Performance evaluation of some MPI implementations on workstation clusters

The Message Passing Interface (MPI) has already become a standard of the communication library for distributed-memory computing systems. Since the release of the new versions of MPI specification, several MPI implementations have been made publicly available. Different implementations employ differe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Fourth International Conference/Exhibition on High-Performance Computing in the Asia-Pacific Region, Beijing, China, May 14-17, 2000: Proceedings Ročník 1; s. 392 - 394 vol.1
Hlavní autoři: Zhixin Ba, Haichang Zhou, Huai Zhang, Zhenxiao Yang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 2000
Témata:
Communication standards
Computer interfaces
Distributed computing
Environmental economics
Guidelines
Hardware
High performance computing
Libraries
Message passing
Workstations
ISBN:9780769505909, 0769505892, 0769505902
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The Message Passing Interface (MPI) has already become a standard of the communication library for distributed-memory computing systems. Since the release of the new versions of MPI specification, several MPI implementations have been made publicly available. Different implementations employ different approaches. It is critical to selecting an appropriate MPI implementation for message passing based applications, because performance of communication is extremely crucial to these applications. Our study is intended to provide a guideline on how to submit a task and how to perform such a task, economically and effectively, on workstation clusters in high performance computing. We investigate several MPI aspects including its implementations, supporting hardware environment and derived datatype which affect the communication performance. In the end, our results point out the strength and weakness of different implementations on our experimental system.
AbstractList The Message Passing Interface (MPI) has already become a standard of the communication library for distributed-memory computing systems. Since the release of the new versions of MPI specification, several MPI implementations have been made publicly available. Different implementations employ different approaches. It is critical to selecting an appropriate MPI implementation for message passing based applications, because performance of communication is extremely crucial to these applications. Our study is intended to provide a guideline on how to submit a task and how to perform such a task, economically and effectively, on workstation clusters in high performance computing. We investigate several MPI aspects including its implementations, supporting hardware environment and derived datatype which affect the communication performance. In the end, our results point out the strength and weakness of different implementations on our experimental system.
Author Zhixin Ba
Zhenxiao Yang
Haichang Zhou
Huai Zhang
Author_xml – sequence: 1
  surname: Zhixin Ba
  fullname: Zhixin Ba
  organization: High Performance Comput. Center, Tsinghua Univ., Beijing, China
– sequence: 2
  surname: Haichang Zhou
  fullname: Haichang Zhou
– sequence: 3
  surname: Huai Zhang
  fullname: Huai Zhang
– sequence: 4
  surname: Zhenxiao Yang
  fullname: Zhenxiao Yang
BookMark eNotz0tLw0AUBeABFdSateBq_kDinUfmsZSgtlIxi-7LTHIHonmUmVTx31saV4fDBwfOLbkcpxEJuWdQMAb2cV1XBQeAwkhVGnlBMqsNaGVLKC3Ya5Kl9HlyppXiYG_IW40xTHFwY4MUv11_dHM3jXQKNE0D0vd6Q7vh0OOA43ymRE_8M8WvtHTa9Mc0Y0x35Cq4PmH2nyuye3neVet8-_G6qZ62eWfsnHMRvNLcMy8F1xwYa00rjJfoNYMgmyAReNtqbRshlHZaeh1UK8uGyZJzsSIPy2yHiPtD7AYXf_fLX_EHG4BNHQ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/HPC.2000.846584
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEL
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EndPage 394 vol.1
ExternalDocumentID 846584
GroupedDBID 6IE
6IK
6IL
AAJGR
AAVQY
AAWTH
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
OCL
RIE
RIL
ID FETCH-LOGICAL-i89t-23fb672b1b43272011d8d38b4eb710f4cf4e02dd779c3367a74b7f6d45c145223
IEDL.DBID RIE
ISBN 9780769505909
0769505892
0769505902
IngestDate Tue Aug 26 17:55:53 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i89t-23fb672b1b43272011d8d38b4eb710f4cf4e02dd779c3367a74b7f6d45c145223
ParticipantIDs ieee_primary_846584
PublicationCentury 2000
PublicationDate 20000000
PublicationDateYYYYMMDD 2000-01-01
PublicationDate_xml – year: 2000
  text: 20000000
PublicationDecade 2000
PublicationTitle The Fourth International Conference/Exhibition on High-Performance Computing in the Asia-Pacific Region, Beijing, China, May 14-17, 2000: Proceedings
PublicationTitleAbbrev HPC
PublicationYear 2000
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001766209
Score 1.2803351
Snippet The Message Passing Interface (MPI) has already become a standard of the communication library for distributed-memory computing systems. Since the release of...
SourceID ieee
SourceType Publisher
StartPage 392
SubjectTerms Communication standards
Computer interfaces
Distributed computing
Environmental economics
Guidelines
Hardware
High performance computing
Libraries
Message passing
Workstations
Title Performance evaluation of some MPI implementations on workstation clusters
URI https://ieeexplore.ieee.org/document/846584
Volume 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA06PHiazom_ycFrtzTJ8jXn4Ziio4chu438hIFbZd38-23SziJ48davDaGkCS_98r33EHpURBDDvKp2bkokXKY2yawNJgJAnPKK0uix9P4Ks1m2WMi80dmOXBjnXCw-c4NwGc_ybWH2IVU2rLCywstjdAwgaqpWm04BISiR9Y-5HAWzPNoGktBGbOcQy0bmJyVyOM3HkbEyqPv_5bMSYWbS_dcLnqF-S9fD-Q8QnaMjt-mh7sGvATfL9wK95C1LALcy37jwuCzWDr_lz3i1PhSUxwmJq8ehdKusY2w-9kFZoeyj-eRpPp4mjZdCssrkLqHMawFUp5qzcPKapjazLNPc6WqL4bnx3BFqLYA0jAlQwDV4YfnIpEFznV2izqbYuCuEIdUKMu4AWMYZI9rFttzygH2eXaNeGJjlZ62WsazH5ObPu7fotKa2h5TGHerstnt3j07M125Vbh_iF_4G0oChMA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwGP2iaKInFDH-tgevg64t7XomElAgOxDDjaxrm5AIIwz8-1274WLixdu-dcmWtstrv37vPYCXBHOcUpsUK7eEB0yGOoi0diYCApvEJoR4j6WPsZhOo_lcxpXOtufCGGN88ZnpuEt_lq-zdO9SZd0CKwu8PIaTHiu2PSVZq06oCM4JluXWXPacXR6pA4lJJbdziGUl9BNi2R3Gfc9Z6ZRv-OW04oFm0PzXJ15AuybsofgHii7hyKxb0Dw4NqDqB76Ct7jmCaBa6BtlFuXZyqBJPELL1aGk3E9JVDS74q28jFH6uXfaCnkbZoPXWX8YVG4KwTKSu4BQq7ggKlSMurPXMNSRppFiRhWLDMtSywwmWgshU0q5SARTwnLNemnoVNfpNTTW2drcABKhSkTEjBA0YpRiZfyzTDOHfpbeQst1zGJT6mUsyj65-_PuM5wNZ5PxYjyavt_DeUl0dwmOB2jstnvzCKfp126Zb5_8aH8Dapmkdw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=The+Fourth+International+Conference%2FExhibition+on+High-Performance+Computing+in+the+Asia-Pacific+Region%2C+Beijing%2C+China%2C+May+14-17%2C+2000%3A+Proceedings&rft.atitle=Performance+evaluation+of+some+MPI+implementations+on+workstation+clusters&rft.au=Zhixin+Ba&rft.au=Haichang+Zhou&rft.au=Huai+Zhang&rft.au=Zhenxiao+Yang&rft.date=2000-01-01&rft.pub=IEEE&rft.isbn=9780769505909&rft.volume=1&rft.spage=392&rft.epage=394+vol.1&rft_id=info:doi/10.1109%2FHPC.2000.846584&rft.externalDocID=846584
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780769505909/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780769505909/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9780769505909/sc.gif&client=summon&freeimage=true