Conference paper Open Access

Learning-based Dynamic Pinning of Parallelized Applications in Many-Core Systems

Chasparis, Georgios; Janjic, Vladimir; Rossbory, Michael; Hammond, Kevin


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20190409133529.0</controlfield>
  <controlfield tag="001">1186660</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="g">Euro-Par 2018</subfield>
    <subfield code="a">24th International European Conference on Parallel and Distributed Computing (submitted to)</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of St Andrews</subfield>
    <subfield code="a">Janjic, Vladimir</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Software Competence Center Hagenberg GmbH</subfield>
    <subfield code="a">Rossbory, Michael</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of St Andrews</subfield>
    <subfield code="a">Hammond, Kevin</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">441706</subfield>
    <subfield code="z">md5:1439d8ba55534bd4f5b693e48f159416</subfield>
    <subfield code="u">https://zenodo.org/record/1186660/files/2018_EuroPar18_NUMAAdaptivePinning.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2018-03-01</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:1186660</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Software Competence Center Hagenberg GmbH</subfield>
    <subfield code="0">(orcid)0000-0003-3059-3575</subfield>
    <subfield code="a">Chasparis, Georgios</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Learning-based Dynamic Pinning of Parallelized Applications in Many-Core Systems</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">644235</subfield>
    <subfield code="a">REfactoring Parallel Heterogeneous Resource-Aware Applications  - a Software Engineering Approach</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This paper introduces a reinforcement-learning based resource allocation framework for dynamic placement of threads of parallel applications to Non-Uniform Memory Access (NUMA) many-core systems. We propose a two-level learning-based decision making process, where at the first level each thread independently decides on which group of cores (NUMA node) it will execute, and on the second level it decides to which particular core from the group it will be pinned. Additionally, a novel performance-based learning dynamics is introduced to handle measurement noise and rapid variations in the performance of the threads. Experiments on a 24-core system show the improvement of up to 16% in the execution time of parallel applications under our framework, compared to the Linux operating system scheduler.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1186659</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1186660</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
5
14
views
downloads
All versions This version
Views 55
Downloads 1414
Data volume 6.2 MB6.2 MB
Unique views 55
Unique downloads 1414

Share

Cite as