Pajé, an interactive visualization tool for tuning multi-threaded parallel applications
Identifieur interne : 00A306 ( Main/Merge ); précédent : 00A305; suivant : 00A307Pajé, an interactive visualization tool for tuning multi-threaded parallel applications
Auteurs : J. Chassin De Kergommeaux [France] ; B. Stein [Brésil] ; P. E. Bernard [France]Source :
- Parallel Computing [ 0167-8191 ] ; 2000.
English descriptors
- Teeft :
- Active threads, Chassin, Communication links, Complex data structure, Computational load, Computer science, Control messages, Controller component, Current observation window, Data objects, Data structure, Elementary events, Elementary object, Elementary objects, Elsevier science, Functionality, Global time, Graphical displays, Graphical representation, Hash tables, Hierarchical structure, High number, Initial date, Inner parallelism, Input data, Instantaneous objects, Interactive visualization tool, Interactivity, Kergommeaux, Large number, Lecture notes, Lightweight processes, Local event, Local forces, Lter, Ltered, Ltered data, Main functionalities, Module, Molecular dynamics, Molecular dynamics application, More information, Mouse pointer, Neighbor node, Neighbor spaces, Node, Nodes work, Observation window, Other components, Parallel applications, Parallel processing, Parallel program, Parallel program visualization, Parallel programming environment, Parallel programs, Parallel system, Particular node, Performance data, Processor states, Program execution, Programming model, Pure graph, Remote memory accesses, Same node, Santa maria, Scalability, Semaphore, Several nodes, Several threads, Silver spring, Simulation, Simulation speed, Simulator, Source code, Synchronization, Technical report georgia institute, Termination date, Thread states, Threads, Time slice, Time slices, Trace reader, Trace readers, Trace visualizer, User, Visualization, Visualization component, Visualization components, Visualization environment, Visualization module, Visualization tool, Visualization tools.
Abstract
Abstract: This paper describes Pajé, an interactive visualization tool for displaying the execution of parallel applications where a potentially large number of communicating threads of various life-times execute on each node of a distributed memory parallel system. Pajé is capable of representing a wide variety of interactions between threads. The main characteristics of Pajé, interactivity and scalability, are exemplified by the performance tuning of a molecular dynamics application. In order to be easily extensible, the architecture of the system was based on components which are connected in a data flow graph to produce a given visualization tool. Innovative components were designed, in addition to “classical” components existing in similar visualization systems, to support scalability and interactivity.
Url:
DOI: 10.1016/S0167-8191(00)00010-7
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002E19
- to stream Istex, to step Curation: 002D82
- to stream Istex, to step Checkpoint: 001F78
Links to Exploration step
ISTEX:C2CA8A3EE6E314B54EC401137A509F3E73B53949Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Pajé, an interactive visualization tool for tuning multi-threaded parallel applications</title>
<author><name sortKey="Chassin De Kergommeaux, J" sort="Chassin De Kergommeaux, J" uniqKey="Chassin De Kergommeaux J" first="J." last="Chassin De Kergommeaux">J. Chassin De Kergommeaux</name>
</author>
<author><name sortKey="Stein, B" sort="Stein, B" uniqKey="Stein B" first="B." last="Stein">B. Stein</name>
</author>
<author><name sortKey="Bernard, P E" sort="Bernard, P E" uniqKey="Bernard P" first="P. E." last="Bernard">P. E. Bernard</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:C2CA8A3EE6E314B54EC401137A509F3E73B53949</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1016/S0167-8191(00)00010-7</idno>
<idno type="url">https://api.istex.fr/ark:/67375/6H6-F56G7NJ6-Z/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002E19</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002E19</idno>
<idno type="wicri:Area/Istex/Curation">002D82</idno>
<idno type="wicri:Area/Istex/Checkpoint">001F78</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001F78</idno>
<idno type="wicri:doubleKey">0167-8191:2000:Chassin De Kergommeaux J:paje:an:interactive</idno>
<idno type="wicri:Area/Main/Merge">00A306</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Pajé, an interactive visualization tool for tuning multi-threaded parallel applications</title>
<author><name sortKey="Chassin De Kergommeaux, J" sort="Chassin De Kergommeaux, J" uniqKey="Chassin De Kergommeaux J" first="J." last="Chassin De Kergommeaux">J. Chassin De Kergommeaux</name>
<affiliation></affiliation>
<affiliation></affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
<author><name sortKey="Stein, B" sort="Stein, B" uniqKey="Stein B" first="B." last="Stein">B. Stein</name>
<affiliation wicri:level="1"><country xml:lang="fr">Brésil</country>
<wicri:regionArea>Departamento de Eletrônica e Computação, Universidade Federal de Santa Maria</wicri:regionArea>
<wicri:noRegion>Universidade Federal de Santa Maria</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Brésil</country>
</affiliation>
</author>
<author><name sortKey="Bernard, P E" sort="Bernard, P E" uniqKey="Bernard P" first="P. E." last="Bernard">P. E. Bernard</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>Numath, INRIA Lorraine, BP 101, F-54600 Villers les Nancy</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Villers les Nancy</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Parallel Computing</title>
<title level="j" type="abbrev">PARCO</title>
<idno type="ISSN">0167-8191</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="2000">2000</date>
<biblScope unit="volume">26</biblScope>
<biblScope unit="issue">10</biblScope>
<biblScope unit="page" from="1253">1253</biblScope>
<biblScope unit="page" to="1274">1274</biblScope>
</imprint>
<idno type="ISSN">0167-8191</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0167-8191</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Active threads</term>
<term>Chassin</term>
<term>Communication links</term>
<term>Complex data structure</term>
<term>Computational load</term>
<term>Computer science</term>
<term>Control messages</term>
<term>Controller component</term>
<term>Current observation window</term>
<term>Data objects</term>
<term>Data structure</term>
<term>Elementary events</term>
<term>Elementary object</term>
<term>Elementary objects</term>
<term>Elsevier science</term>
<term>Functionality</term>
<term>Global time</term>
<term>Graphical displays</term>
<term>Graphical representation</term>
<term>Hash tables</term>
<term>Hierarchical structure</term>
<term>High number</term>
<term>Initial date</term>
<term>Inner parallelism</term>
<term>Input data</term>
<term>Instantaneous objects</term>
<term>Interactive visualization tool</term>
<term>Interactivity</term>
<term>Kergommeaux</term>
<term>Large number</term>
<term>Lecture notes</term>
<term>Lightweight processes</term>
<term>Local event</term>
<term>Local forces</term>
<term>Lter</term>
<term>Ltered</term>
<term>Ltered data</term>
<term>Main functionalities</term>
<term>Module</term>
<term>Molecular dynamics</term>
<term>Molecular dynamics application</term>
<term>More information</term>
<term>Mouse pointer</term>
<term>Neighbor node</term>
<term>Neighbor spaces</term>
<term>Node</term>
<term>Nodes work</term>
<term>Observation window</term>
<term>Other components</term>
<term>Parallel applications</term>
<term>Parallel processing</term>
<term>Parallel program</term>
<term>Parallel program visualization</term>
<term>Parallel programming environment</term>
<term>Parallel programs</term>
<term>Parallel system</term>
<term>Particular node</term>
<term>Performance data</term>
<term>Processor states</term>
<term>Program execution</term>
<term>Programming model</term>
<term>Pure graph</term>
<term>Remote memory accesses</term>
<term>Same node</term>
<term>Santa maria</term>
<term>Scalability</term>
<term>Semaphore</term>
<term>Several nodes</term>
<term>Several threads</term>
<term>Silver spring</term>
<term>Simulation</term>
<term>Simulation speed</term>
<term>Simulator</term>
<term>Source code</term>
<term>Synchronization</term>
<term>Technical report georgia institute</term>
<term>Termination date</term>
<term>Thread states</term>
<term>Threads</term>
<term>Time slice</term>
<term>Time slices</term>
<term>Trace reader</term>
<term>Trace readers</term>
<term>Trace visualizer</term>
<term>User</term>
<term>Visualization</term>
<term>Visualization component</term>
<term>Visualization components</term>
<term>Visualization environment</term>
<term>Visualization module</term>
<term>Visualization tool</term>
<term>Visualization tools</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: This paper describes Pajé, an interactive visualization tool for displaying the execution of parallel applications where a potentially large number of communicating threads of various life-times execute on each node of a distributed memory parallel system. Pajé is capable of representing a wide variety of interactions between threads. The main characteristics of Pajé, interactivity and scalability, are exemplified by the performance tuning of a molecular dynamics application. In order to be easily extensible, the architecture of the system was based on components which are connected in a data flow graph to produce a given visualization tool. Innovative components were designed, in addition to “classical” components existing in similar visualization systems, to support scalability and interactivity.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00A306 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00A306 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Merge |type= RBID |clé= ISTEX:C2CA8A3EE6E314B54EC401137A509F3E73B53949 |texte= Pajé, an interactive visualization tool for tuning multi-threaded parallel applications }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |