Analysis and modeling of social influence in high performance computing workloads

Handle URI:
http://hdl.handle.net/10754/564342
Title:
Analysis and modeling of social influence in high performance computing workloads
Authors:
Zheng, Shuai; Shae, Zon Yin; Zhang, Xiangliang ( 0000-0002-3574-5665 ) ; Jamjoom, Hani T.; Fong, Liana
Abstract:
Social influence among users (e.g., collaboration on a project) creates bursty behavior in the underlying high performance computing (HPC) workloads. Using representative HPC and cluster workload logs, this paper identifies, analyzes, and quantifies the level of social influence across HPC users. We show the existence of a social graph that is characterized by a pattern of dominant users and followers. This pattern also follows a power-law distribution, which is consistent with those observed in mainstream social networks. Given its potential impact on HPC workloads prediction and scheduling, we propose a fast-converging, computationally-efficient online learning algorithm for identifying social groups. Extensive evaluation shows that our online algorithm can (1) quickly identify the social relationships by using a small portion of incoming jobs and (2) can efficiently track group evolution over time. © 2011 Springer-Verlag.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Machine Intelligence & kNowledge Engineering Lab
Publisher:
Springer Science + Business Media
Journal:
Lecture Notes in Computer Science
Conference/Event name:
17th International Conference on Parallel Processing, Euro-Par 2011
Issue Date:
2011
DOI:
10.1007/978-3-642-23400-2_19
Type:
Conference Paper
ISSN:
03029743
ISBN:
9783642233999
Appears in Collections:
Conference Papers; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZheng, Shuaien
dc.contributor.authorShae, Zon Yinen
dc.contributor.authorZhang, Xiangliangen
dc.contributor.authorJamjoom, Hani T.en
dc.contributor.authorFong, Lianaen
dc.date.accessioned2015-08-04T06:24:17Zen
dc.date.available2015-08-04T06:24:17Zen
dc.date.issued2011en
dc.identifier.isbn9783642233999en
dc.identifier.issn03029743en
dc.identifier.doi10.1007/978-3-642-23400-2_19en
dc.identifier.urihttp://hdl.handle.net/10754/564342en
dc.description.abstractSocial influence among users (e.g., collaboration on a project) creates bursty behavior in the underlying high performance computing (HPC) workloads. Using representative HPC and cluster workload logs, this paper identifies, analyzes, and quantifies the level of social influence across HPC users. We show the existence of a social graph that is characterized by a pattern of dominant users and followers. This pattern also follows a power-law distribution, which is consistent with those observed in mainstream social networks. Given its potential impact on HPC workloads prediction and scheduling, we propose a fast-converging, computationally-efficient online learning algorithm for identifying social groups. Extensive evaluation shows that our online algorithm can (1) quickly identify the social relationships by using a small portion of incoming jobs and (2) can efficiently track group evolution over time. © 2011 Springer-Verlag.en
dc.publisherSpringer Science + Business Mediaen
dc.titleAnalysis and modeling of social influence in high performance computing workloadsen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentMachine Intelligence & kNowledge Engineering Laben
dc.identifier.journalLecture Notes in Computer Scienceen
dc.conference.date29 August 2011 through 2 September 2011en
dc.conference.name17th International Conference on Parallel Processing, Euro-Par 2011en
dc.conference.locationBordeauxen
dc.contributor.institutionIBM T. J. Watson Research Center, Hawthorne, NY, United Statesen
kaust.authorZheng, Shuaien
kaust.authorZhang, Xiangliangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.