Analysis and Modeling of Social Influence in High Performance Computing Workloads

  title={Analysis and Modeling of Social Influence in High Performance Computing Workloads},
  author={S. Zheng and Z. Shae and X. Zhang and H. Jamjoom and L. Fong},
  • S. Zheng, Z. Shae, +2 authors L. Fong
  • Published 2011
  • Computer Science
  • ArXiv
  • 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Mining Streaming and Temporal Data : from Representation to Knowledge
    Regularized Singular Value Decomposition and Application to Recommender System
    • 7
    • PDF
    Harmonic Mean Linear Discriminant Analysis
    • 12
    Generative Adversarial Networks for Failure Prediction
    • 4
    • PDF
    A group lasso based sparse KNN classifier
    • 1
    Sparse classification using Group Matching Pursuit
    • 3
    Accelerating Deep Learning with Shrinkage and Recall
    • 17
    • PDF


    Publications referenced by this paper.
    Analysis and Lessons from a Publicly Available Google Cluster Trace
    • 127
    • PDF
    Towards characterizing cloud backend workloads: insights from Google compute clusters
    • 355
    • PDF
    The Characteristics and Performance of Groups of Jobs in Grids
    • 67
    The workload on parallel supercomputers: modeling the characteristics of rigid jobs
    • 427
    Experiences in Running Workloads over Grid3
    • 32
    • PDF
    Blog Community Discovery and Evolution Based on Mutual Awareness Expansion
    • 57
    • PDF
    On Simulation and Design of Parallel-Systems Schedulers: Are We Doing the Right Thing?
    • 45
    • Highly Influential
    • PDF