Graph partitioning for dynamic, adaptive and multi-phase scientific simulations

Kirk Schloegel; George Karypis; Vipin Kumar

doi:10.1109/CLUSTR.2001.959987

Graph partitioning for dynamic, adaptive and multi-phase scientific simulations

Kirk Schloegel, George Karypis, Vipin Kumar

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

The efficient execution of scientific simulations on HPC systems requires a partitioning of the underlying mesh among the processors such that the load is balanced and the inter-processor communication is minimized. Graph partitioning algorithms have been applied with much success for this purpose. However, the parallelization of multi-phase and multi-physics computations poses new challenges that require fundamental advances in graph partitioning technology. In addition, most existing graph partitioning algorithms are not suited for the newer heterogeneous highperformance computing platforms. This talk will describe research efforts in our group that are focused on developing novel multi-constraint and multi-objective graph partitioning algorithms that can support the advancing state-ofthe-A rt in numerical simulation technologies. In addition, we will present our preliminary work on new partitioning algorithms that are well suited for heterogeneous architectures.

Original language	English (US)
Title of host publication	Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001
Editors	Daniel S. Katz, Thomas Sterling, Mark Baker, Larry Bergman, Marcin Paprzycki, Rajkumar Buyya
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	0769511163
DOIs	https://doi.org/10.1109/CLUSTR.2001.959987
State	Published - 2001
Event	2001 IEEE International Conference on Cluster Computing, CLUSTER 2001 - Newport Beach, United States Duration: Oct 8 2001 → Oct 11 2001

Publication series

Name	Proceedings - IEEE International Conference on Cluster Computing, ICCC
Volume	2001-October
ISSN (Print)	1552-5244

Conference

Conference	2001 IEEE International Conference on Cluster Computing, CLUSTER 2001
Country/Territory	United States
City	Newport Beach
Period	10/8/01 → 10/11/01

Bibliographical note

Publisher Copyright:
© 2001 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

Publisher link

10.1109/CLUSTR.2001.959987

Find It

Find It at U of M Libraries

Cite this

Schloegel, K., Karypis, G., & Kumar, V. (2001). Graph partitioning for dynamic, adaptive and multi-phase scientific simulations. In D. S. Katz, T. Sterling, M. Baker, L. Bergman, M. Paprzycki, & R. Buyya (Eds.), Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001 (Proceedings - IEEE International Conference on Cluster Computing, ICCC; Vol. 2001-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLUSTR.2001.959987

Graph partitioning for dynamic, adaptive and multi-phase scientific simulations. / Schloegel, Kirk; Karypis, George ; Kumar, Vipin.
Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001. ed. / Daniel S. Katz; Thomas Sterling; Mark Baker; Larry Bergman; Marcin Paprzycki; Rajkumar Buyya. Institute of Electrical and Electronics Engineers Inc., 2001. (Proceedings - IEEE International Conference on Cluster Computing, ICCC; Vol. 2001-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Schloegel, K, Karypis, G & Kumar, V 2001, Graph partitioning for dynamic, adaptive and multi-phase scientific simulations. in DS Katz, T Sterling, M Baker, L Bergman, M Paprzycki & R Buyya (eds), Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001. Proceedings - IEEE International Conference on Cluster Computing, ICCC, vol. 2001-October, Institute of Electrical and Electronics Engineers Inc., 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001, Newport Beach, United States, 10/8/01. https://doi.org/10.1109/CLUSTR.2001.959987

Schloegel K, Karypis G , Kumar V. Graph partitioning for dynamic, adaptive and multi-phase scientific simulations. In Katz DS, Sterling T, Baker M, Bergman L, Paprzycki M, Buyya R, editors, Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001. Institute of Electrical and Electronics Engineers Inc. 2001. (Proceedings - IEEE International Conference on Cluster Computing, ICCC). doi: 10.1109/CLUSTR.2001.959987

Schloegel, Kirk ; Karypis, George ; Kumar, Vipin. / Graph partitioning for dynamic, adaptive and multi-phase scientific simulations. Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001. editor / Daniel S. Katz ; Thomas Sterling ; Mark Baker ; Larry Bergman ; Marcin Paprzycki ; Rajkumar Buyya. Institute of Electrical and Electronics Engineers Inc., 2001. (Proceedings - IEEE International Conference on Cluster Computing, ICCC).

@inproceedings{1560c410af5a40bf82b0ec94f6359cea,

title = "Graph partitioning for dynamic, adaptive and multi-phase scientific simulations",

abstract = "The efficient execution of scientific simulations on HPC systems requires a partitioning of the underlying mesh among the processors such that the load is balanced and the inter-processor communication is minimized. Graph partitioning algorithms have been applied with much success for this purpose. However, the parallelization of multi-phase and multi-physics computations poses new challenges that require fundamental advances in graph partitioning technology. In addition, most existing graph partitioning algorithms are not suited for the newer heterogeneous highperformance computing platforms. This talk will describe research efforts in our group that are focused on developing novel multi-constraint and multi-objective graph partitioning algorithms that can support the advancing state-ofthe-A rt in numerical simulation technologies. In addition, we will present our preliminary work on new partitioning algorithms that are well suited for heterogeneous architectures.",

author = "Kirk Schloegel and George Karypis and Vipin Kumar",

note = "Publisher Copyright: {\textcopyright} 2001 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001 ; Conference date: 08-10-2001 Through 11-10-2001",

year = "2001",

doi = "10.1109/CLUSTR.2001.959987",

language = "English (US)",

series = "Proceedings - IEEE International Conference on Cluster Computing, ICCC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Katz, {Daniel S.} and Thomas Sterling and Mark Baker and Larry Bergman and Marcin Paprzycki and Rajkumar Buyya",

booktitle = "Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001",

}

TY - GEN

T1 - Graph partitioning for dynamic, adaptive and multi-phase scientific simulations

AU - Schloegel, Kirk

AU - Karypis, George

AU - Kumar, Vipin

PY - 2001

Y1 - 2001

N2 - The efficient execution of scientific simulations on HPC systems requires a partitioning of the underlying mesh among the processors such that the load is balanced and the inter-processor communication is minimized. Graph partitioning algorithms have been applied with much success for this purpose. However, the parallelization of multi-phase and multi-physics computations poses new challenges that require fundamental advances in graph partitioning technology. In addition, most existing graph partitioning algorithms are not suited for the newer heterogeneous highperformance computing platforms. This talk will describe research efforts in our group that are focused on developing novel multi-constraint and multi-objective graph partitioning algorithms that can support the advancing state-ofthe-A rt in numerical simulation technologies. In addition, we will present our preliminary work on new partitioning algorithms that are well suited for heterogeneous architectures.

AB - The efficient execution of scientific simulations on HPC systems requires a partitioning of the underlying mesh among the processors such that the load is balanced and the inter-processor communication is minimized. Graph partitioning algorithms have been applied with much success for this purpose. However, the parallelization of multi-phase and multi-physics computations poses new challenges that require fundamental advances in graph partitioning technology. In addition, most existing graph partitioning algorithms are not suited for the newer heterogeneous highperformance computing platforms. This talk will describe research efforts in our group that are focused on developing novel multi-constraint and multi-objective graph partitioning algorithms that can support the advancing state-ofthe-A rt in numerical simulation technologies. In addition, we will present our preliminary work on new partitioning algorithms that are well suited for heterogeneous architectures.

UR - http://www.scopus.com/inward/record.url?scp=84984827394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984827394&partnerID=8YFLogxK

U2 - 10.1109/CLUSTR.2001.959987

DO - 10.1109/CLUSTR.2001.959987

M3 - Conference contribution

AN - SCOPUS:84984827394

T3 - Proceedings - IEEE International Conference on Cluster Computing, ICCC

BT - Proceedings - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001

A2 - Katz, Daniel S.

A2 - Sterling, Thomas

A2 - Baker, Mark

A2 - Bergman, Larry

A2 - Paprzycki, Marcin

A2 - Buyya, Rajkumar

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2001 IEEE International Conference on Cluster Computing, CLUSTER 2001

Y2 - 8 October 2001 through 11 October 2001

ER -

Graph partitioning for dynamic, adaptive and multi-phase scientific simulations

Abstract

Publication series

Conference

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this