A comparison of the Cray XMT and XMT‐2
Identifieur interne : 001D58 ( Istex/Corpus ); précédent : 001D57; suivant : 001D59A comparison of the Cray XMT and XMT‐2
Auteurs : Shahid H. Bokhari ; Saniyah S. BokhariSource :
- Concurrency and Computation: Practice and Experience [ 1532-0626 ] ; 2013-10.
English descriptors
- Teeft :
- Algorithm, Better performance, Bioinformatics, Biomedical informatics, Bokhari, Clock cycles, Computat, Computational biology, Concurrency, Concurrency computat, Copyright, Cougar, Cray, Dynamic programming, Dynamic programming codes, Egret, Exper, John wiley sons, Large problem sizes, Main loop, Matrix, Matrix multiplication, Matterhorn, Maximum number, Memory access, Memory access times, Memory accesses, Memory cycles, Memory operations, Memory subsystem, Multithreaded supercomputers, Ohio state university, Parallelizing, Pract, Problem size, Problem sizes, Proc, Proc cougar, Proc matterhorn, Processor, Processor cougar, Processor egret, Processors figure, Reassortment, Reassortment networks, Saturation phenomenon, Sequence alignment, Slab size, Small problem sizes, Supercomputing, Supercomputing centre, Target machines, Total number, Traps increase, Virus reassortment algorithm.
Abstract
We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including decreasing the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/cpe.2909
Links to Exploration step
ISTEX:047DFC4DBE0E86719879263C10CDBD10A1EF0C9ALe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A comparison of the Cray XMT and XMT‐2</title><author><name sortKey="Bokhari, Shahid H" sort="Bokhari, Shahid H" uniqKey="Bokhari S" first="Shahid H." last="Bokhari">Shahid H. Bokhari</name><affiliation><mods:affiliation>Department of Biomedical Informatics, The Ohio State University, OH, Columbus, USA</mods:affiliation></affiliation><affiliation><mods:affiliation>Correspondence to: Shahid H. Bokhari, Department of Biomedical Informatics, 3190 Graves Hall, 333 W. 10th Avenue Columbus, OH 43210, USA.E‐mail:</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: shahid@bmi.osu.edu</mods:affiliation></affiliation></author><author><name sortKey="Bokhari, Saniyah S" sort="Bokhari, Saniyah S" uniqKey="Bokhari S" first="Saniyah S." last="Bokhari">Saniyah S. Bokhari</name><affiliation><mods:affiliation>Department of Computer Science and Engineering, The Ohio State University, OH, Columbus, USA</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:047DFC4DBE0E86719879263C10CDBD10A1EF0C9A</idno><date when="2013" year="2013">2013</date><idno type="doi">10.1002/cpe.2909</idno><idno type="url">https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">001D58</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">001D58</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main">A comparison of the Cray XMT and XMT‐2</title><author><name sortKey="Bokhari, Shahid H" sort="Bokhari, Shahid H" uniqKey="Bokhari S" first="Shahid H." last="Bokhari">Shahid H. Bokhari</name><affiliation><mods:affiliation>Department of Biomedical Informatics, The Ohio State University, OH, Columbus, USA</mods:affiliation></affiliation><affiliation><mods:affiliation>Correspondence to: Shahid H. Bokhari, Department of Biomedical Informatics, 3190 Graves Hall, 333 W. 10th Avenue Columbus, OH 43210, USA.E‐mail:</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: shahid@bmi.osu.edu</mods:affiliation></affiliation></author><author><name sortKey="Bokhari, Saniyah S" sort="Bokhari, Saniyah S" uniqKey="Bokhari S" first="Saniyah S." last="Bokhari">Saniyah S. Bokhari</name><affiliation><mods:affiliation>Department of Computer Science and Engineering, The Ohio State University, OH, Columbus, USA</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j" type="main">Concurrency and Computation: Practice and Experience</title><title level="j" type="alt">CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE</title><idno type="ISSN">1532-0626</idno><idno type="eISSN">1532-0634</idno><imprint><biblScope unit="vol">25</biblScope><biblScope unit="issue">15</biblScope><biblScope unit="page" from="2123">2123</biblScope><biblScope unit="page" to="2139">2139</biblScope><biblScope unit="page-count">17</biblScope><date type="published" when="2013-10">2013-10</date></imprint><idno type="ISSN">1532-0626</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1532-0626</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Algorithm</term><term>Better performance</term><term>Bioinformatics</term><term>Biomedical informatics</term><term>Bokhari</term><term>Clock cycles</term><term>Computat</term><term>Computational biology</term><term>Concurrency</term><term>Concurrency computat</term><term>Copyright</term><term>Cougar</term><term>Cray</term><term>Dynamic programming</term><term>Dynamic programming codes</term><term>Egret</term><term>Exper</term><term>John wiley sons</term><term>Large problem sizes</term><term>Main loop</term><term>Matrix</term><term>Matrix multiplication</term><term>Matterhorn</term><term>Maximum number</term><term>Memory access</term><term>Memory access times</term><term>Memory accesses</term><term>Memory cycles</term><term>Memory operations</term><term>Memory subsystem</term><term>Multithreaded supercomputers</term><term>Ohio state university</term><term>Parallelizing</term><term>Pract</term><term>Problem size</term><term>Problem sizes</term><term>Proc</term><term>Proc cougar</term><term>Proc matterhorn</term><term>Processor</term><term>Processor cougar</term><term>Processor egret</term><term>Processors figure</term><term>Reassortment</term><term>Reassortment networks</term><term>Saturation phenomenon</term><term>Sequence alignment</term><term>Slab size</term><term>Small problem sizes</term><term>Supercomputing</term><term>Supercomputing centre</term><term>Target machines</term><term>Total number</term><term>Traps increase</term><term>Virus reassortment algorithm</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract">We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including decreasing the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.</div></front></TEI><istex><corpusName>wiley</corpusName><keywords><teeft><json:string>matterhorn</json:string><json:string>cougar</json:string><json:string>egret</json:string><json:string>bokhari</json:string><json:string>cray</json:string><json:string>proc</json:string><json:string>concurrency</json:string><json:string>copyright</json:string><json:string>john wiley sons</json:string><json:string>reassortment</json:string><json:string>pract</json:string><json:string>computat</json:string><json:string>exper</json:string><json:string>concurrency computat</json:string><json:string>problem size</json:string><json:string>processor</json:string><json:string>algorithm</json:string><json:string>proc matterhorn</json:string><json:string>supercomputing</json:string><json:string>bioinformatics</json:string><json:string>parallelizing</json:string><json:string>memory accesses</json:string><json:string>proc cougar</json:string><json:string>problem sizes</json:string><json:string>large problem sizes</json:string><json:string>total number</json:string><json:string>clock cycles</json:string><json:string>reassortment networks</json:string><json:string>maximum number</json:string><json:string>virus reassortment algorithm</json:string><json:string>small problem sizes</json:string><json:string>main loop</json:string><json:string>better performance</json:string><json:string>saturation phenomenon</json:string><json:string>memory access times</json:string><json:string>memory operations</json:string><json:string>processor cougar</json:string><json:string>ohio state university</json:string><json:string>processors figure</json:string><json:string>processor egret</json:string><json:string>dynamic programming</json:string><json:string>matrix</json:string><json:string>dynamic programming codes</json:string><json:string>matrix multiplication</json:string><json:string>memory access</json:string><json:string>biomedical informatics</json:string><json:string>computational biology</json:string><json:string>target machines</json:string><json:string>memory cycles</json:string><json:string>supercomputing centre</json:string><json:string>sequence alignment</json:string><json:string>traps increase</json:string><json:string>multithreaded supercomputers</json:string><json:string>memory subsystem</json:string><json:string>slab size</json:string></teeft></keywords><author><json:item><name>Shahid H. Bokhari</name><affiliations><json:string>Department of Biomedical Informatics, The Ohio State University, OH, Columbus, USA</json:string><json:string>Correspondence to: Shahid H. Bokhari, Department of Biomedical Informatics, 3190 Graves Hall, 333 W. 10th Avenue Columbus, OH 43210, USA.E‐mail:</json:string><json:string>E-mail: shahid@bmi.osu.edu</json:string></affiliations></json:item><json:item><name>Saniyah S. Bokhari</name><affiliations><json:string>Department of Computer Science and Engineering, The Ohio State University, OH, Columbus, USA</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Cray XMT</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Cray XMT‐2</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>matrix multiply</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>dynamic programming</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>multithreading</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>parallel algorithms</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>parallel computing</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>reassortment</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>sequence alignment</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>shared memory</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>subset‐sum problem</value></json:item></subject><articleId><json:string>CPE2909</json:string></articleId><arkIstex>ark:/67375/WNG-QQKFKKT7-F</arkIstex><language><json:string>eng</json:string></language><originalGenre><json:string>article</json:string></originalGenre><abstract>We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including decreasing the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.</abstract><qualityIndicators><refBibsNative>true</refBibsNative><abstractWordCount>215</abstractWordCount><abstractCharCount>1396</abstractCharCount><keywordCount>11</keywordCount><score>9.58</score><pdfWordCount>5744</pdfWordCount><pdfCharCount>34205</pdfCharCount><pdfVersion>1.4</pdfVersion><pdfPageCount>17</pdfPageCount><pdfPageSize>595.276 x 782.362 pts</pdfPageSize><pdfWordsPerPage>338</pdfWordsPerPage><pdfText>true</pdfText></qualityIndicators><title>A comparison of the Cray XMT and XMT‐2</title><genre><json:string>article</json:string></genre><host><title>Concurrency and Computation: Practice and Experience</title><language><json:string>unknown</json:string></language><doi><json:string>10.1002/(ISSN)1532-0634</json:string></doi><issn><json:string>1532-0626</json:string></issn><eissn><json:string>1532-0634</json:string></eissn><publisherId><json:string>CPE</json:string></publisherId><volume>25</volume><issue>15</issue><pages><first>2123</first><last>2139</last><total>17</total></pages><genre><json:string>journal</json:string></genre><subject><json:item><value>Research Article</value></json:item><json:item><value>Research Articles</value></json:item></subject></host><namedEntities><unitex><date><json:string>2009</json:string><json:string>2012-07-31</json:string></date><geogName></geogName><orgName><json:string>Northwest National Laboratory</json:string><json:string>Sons, Ltd.</json:string><json:string>Swiss National Supercomputing Centre</json:string><json:string>The Ohio State University</json:string><json:string>Sons, Ltd</json:string><json:string>Cray Inc.</json:string><json:string>CSCS</json:string><json:string>Cray Inc</json:string></orgName><orgName_funder></orgName_funder><orgName_provider></orgName_provider><persName><json:string>Thomas Schoenemeyer</json:string><json:string>John Wiley</json:string><json:string>Richard Russell</json:string><json:string>H. Bokhari</json:string><json:string>Michael Peterson</json:string><json:string>David Mizell</json:string><json:string>S. Bokhari</json:string><json:string>John Feo</json:string><json:string>Surfaces</json:string></persName><placeName><json:string>Columbus</json:string><json:string>USA</json:string><json:string>OH</json:string></placeName><ref_url></ref_url><ref_bibl><json:string>[18]</json:string><json:string>[6]</json:string><json:string>[2, 19]</json:string><json:string>[17]</json:string><json:string>[1]</json:string><json:string>Department of Biomedical Informatics, 3190</json:string><json:string>Bokhari et al. [17]</json:string><json:string>[16]</json:string><json:string>[3]</json:string><json:string>Reidy et al. [21]</json:string><json:string>[20]</json:string><json:string>[5, 6]</json:string><json:string>[15]</json:string><json:string>[14]</json:string><json:string>[13]</json:string></ref_bibl><bibl></bibl></unitex></namedEntities><ark><json:string>ark:/67375/WNG-QQKFKKT7-F</json:string></ark><categories><wos><json:string>1 - science</json:string><json:string>2 - computer science, theory & methods</json:string><json:string>2 - computer science, software engineering</json:string></wos><scienceMetrix><json:string>1 - applied sciences</json:string><json:string>2 - information & communication technologies</json:string><json:string>3 - distributed computing</json:string></scienceMetrix><scopus><json:string>1 - Physical Sciences</json:string><json:string>2 - Computer Science</json:string><json:string>3 - Computational Theory and Mathematics</json:string><json:string>1 - Physical Sciences</json:string><json:string>2 - Computer Science</json:string><json:string>3 - Computer Networks and Communications</json:string><json:string>1 - Physical Sciences</json:string><json:string>2 - Computer Science</json:string><json:string>3 - Computer Science Applications</json:string><json:string>1 - Physical Sciences</json:string><json:string>2 - Mathematics</json:string><json:string>3 - Theoretical Computer Science</json:string><json:string>1 - Physical Sciences</json:string><json:string>2 - Computer Science</json:string><json:string>3 - Software</json:string></scopus><inist><json:string>1 - sciences appliquees, technologies et medecines</json:string><json:string>2 - sciences exactes et technologie</json:string><json:string>3 - sciences et techniques communes</json:string><json:string>4 - mathematiques</json:string></inist></categories><publicationDate>2013</publicationDate><copyrightDate>2013</copyrightDate><doi><json:string>10.1002/cpe.2909</json:string></doi><id>047DFC4DBE0E86719879263C10CDBD10A1EF0C9A</id><score>1</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/fulltext.pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/bundle.zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/fulltext.tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main">A comparison of the Cray XMT and XMT‐2</title><title level="a" type="short">CRAY XMT AND XMT‐2</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher ref="https://scientific-publisher.data.istex.fr/ark:/67375/H02-QW5Q88H5-V">Wiley Publishing Ltd</publisher><availability><licence>Copyright © 2012 John Wiley & Sons, Ltd.</licence></availability><date type="published" when="2013-10"></date></publicationStmt><notesStmt><note type="content-type" subtype="article" source="article" scheme="https://content-type.data.istex.fr/ark:/67375/XTP-6N5SZHKN-D">article</note><note type="publication-type" subtype="journal" scheme="https://publication-type.data.istex.fr/ark:/67375/JMC-0GLKJH51-B">journal</note></notesStmt><sourceDesc><biblStruct type="article"><analytic><title level="a" type="main">A comparison of the Cray XMT and XMT‐2</title><title level="a" type="short">CRAY XMT AND XMT‐2</title><author xml:id="author-0000" role="corresp"><persName><forename type="first">Shahid H.</forename><surname>Bokhari</surname></persName><affiliation><orgName type="division">Department of Biomedical Informatics</orgName><orgName type="institution">The Ohio State University</orgName><address><settlement>Columbus</settlement><region>OH</region><country key="US" xml:lang="en">UNITED STATES</country></address></affiliation></author><author xml:id="author-0001"><persName><forename type="first">Saniyah S.</forename><surname>Bokhari</surname></persName><affiliation><orgName type="division">Department of Computer Science and Engineering</orgName><orgName type="institution">The Ohio State University</orgName><address><settlement>Columbus</settlement><region>OH</region><country key="US" xml:lang="en">UNITED STATES</country></address></affiliation></author><idno type="istex">047DFC4DBE0E86719879263C10CDBD10A1EF0C9A</idno><idno type="ark">ark:/67375/WNG-QQKFKKT7-F</idno><idno type="DOI">10.1002/cpe.2909</idno><idno type="unit">CPE2909</idno><idno type="toTypesetVersion">file:CPE.CPE2909.pdf</idno></analytic><monogr><title level="j" type="main">Concurrency and Computation: Practice and Experience</title><title level="j" type="alt">CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE</title><idno type="pISSN">1532-0626</idno><idno type="eISSN">1532-0634</idno><idno type="book-DOI">10.1002/(ISSN)1532-0634</idno><idno type="book-part-DOI">10.1002/cpe.v25.15</idno><idno type="product">CPE</idno><imprint><biblScope unit="vol">25</biblScope><biblScope unit="issue">15</biblScope><biblScope unit="page" from="2123">2123</biblScope><biblScope unit="page" to="2139">2139</biblScope><biblScope unit="page-count">17</biblScope><date type="published" when="2013-10"></date></imprint></monogr></biblStruct></sourceDesc></fileDesc><encodingDesc><schemaRef type="ODD" url="https://xml-schema.delivery.istex.fr/tei-istex.odd"></schemaRef><appInfo><application ident="pub2tei" version="1.0.10" when="2019-12-20"><label>pub2TEI-ISTEX</label><desc>A set of style sheets for converting XML documents encoded in various scientific publisher formats into a common TEI format.
<ref target="http://www.tei-c.org/">We use TEI</ref></desc></application></appInfo></encodingDesc><profileDesc><abstract style="main" xml:id="cpe2909-abs-0001"><head>SUMMARY</head><p xml:id="cpe2909-para-0001">We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including <hi rend="italic">decreasing</hi> the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.</p></abstract><textClass><keywords><term xml:id="cpe2909-kwd-0001">Cray XMT</term><term xml:id="cpe2909-kwd-0002">Cray XMT‐2</term><term xml:id="cpe2909-kwd-0003">matrix multiply</term><term xml:id="cpe2909-kwd-0004">dynamic programming</term><term xml:id="cpe2909-kwd-0005">multithreading</term><term xml:id="cpe2909-kwd-0006">parallel algorithms</term><term xml:id="cpe2909-kwd-0007">parallel computing</term><term xml:id="cpe2909-kwd-0008">reassortment</term><term xml:id="cpe2909-kwd-0009">sequence alignment</term><term xml:id="cpe2909-kwd-0010">shared memory</term><term xml:id="cpe2909-kwd-0011">subset‐sum problem</term></keywords><keywords rend="articleCategory"><term>Research Article</term></keywords><keywords rend="tocHeading1"><term>Research Articles</term></keywords></textClass><langUsage><language ident="en"></language></langUsage></profileDesc><revisionDesc><change when="2019-12-20" who="#istex" xml:id="pub2tei">formatting</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/fulltext.txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Wiley, elements deleted: body"><istex:xmlDeclaration>version="1.0" encoding="UTF-8" standalone="yes"</istex:xmlDeclaration><istex:document><component type="serialArticle" version="2.0" xml:lang="en" xml:id="cpe2909"><header xml:id="cpe2909-hdr-0001">
<publicationMeta level="product">
<doi>10.1002/(ISSN)1532-0634</doi><issn type="print">1532-0626</issn><issn type="electronic">1532-0634</issn><idGroup><id type="product" value="CPE"></id></idGroup><titleGroup><title type="main" sort="CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE">Concurrency and Computation: Practice and Experience</title><title type="short">Concurrency Computat.: Pract. Exper.</title></titleGroup></publicationMeta>
<publicationMeta level="part" position="150"><doi>10.1002/cpe.v25.15</doi><copyright ownership="publisher">Copyright © 2013 John Wiley & Sons, Ltd.</copyright><numberingGroup><numbering type="journalVolume" number="25">25</numbering><numbering type="journalIssue">15</numbering></numberingGroup><coverDate startDate="2013-10">October 2013</coverDate></publicationMeta>
<publicationMeta level="unit" position="10" type="article" status="forIssue"><doi>10.1002/cpe.2909</doi><idGroup><id type="unit" value="CPE2909"></id></idGroup><countGroup><count type="pageTotal" number="17"></count></countGroup><titleGroup><title type="articleCategory">Research Article</title><title type="tocHeading1">Research Articles</title></titleGroup><copyright ownership="publisher">Copyright © 2012 John Wiley & Sons, Ltd.</copyright><eventGroup><event type="manuscriptReceived" date="2012-01-27"></event><event type="manuscriptRevised" date="2012-07-04"></event><event type="manuscriptAccepted" date="2012-07-05"></event><event type="xmlCreated" agent="SPi Global" date="2012-07-31"></event><event type="publishedOnlineEarlyUnpaginated" date="2012-08-09"></event><event type="firstOnline" date="2012-08-09"></event><event type="publishedOnlineFinalForm" date="2013-09-12"></event><event type="xmlConverted" agent="Converter:WILEY_ML3G_TO_WILEY_ML3GV2 version:3.8.8" date="2014-01-16"></event><event type="xmlConverted" agent="Converter:WML3G_To_WML3G version:4.6.4 mode:FullText" date="2015-10-02"></event></eventGroup><numberingGroup><numbering type="pageFirst">2123</numbering><numbering type="pageLast">2139</numbering></numberingGroup><correspondenceTo>
<lineatedText xml:id="cpe2909-lntext-0001"><line>Correspondence to: Shahid H. Bokhari, Department of Biomedical Informatics, 3190 Graves Hall, 333 W. 10th Avenue Columbus, OH 43210, USA.</line><line>E‐mail: <email>shahid@bmi.osu.edu</email></line></lineatedText> </correspondenceTo><objectNameGroup><objectName elementName="appendix">APPENDIX</objectName></objectNameGroup><linkGroup><link type="toTypesetVersion" href="file:CPE.CPE2909.pdf"></link></linkGroup></publicationMeta><contentMeta><titleGroup><title type="main">A comparison of the Cray XMT and XMT‐2</title><title type="shortAuthors">S. H. BOKHARI AND S. S. BOKHARI</title><title type="short">CRAY XMT AND XMT‐2</title></titleGroup><creators><creator xml:id="cpe2909-cr-0001" creatorRole="author" affiliationRef="#cpe2909-aff-0001" corresponding="yes"><personName><givenNames>Shahid H.</givenNames><familyName>Bokhari</familyName></personName></creator><creator xml:id="cpe2909-cr-0002" creatorRole="author" affiliationRef="#cpe2909-aff-0002"><personName><givenNames>Saniyah S.</givenNames><familyName>Bokhari</familyName></personName></creator></creators><affiliationGroup><affiliation xml:id="cpe2909-aff-0001" countryCode="US" type="organization"><orgDiv>Department of Biomedical Informatics</orgDiv><orgName>The Ohio State University</orgName><address><city>Columbus</city><countryPart>OH</countryPart><country>USA</country></address></affiliation><affiliation xml:id="cpe2909-aff-0002" countryCode="US" type="organization"><orgDiv>Department of Computer Science and Engineering</orgDiv><orgName>The Ohio State University</orgName><address><city>Columbus</city><countryPart>OH</countryPart><country>USA</country></address></affiliation></affiliationGroup><keywordGroup type="author"><keyword xml:id="cpe2909-kwd-0001">Cray XMT</keyword><keyword xml:id="cpe2909-kwd-0002">Cray XMT‐2</keyword><keyword xml:id="cpe2909-kwd-0003">matrix multiply</keyword><keyword xml:id="cpe2909-kwd-0004">dynamic programming</keyword><keyword xml:id="cpe2909-kwd-0005">multithreading</keyword><keyword xml:id="cpe2909-kwd-0006">parallel algorithms</keyword><keyword xml:id="cpe2909-kwd-0007">parallel computing</keyword><keyword xml:id="cpe2909-kwd-0008">reassortment</keyword><keyword xml:id="cpe2909-kwd-0009">sequence alignment</keyword><keyword xml:id="cpe2909-kwd-0010">shared memory</keyword><keyword xml:id="cpe2909-kwd-0011">subset‐sum problem</keyword></keywordGroup><abstractGroup><abstract type="main" xml:id="cpe2909-abs-0001"><title type="main">SUMMARY</title><p xml:id="cpe2909-para-0001">We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including <i>decreasing</i> the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.</p></abstract></abstractGroup></contentMeta></header></component></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>A comparison of the Cray XMT and XMT‐2</title></titleInfo><titleInfo type="abbreviated" lang="en"><title>CRAY XMT AND XMT‐2</title></titleInfo><titleInfo type="alternative" contentType="CDATA" lang="en"><title>A comparison of the Cray XMT and XMT‐2</title></titleInfo><name type="personal"><namePart type="given">Shahid H.</namePart><namePart type="family">Bokhari</namePart><affiliation>Department of Biomedical Informatics, The Ohio State University, OH, Columbus, USA</affiliation><affiliation>Correspondence to: Shahid H. Bokhari, Department of Biomedical Informatics, 3190 Graves Hall, 333 W. 10th Avenue Columbus, OH 43210, USA.E‐mail:</affiliation><affiliation>E-mail: shahid@bmi.osu.edu</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Saniyah S.</namePart><namePart type="family">Bokhari</namePart><affiliation>Department of Computer Science and Engineering, The Ohio State University, OH, Columbus, USA</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="article" displayLabel="article" authority="ISTEX" authorityURI="https://content-type.data.istex.fr" valueURI="https://content-type.data.istex.fr/ark:/67375/XTP-6N5SZHKN-D">article</genre><originInfo><publisher>Blackwell Publishing Ltd</publisher><dateIssued encoding="w3cdtf">2013-10</dateIssued><dateCreated encoding="w3cdtf">2012-07-31</dateCreated><dateCaptured encoding="w3cdtf">2012-01-27</dateCaptured><dateValid encoding="w3cdtf">2012-07-05</dateValid><copyrightDate encoding="w3cdtf">2013</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><abstract>We explore the comparative performance of the Cray XMT and XMT‐2 massively multithreaded supercomputers. We use benchmarks to evaluate memory accesses for various types of loops. We also compare the performance of these machines on matrix multiply and on three previously implemented dynamic programming algorithms. It is shown that the relative performance of these machines is dependent on the size (number of processors) of the configuration, as well as the size of the problem being evaluated. In particular, small configurations of the original XMT can sometimes show slightly better performance than larger configurations of the XMT‐2, for the same problem size. We note that, under heavy memory load, performance of loops can saturate well before the maximum number of processors available. This suggests that it may not always be useful to use the maximum number of processors for a specific run. We also show that manual restructuring of nested loops, including decreasing the parallelism, can result in major improvements in performance. The results in this paper indicate that careful exploration of the space of problem sizes, number of processors used, and choices of loop parallelization can yield substantial improvements in performance. These improvements can be very significant for production codes that run for extended periods of time. Copyright © 2012 John Wiley & Sons, Ltd.</abstract><subject><genre>keywords</genre><topic>Cray XMT</topic><topic>Cray XMT‐2</topic><topic>matrix multiply</topic><topic>dynamic programming</topic><topic>multithreading</topic><topic>parallel algorithms</topic><topic>parallel computing</topic><topic>reassortment</topic><topic>sequence alignment</topic><topic>shared memory</topic><topic>subset‐sum problem</topic></subject><relatedItem type="host"><titleInfo><title>Concurrency and Computation: Practice and Experience</title></titleInfo><titleInfo type="abbreviated"><title>Concurrency Computat.: Pract. Exper.</title></titleInfo><genre type="journal" authority="ISTEX" authorityURI="https://publication-type.data.istex.fr" valueURI="https://publication-type.data.istex.fr/ark:/67375/JMC-0GLKJH51-B">journal</genre><subject><genre>article-category</genre><topic>Research Article</topic><topic>Research Articles</topic></subject><identifier type="ISSN">1532-0626</identifier><identifier type="eISSN">1532-0634</identifier><identifier type="DOI">10.1002/(ISSN)1532-0634</identifier><identifier type="PublisherID">CPE</identifier><part><date>2013</date><detail type="volume"><caption>vol.</caption><number>25</number></detail><detail type="issue"><caption>no.</caption><number>15</number></detail><extent unit="pages"><start>2123</start><end>2139</end><total>17</total></extent></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0001"><titleInfo><title>Exploiting heterogeneous parallelism on a multithreaded multiprocessor</title></titleInfo><name type="personal"><namePart type="given">G</namePart><namePart type="family">Alverson</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">R</namePart><namePart type="family">Alverson</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">D</namePart><namePart type="family">Callahan</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Koblenz</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">A</namePart><namePart type="family">Porterfield</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Smith</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>1992</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0002"><titleInfo><title>The Tera computer system</title></titleInfo><name type="personal"><namePart type="given">R</namePart><namePart type="family">Alverson</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">D</namePart><namePart type="family">Callahan</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">D</namePart><namePart type="family">Cummings</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Koblenz</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">A</namePart><namePart type="family">Porterfield</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Smith</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>1990</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0003"><titleInfo><title>Multi‐processor performance on the Tera MTA</title></titleInfo><name type="personal"><namePart type="given">A</namePart><namePart type="family">Snavely</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">L</namePart><namePart type="family">Carter</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Boisseau</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">A</namePart><namePart type="family">Majumdar</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">KS</namePart><namePart type="family">Gatlin</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">N</namePart><namePart type="family">Mitchell</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Feo</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Koblenz</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>1998</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0004"><titleInfo><title>Early experience with scientific programs on the Cray MTA‐2</title></titleInfo><name type="personal"><namePart type="given">W</namePart><namePart type="family">Anderson</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">P</namePart><namePart type="family">Briggs</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">CS</namePart><namePart type="family">Hellberg</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DW</namePart><namePart type="family">Hess</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">A</namePart><namePart type="family">Khokhlov</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">M</namePart><namePart type="family">Lanzagorta</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">R</namePart><namePart type="family">Rosenberg</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>book-chapter</genre><relatedItem type="host"><titleInfo><title>Sc ’03: Proceedings of the 2003 ACM/IEEE Conference on Supercomputing</title></titleInfo><originInfo><publisher>IEEE Computer Society</publisher><place><placeTerm type="text">Phoenix</placeTerm></place></originInfo><part><date>2003</date><extent unit="pages"><start>46</start></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0005"><titleInfo><title>Sequence alignment on the Cray MTA‐2</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">JR</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari SH, Sauer JR. Sequence alignment on the Cray MTA‐2. Concurrency and Computation 2004; 16:823–839.</note><part><date>2004</date><detail type="volume"><caption>vol.</caption><number>16</number></detail><extent unit="pages"><start>823</start><end>839</end></extent></part><relatedItem type="host"><titleInfo><title>Concurrency and Computation</title></titleInfo><part><date>2004</date><detail type="volume"><caption>vol.</caption><number>16</number></detail><extent unit="pages"><start>823</start><end>839</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0006"><titleInfo><title>Exploring the performance of massively multithreaded architectures</title></titleInfo><name type="personal"><namePart type="given">S</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Saltz</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari S, Saltz J. Exploring the performance of massively multithreaded architectures. Concurrency and Computation: Practice and Experience 2010; 22(5):588–616.</note><part><date>2010</date><detail type="volume"><caption>vol.</caption><number>22</number></detail><detail type="issue"><caption>no.</caption><number>5</number></detail><extent unit="pages"><start>588</start><end>616</end></extent></part><relatedItem type="host"><titleInfo><title>Concurrency and Computation: Practice and Experience</title></titleInfo><part><date>2010</date><detail type="volume"><caption>vol.</caption><number>22</number></detail><detail type="issue"><caption>no.</caption><number>5</number></detail><extent unit="pages"><start>588</start><end>616</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0007"><titleInfo><title>Exploring the performance of massively multithreaded supercomputers</title></titleInfo><name type="personal"><namePart type="given">S</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Saltz</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2009</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0008"><titleInfo><title>Parallel algorithms for bioinformatics</title></titleInfo><name type="personal"><namePart type="given">S</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>book-chapter</genre><relatedItem type="host"><titleInfo><title>Parallel Computing for Bioinformatics</title></titleInfo><originInfo><publisher>Wiley</publisher><place><placeTerm type="text">Hoboken, New Jersey</placeTerm></place></originInfo><part><date>2006</date><extent unit="pages"><start>509</start><end>529</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0009"><titleInfo><title>Sequence alignment on the Cray MTA‐2</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">JR</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2003</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0010"><titleInfo><title>A parallel graph decomposition algorithm for DNA sequencing with nanopores</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">JR</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari SH, Sauer JR. A parallel graph decomposition algorithm for DNA sequencing with nanopores. Bioinformatics 2005; 21(7):889–896.</note><part><date>2005</date><detail type="volume"><caption>vol.</caption><number>21</number></detail><detail type="issue"><caption>no.</caption><number>7</number></detail><extent unit="pages"><start>889</start><end>896</end></extent></part><relatedItem type="host"><titleInfo><title>Bioinformatics</title></titleInfo><part><date>2005</date><detail type="volume"><caption>vol.</caption><number>21</number></detail><detail type="issue"><caption>no.</caption><number>7</number></detail><extent unit="pages"><start>889</start><end>896</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0011"><titleInfo><title>Parallelizing a DNA simulation code for the Cray MTA‐2</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">MA</namePart><namePart type="family">Glaser</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">HF</namePart><namePart type="family">Jordan</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Y</namePart><namePart type="family">Lansac</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">JR</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B</namePart><namePart type="family">Van Zeghbroeck</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2002</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0012"><titleInfo><title>Parallelizing a DNA simulation code for the Cray MTA‐2</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">MA</namePart><namePart type="family">Glaser</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">HF</namePart><namePart type="family">Jordan</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Y</namePart><namePart type="family">Lansac</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">JR</namePart><namePart type="family">Sauer</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">BV</namePart><namePart type="family">Zeghbroeck</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2002</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0013"><titleInfo><title>Garey MR, Johnson DS. Computers and Intractability, W. H. Freeman: New York, 1979.</title></titleInfo><note type="citation/reference">Garey MR, Johnson DS. Computers and Intractability, W. H. Freeman: New York, 1979.</note><name type="personal"><namePart type="given">MR</namePart><namePart type="family">Garey</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DS</namePart><namePart type="family">Johnson</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>book</genre><originInfo><publisher>W. H. Freeman</publisher><place><placeTerm type="text">New York</placeTerm></place></originInfo><part><date>1979</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0014"><titleInfo><title>Parallel solution of the subset‐sum problem: An empirical study</title></titleInfo><name type="personal"><namePart type="given">SS</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2011</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0015"><titleInfo><title>Parallel solution of the subset‐sum problem: An empirical study</title></titleInfo><name type="personal"><namePart type="given">SS</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari SS. Parallel solution of the subset‐sum problem: An empirical study. Concurrency and Computation: Practice and Experience 2012. DOI: 10.1002/cpe.2800. Article first published online: 2 Feb 2012.</note><part><date>2012</date></part><relatedItem type="host"><titleInfo><title>Concurrency and Computation: Practice and Experience</title></titleInfo><part><date>2012</date></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0016"><titleInfo><title>Reassortment networks for investigating the evolution of segmented viruses</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DA</namePart><namePart type="family">Janies</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari SH, Janies DA. Reassortment networks for investigating the evolution of segmented viruses. IEEE/ACM Transactions on Computational Biology and Bioinformatics 2010; 7:288–298.</note><part><date>2010</date><detail type="volume"><caption>vol.</caption><number>7</number></detail><extent unit="pages"><start>288</start><end>298</end></extent></part><relatedItem type="host"><titleInfo><title>IEEE/ACM Transactions on Computational Biology and Bioinformatics</title></titleInfo><part><date>2010</date><detail type="volume"><caption>vol.</caption><number>7</number></detail><extent unit="pages"><start>288</start><end>298</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0017"><titleInfo><title>Reassortment networks and the evolution of pandemic H1N1 swine‐origin influenza</title></titleInfo><name type="personal"><namePart type="given">SH</namePart><namePart type="family">Bokhari</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">LW</namePart><namePart type="family">Pomeroy</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DA</namePart><namePart type="family">Janies</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>journal-article</genre><note type="citation/reference">Bokhari SH, Pomeroy LW, Janies DA. Reassortment networks and the evolution of pandemic H1N1 swine‐origin influenza. IEEE/ACM Transactions on Computational Biology and Bioinformatics 2012; 9:214–227.</note><part><date>2012</date><detail type="volume"><caption>vol.</caption><number>9</number></detail><extent unit="pages"><start>214</start><end>227</end></extent></part><relatedItem type="host"><titleInfo><title>IEEE/ACM Transactions on Computational Biology and Bioinformatics</title></titleInfo><part><date>2012</date><detail type="volume"><caption>vol.</caption><number>9</number></detail><extent unit="pages"><start>214</start><end>227</end></extent></part></relatedItem></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0018"><titleInfo><title>Cray XMT performance tools user's guide</title></titleInfo><name type="corporate"><namePart>Cray Inc</namePart></name><genre>other</genre><part><date>2011</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0019"><titleInfo><title>Early experiences with large‐scale Cray XMT systems</title></titleInfo><name type="personal"><namePart type="given">D</namePart><namePart type="family">Mizell</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">K</namePart><namePart type="family">Maschhoff</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2009</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0020"><titleInfo><title>Limiting loop parallelism in Cray XMT applications</title></titleInfo><name type="corporate"><namePart>Cray Inc</namePart></name><genre>other</genre><part><date>2010</date></part></relatedItem><relatedItem type="references" displayLabel="cpe2909-cit-0021"><titleInfo><title>Modeling memory constrained and massively multithreaded performance</title></titleInfo><name type="personal"><namePart type="given">J</namePart><namePart type="family">Reidy</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DA</namePart><namePart type="family">Bader</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">D</namePart><namePart type="family">Ediger</namePart><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">DW</namePart><namePart type="family">Mizell</namePart><role><roleTerm type="text">author</roleTerm></role></name><genre>other</genre><part><date>2011</date></part></relatedItem><identifier type="istex">047DFC4DBE0E86719879263C10CDBD10A1EF0C9A</identifier><identifier type="ark">ark:/67375/WNG-QQKFKKT7-F</identifier><identifier type="DOI">10.1002/cpe.2909</identifier><identifier type="ArticleID">CPE2909</identifier><accessCondition type="use and reproduction" contentType="copyright">Copyright © 2013 John Wiley & Sons, Ltd.Copyright © 2012 John Wiley & Sons, Ltd.</accessCondition><recordInfo><recordContentSource authority="ISTEX" authorityURI="https://loaded-corpus.data.istex.fr" valueURI="https://loaded-corpus.data.istex.fr/ark:/67375/XBH-L0C46X92-X">wiley</recordContentSource><recordOrigin>Converted from (version ) to MODS version 3.6.</recordOrigin><recordCreationDate encoding="w3cdtf">2019-11-14</recordCreationDate></recordInfo></mods><json:item><extension>json</extension><original>false</original><mimetype>application/json</mimetype><uri>https://api.istex.fr/ark:/67375/WNG-QQKFKKT7-F/record.json</uri></json:item></metadata><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/PandemieGrippaleV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001D58 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 001D58 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Sante
|area= PandemieGrippaleV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:047DFC4DBE0E86719879263C10CDBD10A1EF0C9A
|texte= A comparison of the Cray XMT and XMT‐2
}}
| This area was generated with Dilib version V0.6.34. |  |