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. |
Year | Venue | Keywords |
---|---|---|
2011 | Euro-Par'11 Proceedings of the 17th international conference on Parallel processing - Volume Part I | social influence,online algorithm,hpc workloads prediction,social group,social graph,social relationship,hpc user,mainstream social network,representative hpc,high performance computing workloads,computationally-efficient online |
Field | DocType | Volume |
Social group,Online algorithm,Social graph,Social network,Supercomputer,Computer science,Scheduling (computing),Workload,Parallel computing,Social influence,Distributed computing | Conference | abs/1610.04676 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuai Zheng | 1 | 12 | 4.27 |
Zon-yin Shae | 2 | 206 | 21.12 |
Xiangliang Zhang | 3 | 728 | 87.74 |
Hani Jamjoom | 4 | 691 | 42.44 |
Liana Fong | 5 | 264 | 23.53 |