Conference paper Open Access

The Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures

Rafail Tsirbas; Giorgos Vasiliadis; Sotiris Ioannidis

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.6410912">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.6410912</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.6410912"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Rafail Tsirbas</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Foundation for Research and Technology - Hellas</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Giorgos Vasiliadis</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Foundation for Research and Technology - Hellas, Hellenic Mediterranean University</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Sotiris Ioannidis</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Foundation for Research and Technology - Hellas, Technical University of Crete</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>The Best of Many Worlds: Scheduling Machine Learning Inference on CPU-GPU Integrated Architectures</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2022</dct:issued>
    <dcat:keyword>machine learning</dcat:keyword>
    <dcat:keyword>inference</dcat:keyword>
    <dcat:keyword>gpgpu</dcat:keyword>
    <dcat:keyword>scheduling</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/830927/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/833828/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/871518/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/957337/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2022-04-04</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/6410912"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/6410912</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://doi.org/10.1109/IPDPSW55747.2022.00017"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.6410911"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/c4iiot"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/collabs2020"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/marvel_project"/>
    <dct:description>&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;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.6410912"/>
        <dcat:byteSize>828319</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/6410912/files/IPDPSW2022_Tsirmpas_et_al_preprint.pdf"/>
        <dcat:mediaType>application/pdf</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/830927/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">830927</dct:identifier>
    <dct:title>Cyber security cOmpeteNCe fOr Research anD InnovAtion</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/833828/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">833828</dct:identifier>
    <dct:title>Cyber security 4.0: protecting the Industrial Internet Of Things</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/871518/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">871518</dct:identifier>
    <dct:title>A COmprehensive cyber-intelligence framework for resilient coLLABorative manufacturing Systems</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/957337/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">957337</dct:identifier>
    <dct:title>Multimodal Extreme Scale Data Analytics for Smart Cities Environments</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/100010661</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
404
281
views
downloads
All versions This version
Views 404404
Downloads 281281
Data volume 232.8 MB232.8 MB
Unique views 343343
Unique downloads 269269
More info on how stats are collected.
Indexed in
Publication date:
April 4, 2022
DOI:
10.5281/zenodo.6410912

Zenodo DOI Badge

DOI 

10.5281/zenodo.6410912

Markdown 

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.6410912.svg)](https://doi.org/10.5281/zenodo.6410912)

reStructedText 

.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.6410912.svg
   :target: https://doi.org/10.5281/zenodo.6410912

HTML 

<a href="https://doi.org/10.5281/zenodo.6410912"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.6410912.svg" alt="DOI"></a>

Image URL 

https://zenodo.org/badge/DOI/10.5281/zenodo.6410912.svg

Target URL 

https://doi.org/10.5281/zenodo.6410912

Keyword(s):
machine learning inference gpgpu scheduling
Grants:
European Commission:
  • CONCORDIA - Cyber security cOmpeteNCe fOr Research anD InnovAtion (830927)
  • C4IIoT - Cyber security 4.0: protecting the Industrial Internet Of Things (833828)
  • COLLABS - A COmprehensive cyber-intelligence framework for resilient coLLABorative manufacturing Systems (871518)
  • MARVEL - Multimodal Extreme Scale Data Analytics for Smart Cities Environments (957337)
Meeting:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW 2022), Virtual, May 30 – June 3, 2022
Related identifiers:
Published in
Communities:
License (for files):
Creative Commons Attribution 4.0 International

Versions

Version 1 10.5281/zenodo.6410912 Apr 4, 2022
Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.6410911. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export