Comparing the performance of group detection algorithm in serial and parallel processing environments

Channing Brown; Marshall Scott Poole; Iftekhar Ahmed; Andrew Pilny; Dora Cai; Yannick Atouba

doi:10.1145/2335755.2335817

Comparing the performance of group detection algorithm in serial and parallel processing environments

Channing Brown, Marshall Scott Poole, Iftekhar Ahmed, Andrew Pilny, Dora Cai, Yannick Atouba

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

Abstract

Developing an algorithm for group identification from a collection of individuals without grouping data has been getting significant attention because of the need for increased understanding of groups and teams in online environments. This study used space, time, task, and players' virtual behavioral indicators from a game database to develop an algorithm to detect groups over time. The group detection algorithm was primarily developed for a serial processing environment and later then modified to allow for parallel processing on Gordon. For a collection of data representing 192 days of game play (approximately 140 gigabytes of log data), the computation required 266 minutes for the major steps of the analysis when running on a single processor. The same computation required 25 minutes when running on Gordon with 16 processors. The provision of massive compute nodes and the rich shared memory environment on Gordon has improved the performance of our analysis by a factor of 11. Besides demonstrating the possibility to save time and effort, this study also highlights some lessons learned for transforming a serial detection algorithm to parallel environments.

Original language	English
Title of host publication	Proceedings of the XSEDE12 Conference
Subtitle of host publication	Bridging from the eXtreme to the Campus and Beyond
DOIs	https://doi.org/10.1145/2335755.2335817
State	Published - 2012
Event	1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12 - Chicago, IL, United States Duration: Jul 16 2012 → Jul 19 2012

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12
Country/Territory	United States
City	Chicago, IL
Period	7/16/12 → 7/19/12

Keywords

MMOG
data mining
group detection
online games
serial vs. parallel processing
social computing
virtual groups

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/2335755.2335817

Cite this

@inproceedings{b51249f34600472db69f04aec5ddfee3,

title = "Comparing the performance of group detection algorithm in serial and parallel processing environments",

abstract = "Developing an algorithm for group identification from a collection of individuals without grouping data has been getting significant attention because of the need for increased understanding of groups and teams in online environments. This study used space, time, task, and players' virtual behavioral indicators from a game database to develop an algorithm to detect groups over time. The group detection algorithm was primarily developed for a serial processing environment and later then modified to allow for parallel processing on Gordon. For a collection of data representing 192 days of game play (approximately 140 gigabytes of log data), the computation required 266 minutes for the major steps of the analysis when running on a single processor. The same computation required 25 minutes when running on Gordon with 16 processors. The provision of massive compute nodes and the rich shared memory environment on Gordon has improved the performance of our analysis by a factor of 11. Besides demonstrating the possibility to save time and effort, this study also highlights some lessons learned for transforming a serial detection algorithm to parallel environments.",

keywords = "MMOG, data mining, group detection, online games, serial vs. parallel processing, social computing, virtual groups",

author = "Channing Brown and Poole, {Marshall Scott} and Iftekhar Ahmed and Andrew Pilny and Dora Cai and Yannick Atouba",

year = "2012",

doi = "10.1145/2335755.2335817",

language = "English",

isbn = "9781450316026",

series = "ACM International Conference Proceeding Series",

booktitle = "Proceedings of the XSEDE12 Conference",

note = "1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12 ; Conference date: 16-07-2012 Through 19-07-2012",

}

Brown, C, Poole, MS, Ahmed, I, Pilny, A, Cai, D & Atouba, Y 2012, Comparing the performance of group detection algorithm in serial and parallel processing environments. in Proceedings of the XSEDE12 Conference: Bridging from the eXtreme to the Campus and Beyond. ACM International Conference Proceeding Series, 1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12, Chicago, IL, United States, 7/16/12. https://doi.org/10.1145/2335755.2335817

Comparing the performance of group detection algorithm in serial and parallel processing environments. / Brown, Channing; Poole, Marshall Scott; Ahmed, Iftekhar et al.
Proceedings of the XSEDE12 Conference: Bridging from the eXtreme to the Campus and Beyond. 2012. (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Comparing the performance of group detection algorithm in serial and parallel processing environments

AU - Brown, Channing

AU - Poole, Marshall Scott

AU - Ahmed, Iftekhar

AU - Pilny, Andrew

AU - Cai, Dora

AU - Atouba, Yannick

PY - 2012

Y1 - 2012

N2 - Developing an algorithm for group identification from a collection of individuals without grouping data has been getting significant attention because of the need for increased understanding of groups and teams in online environments. This study used space, time, task, and players' virtual behavioral indicators from a game database to develop an algorithm to detect groups over time. The group detection algorithm was primarily developed for a serial processing environment and later then modified to allow for parallel processing on Gordon. For a collection of data representing 192 days of game play (approximately 140 gigabytes of log data), the computation required 266 minutes for the major steps of the analysis when running on a single processor. The same computation required 25 minutes when running on Gordon with 16 processors. The provision of massive compute nodes and the rich shared memory environment on Gordon has improved the performance of our analysis by a factor of 11. Besides demonstrating the possibility to save time and effort, this study also highlights some lessons learned for transforming a serial detection algorithm to parallel environments.

AB - Developing an algorithm for group identification from a collection of individuals without grouping data has been getting significant attention because of the need for increased understanding of groups and teams in online environments. This study used space, time, task, and players' virtual behavioral indicators from a game database to develop an algorithm to detect groups over time. The group detection algorithm was primarily developed for a serial processing environment and later then modified to allow for parallel processing on Gordon. For a collection of data representing 192 days of game play (approximately 140 gigabytes of log data), the computation required 266 minutes for the major steps of the analysis when running on a single processor. The same computation required 25 minutes when running on Gordon with 16 processors. The provision of massive compute nodes and the rich shared memory environment on Gordon has improved the performance of our analysis by a factor of 11. Besides demonstrating the possibility to save time and effort, this study also highlights some lessons learned for transforming a serial detection algorithm to parallel environments.

KW - MMOG

KW - data mining

KW - group detection

KW - online games

KW - serial vs. parallel processing

KW - social computing

KW - virtual groups

UR - http://www.scopus.com/inward/record.url?scp=84865312348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865312348&partnerID=8YFLogxK

U2 - 10.1145/2335755.2335817

DO - 10.1145/2335755.2335817

M3 - Conference contribution

AN - SCOPUS:84865312348

SN - 9781450316026

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the XSEDE12 Conference

T2 - 1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12

Y2 - 16 July 2012 through 19 July 2012

ER -

Comparing the performance of group detection algorithm in serial and parallel processing environments

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this