Algorithms for Scheduling Imprecise Computations

  • Authors:
  • Jane W. S. Liu;Kwei-Jay Lin;Wei-Kuan Shih;Albert Chuang-shi Yu;Jen-Yao Chung;Wei Zhao

  • Affiliations:
  • Univ. of Illinois at Urbana-Champaign, Urbana;Univ. of Illinois at Urbana-Champaign, Urbana;Univ. of Illinois at Urbana-Champaign, Urbana;Univ. of Illinois at Urbana-Champaign, Urbana;IBM T. J. Watson Research Center, Yorktown Heights, NY;Texas A&M Univ., College Station

  • Venue:
  • Computer - Special issue on real-time systems
  • Year:
  • 1991

Quantified Score

Hi-index 0.02

Visualization

Abstract

The imprecise computation technique, which prevents timing faults and achieves graceful degradation by giving the user an approximate result of acceptable quality whenever the system cannot produce the exact result in time, is considered. Different approaches for scheduling imprecise computations in hard real-time environments are discussed. Workload models that quantify the tradeoff between result quality and computation time are reviewed. Scheduling algorithms that exploit this tradeoff are described. These include algorithms for scheduling to minimize total error, scheduling periodic jobs, and scheduling parallelizable tasks. A queuing-theoretical formulation of the imprecise scheduling problem is presented.