Techniques for dynamically assigning jobs to processors in a cluster based on processor workload

A technique for operating a high performance computing (HPC) cluster includes monitoring workloads of multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more threads assigned to one or more of the...

Full description

Saved in:
Bibliographic Details
Main Authors Arimilli, Lakshminarayana Baba, Arimilli, Ravi Kumar, Basso, Claude, Calvignac, Jean L
Format Patent
LanguageEnglish
Published 07.08.2012
Online AccessGet full text

Cover

Abstract A technique for operating a high performance computing (HPC) cluster includes monitoring workloads of multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more threads assigned to one or more of the multiple processors are moved to a different one of the multiple processors based on the workloads of the multiple processors.
AbstractList A technique for operating a high performance computing (HPC) cluster includes monitoring workloads of multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more threads assigned to one or more of the multiple processors are moved to a different one of the multiple processors based on the workloads of the multiple processors.
Author Arimilli, Lakshminarayana Baba
Calvignac, Jean L
Arimilli, Ravi Kumar
Basso, Claude
Author_xml – sequence: 1
  givenname: Lakshminarayana Baba
  surname: Arimilli
  fullname: Arimilli, Lakshminarayana Baba
– sequence: 2
  givenname: Ravi Kumar
  surname: Arimilli
  fullname: Arimilli, Ravi Kumar
– sequence: 3
  givenname: Claude
  surname: Basso
  fullname: Basso, Claude
– sequence: 4
  givenname: Jean L
  surname: Calvignac
  fullname: Calvignac, Jean L
BookMark eNqNyjsKAjEQANAUWvi7w1xAkF0FrUXxANvrbDIbo3FmzSTI3l4EwdbqNW9qRixME3NpyF45PAspdJLADYyPYDHGAVA1eA7s4SatQhbok1hSlaQQGBBsLJopQYtKDoR_AV6S7lHQzc24w6i0-DozcDw0-9OyaI-ZOOvZJ_yw2lb1blOt6z_KGw2fQIw
ContentType Patent
CorporateAuthor International Business Machines Corporation
CorporateAuthor_xml – name: International Business Machines Corporation
DBID EFH
DatabaseName USPTO Issued Patents
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EFH
  name: USPTO Issued Patents
  url: http://www.uspto.gov/patft/index.html
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
ExternalDocumentID 08239524
GroupedDBID EFH
ID FETCH-uspatents_grants_082395243
IEDL.DBID EFH
IngestDate Sun Mar 05 22:34:56 EST 2023
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-uspatents_grants_082395243
OpenAccessLink https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8239524
ParticipantIDs uspatents_grants_08239524
PatentNumber 8239524
PublicationCentury 2000
PublicationDate 20120807
PublicationDateYYYYMMDD 2012-08-07
PublicationDate_xml – month: 08
  year: 2012
  text: 20120807
  day: 07
PublicationDecade 2010
PublicationYear 2012
References Johnsen et al. (2006/0002385) 20060100
Arimilli et al. (2010/0153541) 20100600
Gee et al. (2008/0016374) 20080100
Newcombe et al. (7290040) 20071000
Schmollinger et al., Designing Parallel Algorithms for Hierarchical SMP Clusters, International Journal of Foundations of Computer Science, AN-7724447, vol. 14, No. 1, p. 59-78, Feb. 2003, World Scientific.
Kogge et al. (2007/0198785) 20070800
Chew et al. (2009/0187915) 20090700
Kumar et al., Single-ISA Heterogenous Multi-Core Architectures for Multithreaded Workload Performance, Proceedings of the 31st Annual International Symposium on Computer Architecture, IEEE 2004.
Hankinson et al. (6799202) 20040900
Emmot (2005/0027880) 20050200
Jinhui et al., A Co-allocation Strategy for Jobs in Multiple HPC Clusters, Proceedings of the 19th International Conference on Parallel and Distributed Computing Systems, San Francisco, Ca, Sep. 20-22, 2006, International Society for Computers and Their Applications, Cary, NC 2006.
Shashidhara, Hosahally, WO 2008/142705 A2, Nov. 27, 2008.
Pan et al. (7712080) 20100500
Newcombe et al. (2003/0172290) 20030900
Kleinsorge et al. (6226734) 20010500
U.S. Appl. No. 12/336,312, "Techniques for Dynamically Assigning Jobs to Processors in a Cluster Based on Broadcast Information," Notice of Allowance dated Oct. 12, 2011.
Arimilli et al. (2010/0153966) 20100600
Zhang (2006/0133369) 20060600
Tang et al., Program Transformation and Runtime Support for Threaded MPI Execution on Shared-Memory Machines, ACM Transactions on Programming Languages and Systems, vol. 22, No. 4, Jul. 2000, p. 673-700.
VanHuben et al. (6038651) 20000300
Koop et al., High Performance MPI Design using Unreliable Datagram for Ultra-Scale InfiniBand Clusters, ICS '07 Jun. 18-20, Seattle, WA, ACM 2007.
Kouril et al., A Parallel Backtracking Framework (BkFr) for Single and Multiple Clusters, CF 2004, Apr. 14-16, 2004, Ischia, Italy, ACM 2004.
Hart (6154765) 20001100
Krylov et al. (2010/0223262) 20100900
Allon et al. (5539883) 19960700
Arimilli et al. (2010/0153965) 20100600
Coulter, K.-Office Action dated Sep. 14, 2010; U.S. Appl. No. 12/336,312.
U.S. Appl. No. 12/336,312, "Techniques for Dynamically Assigning Jobs to Processors in a Cluster Based on Broadcast Information", Notice of Allowance dated Sep. 20, 2011.
Squillante et al., Modeling and Analysis of Dynamic Coscheduling in Parallel and Distributed Environments, ACM 2001.
Wilkinson et al. (5878241) 19990300
Alexander (2002/0143923) 20021000
Boland (6269390) 20010700
Shen et al., Adaptive Two-level Thread Management for Fast MPI Execution on Shared Memory Machines, p. 1-19, SC 1999, Portland ,Oregon, ACM 1999.
Kessler et al. (5841973) 19981100
Norton et al. (2006/0168254) 20060700
de Backer et al. (6266745) 20010700
Kandasamy et al. (5640584) 19970600
Hart (6389451) 20020500
Cirou et al., Programming Irregular Scientific Algorithms with Static Properties on Clusters of SMP Nodes, Proceedings of the 2005 International Conference on Parallel Processing Workshops, AN-8588466, IEEE 2005.
Arimilli et al. (2010/0153542) 20100600
Cascaval et al. (7289939) 20071000
Oliveira (7761876) 20100700
Miller et al. (7389506) 20080600
Wu, et al., Tunable Randomization for Load Management in Shared-Disk Clusters, ACM Transactions on Storage, vol. 1, No. 1, Dec. 2004, pp. 108-131.
L.B. Arimilli-Office Action dated Apr. 1, 2011; U.S. Appl. No. 12/336,312.
Zhuang et al., Power-Efficient Prefetching for Embedded Processors, ACM Transactions on Embedded Computing Systems, vol. 6, No. 1, Article 3, Feb. 2007.
Zager et al. (6393386) 20020500
Chen et al. (7051115) 20060500
Krause (6047323) 20000400
References_xml – year: 20060500
  ident: 7051115
  contributor:
    fullname: Chen et al.
– year: 19960700
  ident: 5539883
  contributor:
    fullname: Allon et al.
– year: 20060600
  ident: 2006/0133369
  contributor:
    fullname: Zhang
– year: 20000400
  ident: 6047323
  contributor:
    fullname: Krause
– year: 20060100
  ident: 2006/0002385
  contributor:
    fullname: Johnsen et al.
– year: 20100900
  ident: 2010/0223262
  contributor:
    fullname: Krylov et al.
– year: 19970600
  ident: 5640584
  contributor:
    fullname: Kandasamy et al.
– year: 20010700
  ident: 6269390
  contributor:
    fullname: Boland
– year: 20080100
  ident: 2008/0016374
  contributor:
    fullname: Gee et al.
– year: 20100700
  ident: 7761876
  contributor:
    fullname: Oliveira
– year: 20100600
  ident: 2010/0153965
  contributor:
    fullname: Arimilli et al.
– year: 19990300
  ident: 5878241
  contributor:
    fullname: Wilkinson et al.
– year: 20040900
  ident: 6799202
  contributor:
    fullname: Hankinson et al.
– year: 20100600
  ident: 2010/0153541
  contributor:
    fullname: Arimilli et al.
– year: 19981100
  ident: 5841973
  contributor:
    fullname: Kessler et al.
– year: 20080600
  ident: 7389506
  contributor:
    fullname: Miller et al.
– year: 20071000
  ident: 7290040
  contributor:
    fullname: Newcombe et al.
– year: 20001100
  ident: 6154765
  contributor:
    fullname: Hart
– year: 20020500
  ident: 6393386
  contributor:
    fullname: Zager et al.
– year: 20050200
  ident: 2005/0027880
  contributor:
    fullname: Emmot
– year: 20020500
  ident: 6389451
  contributor:
    fullname: Hart
– year: 20100600
  ident: 2010/0153966
  contributor:
    fullname: Arimilli et al.
– year: 20010700
  ident: 6266745
  contributor:
    fullname: de Backer et al.
– year: 20030900
  ident: 2003/0172290
  contributor:
    fullname: Newcombe et al.
– year: 20090700
  ident: 2009/0187915
  contributor:
    fullname: Chew et al.
– year: 20000300
  ident: 6038651
  contributor:
    fullname: VanHuben et al.
– year: 20021000
  ident: 2002/0143923
  contributor:
    fullname: Alexander
– year: 20060700
  ident: 2006/0168254
  contributor:
    fullname: Norton et al.
– year: 20010500
  ident: 6226734
  contributor:
    fullname: Kleinsorge et al.
– year: 20100600
  ident: 2010/0153542
  contributor:
    fullname: Arimilli et al.
– year: 20070800
  ident: 2007/0198785
  contributor:
    fullname: Kogge et al.
– year: 20100500
  ident: 7712080
  contributor:
    fullname: Pan et al.
– year: 20071000
  ident: 7289939
  contributor:
    fullname: Cascaval et al.
Score 2.8543317
Snippet A technique for operating a high performance computing (HPC) cluster includes monitoring workloads of multiple processors included in the HPC cluster. The HPC...
SourceID uspatents
SourceType Open Access Repository
Title Techniques for dynamically assigning jobs to processors in a cluster based on processor workload
URI https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/8239524
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB7aIqgnRcX6Yg5eo91Nuo-zdFkEpYcKvdW8tlTWzbIPiv_eZFerF70mYRgSkm8m-fINwK1iOqQyY0RNJSNMex4RmnLCY1cjMwgz2r2ePz0H6Qt7XE6XA0h3f2He7TYipfWlvmvrsjEdudIe7_3Ck1782WkEFk59YFvkhqu5yu4jn8ZTnw1hGE0ctW-WpIewb03YkK1o6l-gkRzB3rxrPYaBLk7gdfEtl1qjjRRR9bXgeZ5_oI1gN2t3Q4FvRtTYGCx7Ar-patwUyFHmrZM0QIc6Ck3xMwAdtcr5dwqYzBYPKdm5s1pXjuaymny5Tc9gZNN9fQ6odKQ8yYPYVxETkRBc2pRJqzCUkmpJxzD-08zFP32XcGDB3u_Ia-EVjJqq1dcWUBtx083WJyVLhQg
link.rule.ids 230,309,783,805,888,64374
linkProvider USPTO
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV07T8MwED6VgnhMIECU5w2sBhI7TTpDo_CqMhSpW3Bsp2oVkqhOhfj32AkUFlht6_TJln13vs-fAS4lUz4VGSPSE4ww5TgkVZQTPrB_ZPb9jDbV8-dRP3phDxNv0oFo9RbmzWwjUhks-mqpq7psyJXmeG8XnrTiz1YjsLDqA-9FXnIZy-w6cOnAc9karNtSlFXRH4bRDmwZIyZoK2r9y22Eu7ARN6170FHFPryOvwVTNZpYEWX7GzzP8w80Mexsau8ocF6mGusSq5bCXy40zgrkKPKlFTVA63cklsXPALTkKovwADAcjm8jsoKTTBeW6JLcfAGnh9A1Cb86ApQqkI7g_YErA5YGacqFSZqU9H0hqBK0B70_zRz_03cBm_FdmDzdjx5PYNt4frdhsvmn0K0XS3VmvGudnjcT9wnOMIgD
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%3Apatent&rft.title=Techniques+for+dynamically+assigning+jobs+to+processors+in+a+cluster+based+on+processor+workload&rft.inventor=Arimilli%2C+Lakshminarayana+Baba&rft.inventor=Arimilli%2C+Ravi+Kumar&rft.inventor=Basso%2C+Claude&rft.inventor=Calvignac%2C+Jean+L&rft.number=8239524&rft.date=2012-08-07&rft.externalDBID=n%2Fa&rft.externalDocID=08239524