Goals guiding design: PVM and MPI
PVM and MPI, two systems for programming clusters, are often compared. The comparisons usually start with the unspoken assumption that PVM and MPI represent different solutions to the same problem. In this paper we show that, in fact, the two systems often are solving different problems. In cases wh...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 265 |
|---|---|
| container_issue | |
| container_start_page | 257 |
| container_title | |
| container_volume | |
| creator | Gropp, W. Lusk, E. |
| description | PVM and MPI, two systems for programming clusters, are often compared. The comparisons usually start with the unspoken assumption that PVM and MPI represent different solutions to the same problem. In this paper we show that, in fact, the two systems often are solving different problems. In cases where the problems do match but the solutions chosen by PVM and MPI are different, we explain the reasons for the differences. Usually such differences can be traced to explicit differences in the goals of the two systems, their origins, or the relationship between their specifications and their implementations. For example, we show that the requirement for portability and performance across many platforms caused MPI to choose approaches different from those made by PVM, which is able to exploit the similarities of network-connected systems. |
| doi_str_mv | 10.1109/CLUSTR.2002.1137754 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1137754</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1137754</ieee_id><sourcerecordid>1137754</sourcerecordid><originalsourceid>FETCH-LOGICAL-c296t-183b34d8216cfaa617693afa578a375c2dbabe78f0711cd750250f27acf9eb8b3</originalsourceid><addsrcrecordid>eNotj89KAzEYxAMiKHWfoJf0AbZ-SZp8WW-yaC1sadHW65K_a0R3pVkPvr0L7VwGhh8zDCFzBkvGoLqvm-Pb4XXJAfgUCES5uiJFhRpQVZKDUnhDipw_YZKUGgTcksV6MF-Zdr_Jp76jPuTU9Q90_76lpvd0u9_ckes4IaG4-Iwcn58O9UvZ7Nab-rEpHa_UWDItrFh5zZly0RjFplFhopGojUDpuLfGBtQRkDHnUQKXEDkaF6tgtRUzsjj3DnlMbXZpDO7DDX0f3NhqYErCxMzPTAohtD-n9G1Of-3lrPgHHOJH0A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Goals guiding design: PVM and MPI</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Gropp, W. ; Lusk, E.</creator><creatorcontrib>Gropp, W. ; Lusk, E. ; Argonne National Lab., IL (US)</creatorcontrib><description>PVM and MPI, two systems for programming clusters, are often compared. The comparisons usually start with the unspoken assumption that PVM and MPI represent different solutions to the same problem. In this paper we show that, in fact, the two systems often are solving different problems. In cases where the problems do match but the solutions chosen by PVM and MPI are different, we explain the reasons for the differences. Usually such differences can be traced to explicit differences in the goals of the two systems, their origins, or the relationship between their specifications and their implementations. For example, we show that the requirement for portability and performance across many platforms caused MPI to choose approaches different from those made by PVM, which is able to exploit the similarities of network-connected systems.</description><identifier>ISBN: 9780769520667</identifier><identifier>ISBN: 0769520669</identifier><identifier>ISBN: 0769517455</identifier><identifier>ISBN: 9780769517452</identifier><identifier>DOI: 10.1109/CLUSTR.2002.1137754</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>COMPUTER NETWORKS ; Computer science ; DATA TRANSMISSION ; DESIGN ; GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE ; Laboratories ; Libraries ; Mathematical programming ; Mathematics ; Parallel algorithms ; Parallel processing ; PROGRAMMING ; SPECIFICATIONS ; Supercomputers ; Writing</subject><ispartof>Proceedings. IEEE International Conference on Cluster Computing, 2002, p.257-265</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c296t-183b34d8216cfaa617693afa578a375c2dbabe78f0711cd750250f27acf9eb8b3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1137754$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,309,310,780,784,789,790,885,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1137754$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.osti.gov/servlets/purl/801650$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Gropp, W.</creatorcontrib><creatorcontrib>Lusk, E.</creatorcontrib><creatorcontrib>Argonne National Lab., IL (US)</creatorcontrib><title>Goals guiding design: PVM and MPI</title><title>Proceedings. IEEE International Conference on Cluster Computing</title><addtitle>CLUSTR</addtitle><description>PVM and MPI, two systems for programming clusters, are often compared. The comparisons usually start with the unspoken assumption that PVM and MPI represent different solutions to the same problem. In this paper we show that, in fact, the two systems often are solving different problems. In cases where the problems do match but the solutions chosen by PVM and MPI are different, we explain the reasons for the differences. Usually such differences can be traced to explicit differences in the goals of the two systems, their origins, or the relationship between their specifications and their implementations. For example, we show that the requirement for portability and performance across many platforms caused MPI to choose approaches different from those made by PVM, which is able to exploit the similarities of network-connected systems.</description><subject>COMPUTER NETWORKS</subject><subject>Computer science</subject><subject>DATA TRANSMISSION</subject><subject>DESIGN</subject><subject>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</subject><subject>Laboratories</subject><subject>Libraries</subject><subject>Mathematical programming</subject><subject>Mathematics</subject><subject>Parallel algorithms</subject><subject>Parallel processing</subject><subject>PROGRAMMING</subject><subject>SPECIFICATIONS</subject><subject>Supercomputers</subject><subject>Writing</subject><isbn>9780769520667</isbn><isbn>0769520669</isbn><isbn>0769517455</isbn><isbn>9780769517452</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2002</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj89KAzEYxAMiKHWfoJf0AbZ-SZp8WW-yaC1sadHW65K_a0R3pVkPvr0L7VwGhh8zDCFzBkvGoLqvm-Pb4XXJAfgUCES5uiJFhRpQVZKDUnhDipw_YZKUGgTcksV6MF-Zdr_Jp76jPuTU9Q90_76lpvd0u9_ckes4IaG4-Iwcn58O9UvZ7Nab-rEpHa_UWDItrFh5zZly0RjFplFhopGojUDpuLfGBtQRkDHnUQKXEDkaF6tgtRUzsjj3DnlMbXZpDO7DDX0f3NhqYErCxMzPTAohtD-n9G1Of-3lrPgHHOJH0A</recordid><startdate>2002</startdate><enddate>2002</enddate><creator>Gropp, W.</creator><creator>Lusk, E.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>OIOZB</scope><scope>OTOTI</scope></search><sort><creationdate>2002</creationdate><title>Goals guiding design: PVM and MPI</title><author>Gropp, W. ; Lusk, E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c296t-183b34d8216cfaa617693afa578a375c2dbabe78f0711cd750250f27acf9eb8b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2002</creationdate><topic>COMPUTER NETWORKS</topic><topic>Computer science</topic><topic>DATA TRANSMISSION</topic><topic>DESIGN</topic><topic>GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE</topic><topic>Laboratories</topic><topic>Libraries</topic><topic>Mathematical programming</topic><topic>Mathematics</topic><topic>Parallel algorithms</topic><topic>Parallel processing</topic><topic>PROGRAMMING</topic><topic>SPECIFICATIONS</topic><topic>Supercomputers</topic><topic>Writing</topic><toplevel>online_resources</toplevel><creatorcontrib>Gropp, W.</creatorcontrib><creatorcontrib>Lusk, E.</creatorcontrib><creatorcontrib>Argonne National Lab., IL (US)</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>OSTI.GOV - Hybrid</collection><collection>OSTI.GOV</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gropp, W.</au><au>Lusk, E.</au><aucorp>Argonne National Lab., IL (US)</aucorp><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Goals guiding design: PVM and MPI</atitle><btitle>Proceedings. IEEE International Conference on Cluster Computing</btitle><stitle>CLUSTR</stitle><date>2002</date><risdate>2002</risdate><spage>257</spage><epage>265</epage><pages>257-265</pages><isbn>9780769520667</isbn><isbn>0769520669</isbn><isbn>0769517455</isbn><isbn>9780769517452</isbn><abstract>PVM and MPI, two systems for programming clusters, are often compared. The comparisons usually start with the unspoken assumption that PVM and MPI represent different solutions to the same problem. In this paper we show that, in fact, the two systems often are solving different problems. In cases where the problems do match but the solutions chosen by PVM and MPI are different, we explain the reasons for the differences. Usually such differences can be traced to explicit differences in the goals of the two systems, their origins, or the relationship between their specifications and their implementations. For example, we show that the requirement for portability and performance across many platforms caused MPI to choose approaches different from those made by PVM, which is able to exploit the similarities of network-connected systems.</abstract><cop>United States</cop><pub>IEEE</pub><doi>10.1109/CLUSTR.2002.1137754</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9780769520667 |
| ispartof | Proceedings. IEEE International Conference on Cluster Computing, 2002, p.257-265 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_1137754 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | COMPUTER NETWORKS Computer science DATA TRANSMISSION DESIGN GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE Laboratories Libraries Mathematical programming Mathematics Parallel algorithms Parallel processing PROGRAMMING SPECIFICATIONS Supercomputers Writing |
| title | Goals guiding design: PVM and MPI |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T05%3A06%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Goals%20guiding%20design:%20PVM%20and%20MPI&rft.btitle=Proceedings.%20IEEE%20International%20Conference%20on%20Cluster%20Computing&rft.au=Gropp,%20W.&rft.aucorp=Argonne%20National%20Lab.,%20IL%20(US)&rft.date=2002&rft.spage=257&rft.epage=265&rft.pages=257-265&rft.isbn=9780769520667&rft.isbn_list=0769520669&rft.isbn_list=0769517455&rft.isbn_list=9780769517452&rft_id=info:doi/10.1109/CLUSTR.2002.1137754&rft_dat=%3Cieee_6IE%3E1137754%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1137754&rfr_iscdi=true |