Energy-Aware Instruction Scheduling

  • Authors:
  • A. Parikh;Mahmut T. Kandemir;Narayanan Vijaykrishnan;Mary Jane Irwin

  • Affiliations:
  • -;-;-;-

  • Venue:
  • HiPC '00 Proceedings of the 7th International Conference on High Performance Computing
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

Energy consumption is increasingly becoming an important metric in designing computing systems. This paper focuses on instruction scheduling algorithms to reduce energy. Our experimentation shows that the best scheduling from the performance perspective is not necessarily the best scheduling from the energy perspective. Further, scheduling techniques that consider both energy and performance simultaneously are found to be desirable. We also validate the energy estimates of the instruction schedules obtained using the energy transition cost tables by executing the instructions on a cycle-accurate energy simulator. We conclude the paper with a discussion of alternate ways of building energy transition tables and estimating absolute energy consumption.