Journal article Open Access

A Design Space Exploration Framework for Convolutional Neural Networks Implemented on Edge Devices

Tsimpourlas, Foivos; Papadopoulos, Lazaros; Bartsokas, Anastasios; Soudris, Dimitrios


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/3380072</identifier>
  <creators>
    <creator>
      <creatorName>Tsimpourlas, Foivos</creatorName>
      <givenName>Foivos</givenName>
      <familyName>Tsimpourlas</familyName>
      <affiliation>School of Electrical and Computer Engineering, National Technical University of Athens (Zographou Campus), Athens, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Papadopoulos, Lazaros</creatorName>
      <givenName>Lazaros</givenName>
      <familyName>Papadopoulos</familyName>
      <affiliation>School of Electrical and Computer Engineering, National Technical University of Athens (Zographou Campus), Athens, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Bartsokas, Anastasios</creatorName>
      <givenName>Anastasios</givenName>
      <familyName>Bartsokas</familyName>
      <affiliation>School of Electrical and Computer Engineering, National Technical University of Athens (Zographou Campus), Athens, Greece</affiliation>
    </creator>
    <creator>
      <creatorName>Soudris, Dimitrios</creatorName>
      <givenName>Dimitrios</givenName>
      <familyName>Soudris</familyName>
      <affiliation>School of Electrical and Computer Engineering, National Technical University of Athens (Zographou Campus), Athens, Greece</affiliation>
    </creator>
  </creators>
  <titles>
    <title>A Design Space Exploration Framework for Convolutional Neural Networks Implemented on Edge Devices</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <dates>
    <date dateType="Issued">2018-07-18</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Journal article</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3380072</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1109/TCAD.2018.2857280</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Deploying convolutional neural networks (CNNs) in embedded devices that operate at the edges of Internet of Things (IoT) networks provides various advantages in terms of performance, energy efficiency, and security in comparison with the alternative approach of transmitting large volumes of data for processing to the cloud. However, the implementation of CNNs on low power embedded devices is challenging due to the limited computational resources they provide and to the large resource requirements of state-of-the-art CNNs. In this paper, we propose a framework for the efficient deployment of CNNs in low power processor-based architectures used as edge devices in IoT networks. The framework leverages design space exploration (DSE) techniques to identify efficient implementations in terms of execution time and energy consumption. The exploration parameter is the utilization of hardware resources of the edge devices. The proposed framework is evaluated using a set of 6 state-of-the-art CNNs deployed in the Intel/Movidius Myriad2 low power embedded platform. The results show that using the maximum available amount of resources is not always the optimal solution in terms of performance and energy efficiency. Fine-tuned resource management based on DSE, reduces the execution time up to 3.6% and the energy consumption up to 7.7% in comparison with straightforward implementations.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/780572/">780572</awardNumber>
      <awardTitle>Software Development toolKit for Energy optimization and technical Debt elimination</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
37
176
views
downloads
Views 37
Downloads 176
Data volume 197.5 MB
Unique views 36
Unique downloads 165

Share

Cite as