor
Identifieur interne : 003248 ( Main/Exploration ); précédent : 003247; suivant : 003249Scheduling of OR-parallel Prolog on a scalable, reconfigurable, distributed-memory multiprocessor
Auteurs : J. Briat [France] ; M. Favre [France] ; C. Geyer [Brésil] ; J. Chassin De Kergommeaux [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 1991.
Abstract
Abstract: The OPERA project aims at efficiently implementing Prolog on a scalable, reconfigurable distributed-memory architecture. The OPERA computational model exploits OR-parallelism following a classical multisequential approach: each processor executes a complete Prolog engine based on the WAM; inter-processor communication is reduced to work installation, the complete state of an active Prolog engine being copied to an idle one. Scheduling is performed by a hierarchy of specialized processors, operating in parallel of the computation of the Prolog program. To avoid costly synchronization, schedulers use an approximate representation of the state of the system. Because of the important overhead of task installation in a distributed-memory system, only workers having a large amount of work to execute can give work to idle workers. Several dynamic work regulation strategies have been designed and are currently being tested. The prototype implementation of OPERA on a transputer-based Supernode is one of the most efficient existing Prolog implementations on the transputer and reaches effective speed-ups in parallel over efficient sequential Prolog systems.
Url:
DOI: 10.1007/3-540-54152-7_76
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000051
- to stream Istex, to step Curation: 000051
- to stream Istex, to step Checkpoint: 001212
- to stream Main, to step Merge: 003393
- to stream Main, to step Curation: 003248
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Scheduling of OR-parallel Prolog on a scalable, reconfigurable, distributed-memory multiprocessor</title><author><name sortKey="Briat, J" sort="Briat, J" uniqKey="Briat J" first="J." last="Briat">J. Briat</name></author><author><name sortKey="Favre, M" sort="Favre, M" uniqKey="Favre M" first="M." last="Favre">M. Favre</name></author><author><name sortKey="Geyer, C" sort="Geyer, C" uniqKey="Geyer C" first="C." last="Geyer">C. Geyer</name></author><author><name sortKey="Chassin De Kergommeaux, J" sort="Chassin De Kergommeaux, J" uniqKey="Chassin De Kergommeaux J" first="J." last="Chassin De Kergommeaux">J. Chassin De Kergommeaux</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:21A37369D25D3F96C68D9EF3B8122264041C5ED6</idno><date when="1991" year="1991">1991</date><idno type="doi">10.1007/3-540-54152-7_76</idno><idno type="url">https://api.istex.fr/document/21A37369D25D3F96C68D9EF3B8122264041C5ED6/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000051</idno><idno type="wicri:Area/Istex/Curation">000051</idno><idno type="wicri:Area/Istex/Checkpoint">001212</idno><idno type="wicri:doubleKey">0302-9743:1991:Briat J:scheduling:of:or</idno><idno type="wicri:Area/Main/Merge">003393</idno><idno type="wicri:Area/Main/Curation">003248</idno><idno type="wicri:Area/Main/Exploration">003248</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Scheduling of OR-parallel Prolog on a scalable, reconfigurable, distributed-memory multiprocessor</title><author><name sortKey="Briat, J" sort="Briat, J" uniqKey="Briat J" first="J." last="Briat">J. Briat</name><affiliation><wicri:noCountry code="subField">Grenoble Cedex</wicri:noCountry></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Favre, M" sort="Favre, M" uniqKey="Favre M" first="M." last="Favre">M. Favre</name><affiliation><wicri:noCountry code="subField">Grenoble Cedex</wicri:noCountry></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Geyer, C" sort="Geyer, C" uniqKey="Geyer C" first="C." last="Geyer">C. Geyer</name><affiliation><wicri:noCountry code="subField">Grenoble Cedex</wicri:noCountry></affiliation><affiliation wicri:level="2"><country xml:lang="fr">Brésil</country><wicri:regionArea>CPGCC-USRGS, University of Porto Alegre, caixa postal 1501, 90000, Porto Alegre RS</wicri:regionArea><placeName><region type="state">Rio Grande do Sul</region></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Brésil</country></affiliation></author><author><name sortKey="Chassin De Kergommeaux, J" sort="Chassin De Kergommeaux, J" uniqKey="Chassin De Kergommeaux J" first="J." last="Chassin De Kergommeaux">J. Chassin De Kergommeaux</name><affiliation><wicri:noCountry code="subField">Meylan</wicri:noCountry></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>1991</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">21A37369D25D3F96C68D9EF3B8122264041C5ED6</idno><idno type="DOI">10.1007/3-540-54152-7_76</idno><idno type="ChapterID">Chap22</idno><idno type="ChapterID">22</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: The OPERA project aims at efficiently implementing Prolog on a scalable, reconfigurable distributed-memory architecture. The OPERA computational model exploits OR-parallelism following a classical multisequential approach: each processor executes a complete Prolog engine based on the WAM; inter-processor communication is reduced to work installation, the complete state of an active Prolog engine being copied to an idle one. Scheduling is performed by a hierarchy of specialized processors, operating in parallel of the computation of the Prolog program. To avoid costly synchronization, schedulers use an approximate representation of the state of the system. Because of the important overhead of task installation in a distributed-memory system, only workers having a large amount of work to execute can give work to idle workers. Several dynamic work regulation strategies have been designed and are currently being tested. The prototype implementation of OPERA on a transputer-based Supernode is one of the most efficient existing Prolog implementations on the transputer and reaches effective speed-ups in parallel over efficient sequential Prolog systems.</div></front></TEI><affiliations><list><country><li>Brésil</li><li>France</li></country><region><li>Rio Grande do Sul</li></region></list><tree><country name="France"><noRegion><name sortKey="Briat, J" sort="Briat, J" uniqKey="Briat J" first="J." last="Briat">J. Briat</name></noRegion><name sortKey="Chassin De Kergommeaux, J" sort="Chassin De Kergommeaux, J" uniqKey="Chassin De Kergommeaux J" first="J." last="Chassin De Kergommeaux">J. Chassin De Kergommeaux</name><name sortKey="Favre, M" sort="Favre, M" uniqKey="Favre M" first="M." last="Favre">M. Favre</name></country><country name="Brésil"><region name="Rio Grande do Sul"><name sortKey="Geyer, C" sort="Geyer, C" uniqKey="Geyer C" first="C." last="Geyer">C. Geyer</name></region><name sortKey="Geyer, C" sort="Geyer, C" uniqKey="Geyer C" first="C." last="Geyer">C. Geyer</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003248 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 003248 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= OperaV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:21A37369D25D3F96C68D9EF3B8122264041C5ED6
|texte= Scheduling of OR-parallel Prolog on a scalable, reconfigurable, distributed-memory multiprocessor
}}
| This area was generated with Dilib version V0.6.21. |  |