A global optimal scheduling algorithm for multiprocessor low-power platforms

  • Authors:
  • Shelby Funk;Vandy Berten;Chiahsun Ho;Joël Goossens

  • Affiliations:
  • University of Georgia (UGA), Athens GA;Université Libre de Bruxelles (ULB), Brussels, Belgium;University of Georgia (UGA), Athens GA;Université Libre de Bruxelles (ULB), Brussels, Belgium

  • Venue:
  • Proceedings of the 20th International Conference on Real-Time and Network Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a real-time scheduling algorithm which globally schedules any feasible periodic task set --- i.e., is optimal --- on a multiprocessor platform. Beside respecting the deadlines, our algorithm, based on DP-Wrap algorithm, drastically reduces the power consumption of the device by slowing down the processors as much as possible. We present our algorithm in two versions (if frequency changes are allowed at any time, or if there are some restrictions about it), prove its (schedulability) correctness, and provide several simulations attesting its low-power efficiency.