6 Şubat 2020 Dergi makalesi Açık Erişim

Cini, Nevin; Yalcin, Gülay

DataCite XML

<?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://aperta.ulakbim.gov.tr/record/273917</identifier>
  <creators>
    <creator>
      <creatorName>Cini, Nevin</creatorName>
      <givenName>Nevin</givenName>
      <familyName>Cini</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-5348-4043</nameIdentifier>
    </creator>
    <creator>
      <creatorName>Yalcin, Gülay</creatorName>
      <givenName>Gülay</givenName>
      <familyName>Yalcin</familyName>
    </creator>
  </creators>
  <titles>
    <title>A Methodology For Comparing The Reliability Of Gpu-Based And Cpu-Based Hpcs</title>
  </titles>
  <publisher>Aperta</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>Computer systems organization</subject>
    <subject>Reliability</subject>
    <subject>System failure</subject>
    <subject>log file analysis</subject>
    <subject>checkpoint/recovery</subject>
    <subject>Graphics Processing Unit</subject>
    <subject>Yüksek başarımlı hesaplama</subject>
    <subject>High Performance Computing</subject>
    <subject>Dependable and fault-tolerant systems and networks</subject>
    <subject>Hardware</subject>
    <subject>Hardware test</subject>
    <subject>Robustness</subject>
    <subject>Computer systems organization</subject>
    <subject>Cross-computing tools and techniques</subject>
    <subject>Software and its engineering</subject>
    <subject>Software organization and properties</subject>
    <subject>Extra-functional properties</subject>
    <subject>failure prediction</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-02-06</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Journal article</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://aperta.ulakbim.gov.tr/record/273917</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1145/3372790</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Today, GPUs are widely used as coprocessors/accelerators in High-Performance Heterogeneous Computing&lt;br&gt;
due to their many advantages. However, many researches emphasize that GPUs are not as reliable as desired&lt;br&gt;
yet. Despite the fact that GPUs are more vulnerable to hardware errors than CPUs, the use of GPUs in HPCs&lt;br&gt;
is increasing more and more. Moreover, due to native reliability problems of GPUs, combining a great number&lt;br&gt;
of GPUs with CPUs can significantly increase HPCs&amp;rsquo; failure rates. For this reason, analyzing the reliability&lt;br&gt;
characteristics of GPU-based HPCs has become a very important issue. Therefore, in this study we evaluate&lt;br&gt;
the reliability of GPU-based HPCs. For this purpose, we first examined field data analysis studies for GPU-&lt;br&gt;
based and CPU-based HPCs and identified factors that could increase systems failure/error rates. We then&lt;br&gt;
compared GPU-based HPCs with CPU-based HPCs in terms of reliability with the help of these factors in&lt;br&gt;
order to point out reliability challenges of GPU-based HPCs. Our primary goal is to present a study that can&lt;br&gt;
guide the researchers in this field by indicating the current state of GPU-based heterogeneous HPCs and&lt;br&gt;
requirements for the future, in terms of reliability. Our second goal is to offer a methodology to compare the&lt;br&gt;
reliability of GPU-based HPCs and CPU-based HPCs. To the best of our knowledge, this is the first survey&lt;br&gt;
study to compare the reliability of GPU-based and CPU-based HPCs in a systematic manner.&lt;/p&gt;</description>
  </descriptions>
</resource>