April 4, 2022 Conference paper Open Access

Rafail Tsirbas; Giorgos Vasiliadis; Sotiris Ioannidis

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">machine learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">inference</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">gpgpu</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">scheduling</subfield>
  </datafield>
  <controlfield tag="005">20220818065904.0</controlfield>
  <controlfield tag="001">6410912</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">May 30 – June 3, 2022</subfield>
    <subfield code="g">IPDPSW 2022</subfield>
    <subfield code="a">2022 IEEE International Parallel and Distributed Processing Symposium Workshops</subfield>
    <subfield code="c">Virtual</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Foundation for Research and Technology - Hellas, Hellenic Mediterranean University</subfield>
    <subfield code="a">Giorgos Vasiliadis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Foundation for Research and Technology - Hellas, Technical University of Crete</subfield>
    <subfield code="a">Sotiris Ioannidis</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">828319</subfield>
    <subfield code="z">md5:7d518d201181000d874a8b48fcb3872f</subfield>
    <subfield code="u">https://zenodo.org/record/6410912/files/IPDPSW2022_Tsirmpas_et_al_preprint.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">https://www.ipdps.org</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-04-04</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-collabs2020</subfield>
    <subfield code="p">user-marvel_project</subfield>
    <subfield code="p">user-c4iiot</subfield>
    <subfield code="o">oai:zenodo.org:6410912</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Foundation for Research and Technology - Hellas</subfield>
    <subfield code="a">Rafail Tsirbas</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">The Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-c4iiot</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-collabs2020</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-marvel_project</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">830927</subfield>
    <subfield code="a">Cyber security cOmpeteNCe fOr Research anD InnovAtion</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">833828</subfield>
    <subfield code="a">Cyber security 4.0: protecting the Industrial Internet Of Things</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">871518</subfield>
    <subfield code="a">A COmprehensive cyber-intelligence framework for resilient coLLABorative manufacturing Systems</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">957337</subfield>
    <subfield code="a">Multimodal Extreme Scale Data Analytics for Smart Cities Environments</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://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;A plethora of applications are using machine learning, the operations of which are becoming more complex and require additional computing power. At the same time, typical commodity system setups (including desktops, servers, and embedded devices) are now offering different processing devices, the most often of which are multi-core CPUs, integrated GPUs, and discrete GPUs. In this paper, we follow a data-driven approach, where we first show the performance of different processing devices when executing a diversified set of inference engines; some processing devices perform better for different performance metrics (e.g., throughput, latency, and power consumption), while at the same time, these metrics may also deviate significantly among different applications. Based on these findings, we propose an adaptive scheduling approach, tailored for machine learning inference operations, that enables the use of the most efficient processing device available. Our scheduler is device-agnostic and can respond quickly to dynamic fluctuations that occur at real-time, such as data bursts, application overloads and system changes. The experimental results show that it is able to match the peak throughput, by predicting correctly the optimal processing device with an accuracy of 92.5%, with energy savings up to 10%.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isPublishedIn</subfield>
    <subfield code="a">10.1109/IPDPSW55747.2022.00017</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.6410911</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.6410912</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>