Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters

Jae-seung Yeom; Abhinav Bhatele; Keith Bisset; Eric Bohm; Abhishek Gupta; Laxmikant V. Kale; Madhav Marathe; Dimitrios S. Nikolopoulos; Martin Schulz; Lukasz Wesolowski

doi:10.1109/IPDPS.2014.83

Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters

Jae-seung Yeom, Abhinav Bhatele, Keith Bisset, Eric Bohm, Abhishek Gupta, Laxmikant V. Kale, Madhav Marathe, Dimitrios S. Nikolopoulos, Martin Schulz, Lukasz Wesolowski

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

22 Citations (Scopus)

384 Downloads (Pure)

Abstract

Modeling dynamical systems represents an important application class covering a wide range of disciplines including but not limited to biology, chemistry, finance, national security, and health care. Such applications typically involve large-scale, irregular graph processing, which makes them difficult to scale due to the evolutionary nature of their workload, irregular communication and load imbalance. EpiSimdemics is such an application simulating epidemic diffusion in extremely large and realistic social contact networks. It implements a graph-based system that captures dynamics among co-evolving entities. This paper presents an implementation of EpiSimdemics in Charm++ that enables future research by social, biological and computational scientists at unprecedented data and system scales. We present new methods for application-specific processing of graph data and demonstrate the effectiveness of these methods on a Cray XE6, specifically NCSA's Blue Waters system.

Original language	English
Title of host publication	2014 IEEE 28th International Parallel and Distributed Processing Symposium
Place of Publication	Washington, DC, USA
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	755-764
Number of pages	10
ISBN (Print)	978-1-4799-3800-1
DOIs	https://doi.org/10.1109/IPDPS.2014.83
Publication status	Published - May 2014

Access to Document

10.1109/IPDPS.2014.83

Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters
© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 2.14 MB

Cite this

Yeom, J., Bhatele, A., Bisset, K., Bohm, E., Gupta, A., Kale, L. V., Marathe, M., Nikolopoulos, D. S., Schulz, M., & Wesolowski, L. (2014). Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters. In 2014 IEEE 28th International Parallel and Distributed Processing Symposium (pp. 755-764). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPDPS.2014.83

Yeom, Jae-seung ; Bhatele, Abhinav ; Bisset, Keith ; Bohm, Eric ; Gupta, Abhishek ; Kale, Laxmikant V. ; Marathe, Madhav ; Nikolopoulos, Dimitrios S. ; Schulz, Martin ; Wesolowski, Lukasz. / Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters. 2014 IEEE 28th International Parallel and Distributed Processing Symposium. Washington, DC, USA : Institute of Electrical and Electronics Engineers Inc., 2014. pp. 755-764

@inproceedings{f14c626790a84bd9a1223f659e621a6d,

title = "Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters",

abstract = "Modeling dynamical systems represents an important application class covering a wide range of disciplines including but not limited to biology, chemistry, finance, national security, and health care. Such applications typically involve large-scale, irregular graph processing, which makes them difficult to scale due to the evolutionary nature of their workload, irregular communication and load imbalance. EpiSimdemics is such an application simulating epidemic diffusion in extremely large and realistic social contact networks. It implements a graph-based system that captures dynamics among co-evolving entities. This paper presents an implementation of EpiSimdemics in Charm++ that enables future research by social, biological and computational scientists at unprecedented data and system scales. We present new methods for application-specific processing of graph data and demonstrate the effectiveness of these methods on a Cray XE6, specifically NCSA's Blue Waters system.",

author = "Jae-seung Yeom and Abhinav Bhatele and Keith Bisset and Eric Bohm and Abhishek Gupta and Kale, {Laxmikant V.} and Madhav Marathe and Nikolopoulos, {Dimitrios S.} and Martin Schulz and Lukasz Wesolowski",

year = "2014",

month = may,

doi = "10.1109/IPDPS.2014.83",

language = "English",

isbn = "978-1-4799-3800-1 ",

pages = "755--764",

booktitle = "2014 IEEE 28th International Parallel and Distributed Processing Symposium",

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

}

Yeom, J, Bhatele, A, Bisset, K, Bohm, E, Gupta, A, Kale, LV, Marathe, M, Nikolopoulos, DS, Schulz, M & Wesolowski, L 2014, Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters. in 2014 IEEE 28th International Parallel and Distributed Processing Symposium. Institute of Electrical and Electronics Engineers Inc., Washington, DC, USA, pp. 755-764. https://doi.org/10.1109/IPDPS.2014.83

Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters. / Yeom, Jae-seung; Bhatele, Abhinav; Bisset, Keith; Bohm, Eric; Gupta, Abhishek; Kale, Laxmikant V.; Marathe, Madhav; Nikolopoulos, Dimitrios S.; Schulz, Martin; Wesolowski, Lukasz.

2014 IEEE 28th International Parallel and Distributed Processing Symposium. Washington, DC, USA : Institute of Electrical and Electronics Engineers Inc., 2014. p. 755-764.

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

TY - GEN

T1 - Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters

AU - Yeom, Jae-seung

AU - Bhatele, Abhinav

AU - Bisset, Keith

AU - Bohm, Eric

AU - Gupta, Abhishek

AU - Kale, Laxmikant V.

AU - Marathe, Madhav

AU - Nikolopoulos, Dimitrios S.

AU - Schulz, Martin

AU - Wesolowski, Lukasz

PY - 2014/5

Y1 - 2014/5

N2 - Modeling dynamical systems represents an important application class covering a wide range of disciplines including but not limited to biology, chemistry, finance, national security, and health care. Such applications typically involve large-scale, irregular graph processing, which makes them difficult to scale due to the evolutionary nature of their workload, irregular communication and load imbalance. EpiSimdemics is such an application simulating epidemic diffusion in extremely large and realistic social contact networks. It implements a graph-based system that captures dynamics among co-evolving entities. This paper presents an implementation of EpiSimdemics in Charm++ that enables future research by social, biological and computational scientists at unprecedented data and system scales. We present new methods for application-specific processing of graph data and demonstrate the effectiveness of these methods on a Cray XE6, specifically NCSA's Blue Waters system.

AB - Modeling dynamical systems represents an important application class covering a wide range of disciplines including but not limited to biology, chemistry, finance, national security, and health care. Such applications typically involve large-scale, irregular graph processing, which makes them difficult to scale due to the evolutionary nature of their workload, irregular communication and load imbalance. EpiSimdemics is such an application simulating epidemic diffusion in extremely large and realistic social contact networks. It implements a graph-based system that captures dynamics among co-evolving entities. This paper presents an implementation of EpiSimdemics in Charm++ that enables future research by social, biological and computational scientists at unprecedented data and system scales. We present new methods for application-specific processing of graph data and demonstrate the effectiveness of these methods on a Cray XE6, specifically NCSA's Blue Waters system.

U2 - 10.1109/IPDPS.2014.83

DO - 10.1109/IPDPS.2014.83

M3 - Conference contribution

SN - 978-1-4799-3800-1

SP - 755

EP - 764

BT - 2014 IEEE 28th International Parallel and Distributed Processing Symposium

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Washington, DC, USA

ER -

Overcoming the Scalability Challenges of Epidemic Simulations on Blue Waters

Abstract

Access to Document

Fingerprint

Cite this