<?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-02073710</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="2026-05-24T21:20:38+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Dual tree traversal on integrated GPUs for astrophysical N-body simulations</title>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Fortin</surname>
              </persName>
              <email type="md5">e19e7b55edfec3940e3b1fc931ad011d</email>
              <email type="domain">univ-lille.fr</email>
              <idno type="idhal" notation="string">pierre-fortin</idno>
              <idno type="idhal" notation="numeric">2113</idno>
              <idno type="halauthorid" notation="string">13598-2113</idno>
              <idno type="IDREF">https://www.idref.fr/11411255X</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-3117-9122</idno>
              <affiliation ref="#struct-541706"/>
              <affiliation ref="#struct-410272"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Maxime</forename>
                <surname>Touche</surname>
              </persName>
              <idno type="halauthorid">1549302-0</idno>
              <orgName ref="#struct-413221"/>
              <affiliation ref="#struct-541706"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Pierre</forename>
                <surname>Fortin</surname>
              </persName>
              <email type="md5">e19e7b55edfec3940e3b1fc931ad011d</email>
              <email type="domain">univ-lille.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-07-23 16:13:37</date>
              <date type="whenModified">2024-10-30 13:33:06</date>
              <date type="whenReleased">2020-07-27 15:06:11</date>
              <date type="whenProduced">2019-09-01</date>
              <date type="whenEndEmbargoed">2020-07-23</date>
              <ref type="file" target="https://hal.sorbonne-universite.fr/hal-02073710v1/document">
                <date notBefore="2020-07-23"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.sorbonne-universite.fr/hal-02073710v1/file/article-HAL.pdf" id="file-2905702-2557053">
                <date notBefore="2020-07-23"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="179241">
                <persName>
                  <forename>Pierre</forename>
                  <surname>Fortin</surname>
                </persName>
                <email type="md5">e19e7b55edfec3940e3b1fc931ad011d</email>
                <email type="domain">univ-lille.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02073710</idno>
            <idno type="halUri">https://hal.sorbonne-universite.fr/hal-02073710</idno>
            <idno type="halBibtex">fortin:hal-02073710</idno>
            <idno type="halRefHtml">&lt;i&gt;International Journal of High Performance Computing Applications&lt;/i&gt;, 2019, 33 (5), pp.960-972. &lt;a target="_blank" href="https://dx.doi.org/10.1177/1094342019840806"&gt;&amp;#x27E8;10.1177/1094342019840806&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">International Journal of High Performance Computing Applications, 2019, 33 (5), pp.960-972. &amp;#x27E8;10.1177/1094342019840806&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2905702-2557053"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="LIP6" corresp="SORBONNE-UNIVERSITE">Laboratoire d'Informatique de Paris 6</idno>
            <idno type="stamp" n="CRISTAL-CFHP">CRIStAL - Calcul Formel et Haute Performance</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="SU-SCIENCES" corresp="SORBONNE-UNIVERSITE">Faculté des Sciences de Sorbonne Université</idno>
            <idno type="stamp" n="TEST-HALCNRS">Collection test HAL CNRS</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="SUPRA_MATHS_INFO">Mathématiques + Informatique</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Dual tree traversal on integrated GPUs for astrophysical N-body simulations</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Fortin</surname>
                  </persName>
                  <email type="md5">e19e7b55edfec3940e3b1fc931ad011d</email>
                  <email type="domain">univ-lille.fr</email>
                  <idno type="idhal" notation="string">pierre-fortin</idno>
                  <idno type="idhal" notation="numeric">2113</idno>
                  <idno type="halauthorid" notation="string">13598-2113</idno>
                  <idno type="IDREF">https://www.idref.fr/11411255X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-3117-9122</idno>
                  <affiliation ref="#struct-541706"/>
                  <affiliation ref="#struct-410272"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Maxime</forename>
                    <surname>Touche</surname>
                  </persName>
                  <idno type="halauthorid">1549302-0</idno>
                  <orgName ref="#struct-413221"/>
                  <affiliation ref="#struct-541706"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">14463</idno>
                <idno type="issn">1094-3420</idno>
                <title level="j">International Journal of High Performance Computing Applications</title>
                <imprint>
                  <publisher>SAGE Publications</publisher>
                  <biblScope unit="volume">33</biblScope>
                  <biblScope unit="issue">5</biblScope>
                  <biblScope unit="pp">960-972</biblScope>
                  <date type="datePub">2019-09-01</date>
                  <date type="dateEpub">2019-04-15</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1177/1094342019840806</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">astrophysics</term>
                <term xml:lang="en">fast multipole method</term>
                <term xml:lang="en">hybrid CPU-GPU algorithm</term>
                <term xml:lang="en">integrated GPU</term>
                <term xml:lang="en">dual tree traversal</term>
              </keywords>
              <classCode scheme="halDomain" n="scco.comp">Cognitive science/Computer science</classCode>
              <classCode scheme="halDomain" n="info.info-dc">Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>In astrophysical N-body simulations, O(N) fast multipole methods (FMMs) with dual tree traversal (DTT) on multi-core CPUs are faster than O(N log N) CPU tree-codes but can still be outperformed by GPU ones. In this paper, we aim at combining the best algorithm , namely FMM with DTT, with the most powerful hardware currently available, namely GPUs. In the astrophysical context requiring low accuracies and non-uniform particle distributions, we show that such combination can be achieved thanks to an hybrid CPU-GPU algorithm on integrated GPUs: while the DTT is performed on the CPU cores, the far-and near-field computations are all performed on the GPU cores. We show how to efficiently expose the interactions resulting from the DTT to the GPU cores, how to deploy both the far-and near-field computations on GPU and how to overlap the parallel DTT on CPU with GPU computations. Based on the falcON code and using OpenCL on AMD Accelerated Processing Units and on Intel integrated GPUs, this first heterogeneous deployment of DTT for FMM outperforms standard multi-core CPUs, and matches GPU and high-end CPU performance, being hence more cost-and power-efficient.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-541706" status="VALID">
          <orgName>Performance et Qualité des Algorithmes Numériques</orgName>
          <orgName type="acronym">PEQUAN</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-541703" type="direct"/>
            <relation active="#struct-413221" type="indirect"/>
            <relation name="UMR7606" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-541703" status="VALID">
          <idno type="IdRef">13558292X</idno>
          <idno type="RNSR">199712651U</idno>
          <idno type="ROR">https://ror.org/05krcen59</idno>
          <orgName>LIP6</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>4 Place JUSSIEU 75252 PARIS CEDEX 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lip6.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-413221" type="direct"/>
            <relation name="UMR7606" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-413221" status="VALID">
          <idno type="IdRef">221333754</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Sorbonne Université</orgName>
          <orgName type="acronym">SU</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>21 rue de l’École de médecine - 75006 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-universite.fr/</ref>
          </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="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>