<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01502749</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-20T03:09:40+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Exploiting Two-Level Parallelism by Aggregating Computing Resources in Task-Based Applications Over Accelerator-Based Machines</title>
            <author role="aut">
              <persName>
                <forename type="first">Terry</forename>
                <surname>Cojean</surname>
              </persName>
              <email type="md5">bf9de7a428d3cafaee786737277014f7</email>
              <email type="domain">posteo.net</email>
              <idno type="idhal" notation="string">terry-cojean</idno>
              <idno type="idhal" notation="numeric">750557</idno>
              <idno type="halauthorid" notation="string">26424-750557</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABE-4779-2021</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1560-921X</idno>
              <affiliation ref="#struct-409747"/>
              <affiliation ref="#struct-259761"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Terry</forename>
                <surname>Cojean</surname>
              </persName>
              <email type="md5">bf9de7a428d3cafaee786737277014f7</email>
              <email type="domain">posteo.net</email>
            </editor>
            <funder ref="#projanr-37127"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2017-04-24 17:13:12</date>
              <date type="whenModified">2025-05-26 14:36:02</date>
              <date type="whenReleased">2017-04-25 08:44:10</date>
              <date type="whenProduced">2016-04-12</date>
              <ref type="annex" n="0" target="https://inria.hal.science/hal-01502749v1/file/siampp16.pdf" id="file-1513182-1574587">
                <date notBefore="2017-04-24"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="319401">
                <persName>
                  <forename>Terry</forename>
                  <surname>Cojean</surname>
                </persName>
                <email type="md5">bf9de7a428d3cafaee786737277014f7</email>
                <email type="domain">posteo.net</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01502749</idno>
            <idno type="halUri">https://inria.hal.science/hal-01502749</idno>
            <idno type="halBibtex">cojean:hal-01502749</idno>
            <idno type="halRefHtml">&lt;i&gt;SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2016)&lt;/i&gt;, Apr 2016, Paris, France</idno>
            <idno type="halRef">SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2016), Apr 2016, Paris, France</idno>
            <availability status="restricted">
              <licence target="https://hal.science/licences/copyright/">Copyright - All rights reserved<ref corresp="#file-1513182-1574587"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="ENSEIRB">Ecole Nationale Supérieure d'Electronique, Informatique et Radiocommunications de Bordeaux</idno>
            <idno type="stamp" n="INRIA-BORDEAUX">INRIA Bordeaux - Sud-Ouest</idno>
            <idno type="stamp" n="UNIV-BORDEAUX">Université de Bordeaux</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="PLAFRIM">Plateforme Fédérative pour la Recherche en Informatique et Mathématiques</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="TEST3-HALCNRS">TEST3-HALCNRS</idno>
            <idno type="stamp" n="UNIVERSITE-BORDEAUX">Université de Bordeaux</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="0">No</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Exploiting Two-Level Parallelism by Aggregating Computing Resources in Task-Based Applications Over Accelerator-Based Machines</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Terry</forename>
                    <surname>Cojean</surname>
                  </persName>
                  <email type="md5">bf9de7a428d3cafaee786737277014f7</email>
                  <email type="domain">posteo.net</email>
                  <idno type="idhal" notation="string">terry-cojean</idno>
                  <idno type="idhal" notation="numeric">750557</idno>
                  <idno type="halauthorid" notation="string">26424-750557</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/ABE-4779-2021</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1560-921X</idno>
                  <affiliation ref="#struct-409747"/>
                  <affiliation ref="#struct-259761"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>SIAM Conference on Parallel Processing for Scientific Computing (SIAM PP 2016)</title>
                  <date type="start">2016-04-12</date>
                  <date type="end">2016-04-15</date>
                  <settlement>Paris</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint>
                  <date type="datePub">2016-04-12</date>
                </imprint>
              </monogr>
              <ref type="publisher">http://www.siam.org/meetings/pp16/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-dc">Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Computing platforms are now extremely complex providing an increasing number of CPUs and accelerators. This trend makes balancing computations between these heterogeneous resources performance critical. In this paper we tackle the task granularity problem and we propose aggregating several CPUs in order to execute larger parallel tasks and thus find a better equilibrium between the workload assigned to the CPUs and the one assigned to the GPUs. To this end, we rely on the notion of scheduling contexts in order to isolate the parallel tasks and thus delegate the management of the task parallelism to the inner scheduling strategy. We demonstrate the relevance of our approach through the dense Cholesky factorization kernel implemented on top of the StarPU task-based runtime system. We allow having parallel elementary tasks and using Intel MKL parallel implementation optimized through the use of the OpenMP runtime system. We show how our approach handles the interaction between the StarPU and the OpenMP runtime systems and how it exploits the parallelism of modern accelerator-based machines. We present experimental results showing that our solution outperforms state of the art implementations to reach a peak performance of 4.5 TFlop/s on a platform equipped with 20 CPU cores and 4 GPU devices. </p>
            </abstract>
            <particDesc>
              <org type="consortium">Plafrim</org>
            </particDesc>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-409747" status="VALID">
          <idno type="RNSR">201521157L</idno>
          <idno type="ROR">https://ror.org/00zzgef46</idno>
          <orgName>STatic Optimizations, Runtime Methods</orgName>
          <orgName type="acronym">STORM</orgName>
          <date type="start">2015-01-01</date>
          <date type="end">2026-06-30</date>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour 33405 Talence cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/storm</ref>
          </desc>
          <listRelation>
            <relation active="#struct-3102" type="direct"/>
            <relation active="#struct-259761" type="indirect"/>
            <relation active="#struct-300366" type="indirect"/>
            <relation name="UMR5800 / URA1304" active="#struct-441569" type="indirect"/>
            <relation active="#struct-104751" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-259761" status="VALID">
          <idno type="IdRef">175206562</idno>
          <idno type="ROR">https://ror.org/057qpr032</idno>
          <orgName>Université de Bordeaux</orgName>
          <orgName type="acronym">UB</orgName>
          <desc>
            <address>
              <addrLine>35, place Pey Berland - 33076 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-3102" status="VALID">
          <idno type="IdRef">155054465</idno>
          <idno type="ISNI">0000000122898198</idno>
          <idno type="RNSR">199511665F</idno>
          <idno type="ROR">https://ror.org/03adqg323</idno>
          <idno type="Wikidata">Q3214395</idno>
          <orgName>Laboratoire Bordelais de Recherche en Informatique</orgName>
          <orgName type="acronym">LaBRI</orgName>
          <date type="start">1988-01-01</date>
          <desc>
            <address>
              <addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.labri.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-259761" type="direct"/>
            <relation active="#struct-300366" type="direct"/>
            <relation name="UMR5800 / URA1304" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300366" status="VALID">
          <orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104751" status="VALID">
          <idno type="RNSR">200818243Z</idno>
          <idno type="ROR">https://ror.org/03tjcj052</idno>
          <orgName>Centre Inria de l'Université de Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour, 33405 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/bordeaux/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-37127" status="VALID">
          <idno type="anr">ANR-13-MONU-0007</idno>
          <idno type="program">Modèles Numériques</idno>
          <orgName>SOLHAR</orgName>
          <desc>Solveurs pour architectures hétérogènes utilisant des supports d'exécution</desc>
          <date type="start">2013</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>