Improving efficiency of a global barrier operation in a parallel computer

Title: Improving efficiency of a global barrier operation in a parallel computer

Abstract

Performing a global barrier operation in a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the single local barrier.

Issue Date:: 2016-10-04

Research Org.:: International Business Machines Corp., Armonk, NY (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1327915

Patent Number(s):: 9459934

Application Number:: 13/683,726

Assignee:: International Business Machines Corporation (Armonk, NY

Patent Classifications (CPCs):: G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING

Show more

G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
G06F9/52 - Program synchronisation
G06F9/546 - {Message passing systems or structures, e.g. queues}
G06F15/17318 - {Parallel communications techniques, e.g. gather, scatter, reduce, roadcast, multicast, all to all}
G06F9/522 - {Barrier synchronisation}
G06F9/46 - Multiprogramming arrangements
G06F9/542 - {Event management

Show less

DOE Contract Number:: B554331

Resource Type:: Patent

Resource Relation:: Patent File Date: 2012 Nov 21

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    . Improving efficiency of a global barrier operation in a parallel computer.  United States: N. p., 2016. 
        Web.

Copy to clipboard


                    . Improving efficiency of a global barrier operation in a parallel computer.  United States.

Copy to clipboard


                    . Tue .  
        "Improving efficiency of a global barrier operation in a parallel computer".  United States.  https://www.osti.gov/servlets/purl/1327915.

Copy to clipboard


                    
@article{osti_1327915,

  title        = {Improving efficiency of a global barrier operation in a parallel computer},

  author       = {},

  abstractNote = {Performing a global barrier operation in a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the single local barrier.},

  doi          = {},

  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {2016},

  month        = {10}

}

Copy to clipboard

Patent:

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Automatic generation and tuning of MPI collective communication routines
conference, January 2005

Faraj, Ahmad; Yuan, Xin
Proceedings of the 19th annual international conference on Supercomputing - ICS '05
https://doi.org/10.1145/1088149.1088202

Building packet buffers using interleaved memories
conference, January 2005

Shrimali, G.; McKeown, N.
HPSR. 2005 Workshop on High Performance Switching and Routing, 2005.
https://doi.org/10.1109/HPSR.2005.1503183

Kernel-level single system image for petascale computing
journal, April 2006

Ong, Hong; Vetter, Jeffrey; Studham, R. Scott
ACM SIGOPS Operating Systems Review, Vol. 40, Issue 2
https://doi.org/10.1145/1131322.1131335

Real-Time Performance Monitoring, Adaptive Control, and Interactive Steering of Computational Grids
journal, November 2000

Vetter, Jeffrey S.; Reed, Daniel A.
The International Journal of High Performance Computing Applications, Vol. 14, Issue 4
https://doi.org/10.1177/109434200001400407

Optimization of MPI collectives on clusters of large-scale SMP's
conference, January 1999

Sistare, Steve; vandeVaart, Rolf; Loh, Eugene
Proceedings of the 1999 ACM/IEEE conference on Supercomputing (CDROM) - Supercomputing '99
https://doi.org/10.1145/331532.331555

AM++: a generalized active message framework
conference, January 2010

Willcock, Jeremiah James; Hoefler, Torsten; Edmonds, Nicholas Gerard
Proceedings of the 19th international conference on Parallel architectures and compilation techniques - PACT '10
https://doi.org/10.1145/1854273.1854323

Extending the message passing interface (MPI)
conference, January 1995

Skjellum, A.; Doss, N. E.; Viswanathan, K.
Proceedings Scalable Parallel Libraries Conference
https://doi.org/10.1109/SPLC.1994.376998

Computing parallel prefix and reduction using coterie structures
conference, January 1992

Herbordt, M. C.; Weems, C. C.
[1992] The Fourth Symposium on the Frontiers of Massively Parallel Computation, [Proceedings 1992] The Fourth Symposium on the Frontiers of Massively Parallel Computation
https://doi.org/10.1109/FMPC.1992.234895

Computing the Hough transform on a scan line array processor (image processing)
journal, March 1989

Fisher, A. L.; Highnam, P. T.
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, Issue 3
https://doi.org/10.1109/34.21795

Efficient MPI Collective Operations for Clusters in Long-and-Fast Networks
conference, September 2006

Matsuda, Motohiko; Kudoh, Tomohiro; Kodama, Yuetsu
2006 IEEE International Conference on Cluster Computing
https://doi.org/10.1109/CLUSTR.2006.311848

Bandwidth Efficient All-reduce Operation on Tree Topologies
conference, March 2007

Patarasuk, Pitch; Yuan, Xin
2007 IEEE International Parallel and Distributed Processing Symposium
https://doi.org/10.1109/IPDPS.2007.370405

Optimizing threaded MPI execution on SMP clusters
conference, January 2001

Tang, Hong; Yang, Tao
Proceedings of the 15th international conference on Supercomputing - ICS '01
https://doi.org/10.1145/377792.377895

Interleaved all-to-all reliable broadcast on meshes and hypercubes
journal, May 1994

Sunggu Lee, ; Shin, K. G.
IEEE Transactions on Parallel and Distributed Systems, Vol. 5, Issue 5
https://doi.org/10.1109/71.282556

Efficient algorithms for all-to-all communications in multiport message-passing systems
journal, January 1997

Bruck, J.; Kipnis, S.
IEEE Transactions on Parallel and Distributed Systems, Vol. 8, Issue 11
https://doi.org/10.1109/71.642949

Performance analysis and optimization of MPI collective operations on multi-core clusters
journal, April 2009

Tu, Bibo; Fan, Jianping; Zhan, Jianfeng
The Journal of Supercomputing, Vol. 60, Issue 1
https://doi.org/10.1007/s11227-009-0296-3

Similar Records in DOE Patents and OSTI.GOV collections:

Performing a global barrier operation in a parallel computer

Patent Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; ...

Executing computing tasks on a parallel computer that includes compute nodes coupled for data communications, where each compute node executes tasks, with one task on each compute node designated as a master task, including: for each task on each compute node until all master tasks have joined a global barrier: determining whether the task is a master task; if the task is not a master task, joining a single local barrier; if the task is a master task, joining the global barrier and the single local barrier only after all other tasks on the compute node have joined the singlemore » local barrier. « less
Full Text Available
Determining when a set of compute nodes participating in a barrier operation on a parallel computer are ready to exit the barrier operation

Patent Blocksome, Michael A [Rochester, MN]

Methods, apparatus, and products are disclosed for determining when a set of compute nodes participating in a barrier operation on a parallel computer are ready to exit the barrier operation that includes, for each compute node in the set: initializing a barrier counter with no counter underflow interrupt; configuring, upon entering the barrier operation, the barrier counter with a value in dependence upon a number of compute nodes in the set; broadcasting, by a DMA engine on the compute node to each of the other compute nodes upon entering the barrier operation, a barrier control packet; receiving, by the DMAmore » « less
Full Text Available
Providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer

Patent Archer, Charles J.; Faraj, Daniel A.; Inglett, Todd A.; ...

Methods, apparatus, and products are disclosed for providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer, each compute node connected to each adjacent compute node in the global combining network through a link, that include: receiving a network packet in a compute node, the network packet specifying a destination compute node; selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node; and forwarding the network packet along the selectedmore » « less
Full Text Available
Providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer

Patent Archer, Charles J; Faraj, Ahmad A; Inglett, Todd A; ...

Methods, apparatus, and products are disclosed for providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer, each compute node connected to each adjacent compute node in the global combining network through a link, that include: receiving a network packet in a compute node, the network packet specifying a destination compute node; selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node; and forwarding the network packet along the selectedmore » « less
Full Text Available
Determining collective barrier operation skew in a parallel computer

Patent Faraj, Daniel A.

Determining collective barrier operation skew in a parallel computer that includes a number of compute nodes organized into an operational group includes: for each of the nodes until each node has been selected as a delayed node: selecting one of the nodes as a delayed node; entering, by each node other than the delayed node, a collective barrier operation; entering, after a delay by the delayed node, the collective barrier operation; receiving an exit signal from a root of the collective barrier operation; and measuring, for the delayed node, a barrier completion time. The barrier operation skew is calculated by:more » « less
Full Text Available

Similar Records

Title: Improving efficiency of a global barrier operation in a parallel computer

Abstract

Citation Formats

Automatic generation and tuning of MPI collective communication routines conference, January 2005

Building packet buffers using interleaved memories conference, January 2005

Kernel-level single system image for petascale computing journal, April 2006

Real-Time Performance Monitoring, Adaptive Control, and Interactive Steering of Computational Grids journal, November 2000

Optimization of MPI collectives on clusters of large-scale SMP's conference, January 1999

AM++: a generalized active message framework conference, January 2010

Extending the message passing interface (MPI) conference, January 1995

Computing parallel prefix and reduction using coterie structures conference, January 1992

Computing the Hough transform on a scan line array processor (image processing) journal, March 1989

Efficient MPI Collective Operations for Clusters in Long-and-Fast Networks conference, September 2006

Bandwidth Efficient All-reduce Operation on Tree Topologies conference, March 2007

Optimizing threaded MPI execution on SMP clusters conference, January 2001

Interleaved all-to-all reliable broadcast on meshes and hypercubes journal, May 1994

Efficient algorithms for all-to-all communications in multiport message-passing systems journal, January 1997

Performance analysis and optimization of MPI collective operations on multi-core clusters journal, April 2009

Automatic generation and tuning of MPI collective communication routines
conference, January 2005

Building packet buffers using interleaved memories
conference, January 2005

Kernel-level single system image for petascale computing
journal, April 2006

Real-Time Performance Monitoring, Adaptive Control, and Interactive Steering of Computational Grids
journal, November 2000

Optimization of MPI collectives on clusters of large-scale SMP's
conference, January 1999

AM++: a generalized active message framework
conference, January 2010

Extending the message passing interface (MPI)
conference, January 1995

Computing parallel prefix and reduction using coterie structures
conference, January 1992

Computing the Hough transform on a scan line array processor (image processing)
journal, March 1989

Efficient MPI Collective Operations for Clusters in Long-and-Fast Networks
conference, September 2006

Bandwidth Efficient All-reduce Operation on Tree Topologies
conference, March 2007

Optimizing threaded MPI execution on SMP clusters
conference, January 2001

Interleaved all-to-all reliable broadcast on meshes and hypercubes
journal, May 1994

Efficient algorithms for all-to-all communications in multiport message-passing systems
journal, January 1997

Performance analysis and optimization of MPI collective operations on multi-core clusters
journal, April 2009