Task Fusion: Improving Utilization of Multi-User Clusters

By: Robert Dyer

Download Paper
Poster
Slides

Abstract

Researchers use shared computing clusters to ask interesting questions and wish to maximize their utilization. Currently, optimizations focus on individual programs. We present task fusion to automatically merge multiple tasks into a single task. An example implementation shows fused tasks take 14-90% less time than running the tasks individually.

ACM Reference

Dyer, R. 2013. Task Fusion: Improving Utilization of Multi-user Clusters. SPLASH 2013 (Oct. 2013).

BibTeX Reference

@inproceedings{dyer2013task,
  author = {Robert Dyer},
  title = {Task Fusion: Improving Utilization of Multi-user Clusters},
  booktitle = {SPLASH 2013},
  location = {Indianapolis, IN, USA},
  month = {October},
  year = {2013},
  entrysubtype = {conference},
  abstract = {
    Researchers use shared computing clusters to ask interesting questions and
    wish to maximize their utilization. Currently, optimizations focus on
    individual programs. We present task fusion to automatically merge multiple
    tasks into a single task. An example implementation shows fused tasks take
    14-90% less time than running the tasks individually.
  }
}