Dataset Open Access

Profiling of RT-PICLS Code

Kelling, Jeffrey; Juckeland, Guido


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="DOI">10.14278/rodare.16</identifier>
  <creators>
    <creator>
      <creatorName>Kelling, Jeffrey</creatorName>
      <givenName>Jeffrey</givenName>
      <familyName>Kelling</familyName>
      <affiliation>Helmholtz-Zentrum Dresden-Rossendorf</affiliation>
    </creator>
    <creator>
      <creatorName>Juckeland, Guido</creatorName>
      <givenName>Guido</givenName>
      <familyName>Juckeland</familyName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-9935-4428</nameIdentifier>
      <affiliation>Helmholtz-Zentrum Dresden-Rossendorf</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Profiling of RT-PICLS Code</title>
  </titles>
  <publisher>Rodare</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>Scorep</subject>
    <subject>Vampir</subject>
    <subject>Tracing</subject>
    <subject>Profiling</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-04-25</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://rodare.hzdr.de/record/16</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URN" relationType="IsSupplementTo">urn:nbn:de:bsz:d120-qucosa-224404</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsIdenticalTo">https://www.hzdr.de/publications/Publ-27417</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.14278/rodare.15</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/fwc</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://rodare.hzdr.de/communities/rodare</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;It was observed, that the RT-PICLS code ran by FWKT on the hypnos cluster was producing an unusual amount of system load, according to Ganglia metrics. Since this may point to an IO-problem in the code, this code was analyzed more closely.&lt;/p&gt;

&lt;p&gt;RT-PICLS was run with additionally provided input data on 64 CPU cores (AMD Opteron) in a single node of the hypnos cluster. Score-P 4.0 with IO-tracing support was used for profiling and tracing of the application. A developer version of Vampir 9.2 [3] enabled graphical analysis of the traces.&lt;/p&gt;

&lt;p&gt;Different file systems were evaluated for storing the output:&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;&lt;strong&gt;bigdata&lt;/strong&gt;: the high-performance file system of the cluster based on GPFS.&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;nfs&lt;/strong&gt;: a loop-mounted EXT4 image mounted to the current compute node via NFS.&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;scr&lt;/strong&gt;: the local scratch file-system of the compute node.&lt;/li&gt;
	&lt;li&gt;&lt;strong&gt;tmpfs&lt;/strong&gt;: a virtual filesystem, physically located in the main memory of the compute node.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;The trace files that were used to compile the referenced report are collected in this upload.&lt;/p&gt;</description>
  </descriptions>
</resource>
976
451
views
downloads
All versions This version
Views 976976
Downloads 451451
Data volume 3.4 TB3.4 TB
Unique views 578578
Unique downloads 101101

Share

Cite as