Scheduling with dynamic voltage/speed adjustment using slack reclamation in multiprocessor real-time systems

TLDR

Modern processors consume high power, reducing mission duration, increasing heat, and lowering reliability, yet most power‑saving research focuses on uniprocessor systems rather than multiprocessors. This work proposes two power‑aware scheduling algorithms for multiprocessor real‑time systems that use slack sharing and voltage/speed adjustment, and examines how discrete voltage levels and overhead affect energy savings. The algorithms reclaim unused task time to lower the execution speed of subsequent tasks, and a slack‑reservation scheme incorporates voltage‑adjustment overhead into the scheduling decisions. Simulations and trace‑based experiments show substantial energy savings, with processors having few discrete voltage levels achieving nearly the same savings as continuous levels and minimal impact from adjustment overhead.

Abstract

The high power consumption of modern processors becomes a major concern because it leads to decreased mission duration (for battery-operated systems), increased heat dissipation, and decreased reliability. While many techniques have been proposed to reduce power consumption for uniprocessor systems, there has been considerably less work on multiprocessor systems. In this paper, based on the concept of slack sharing among processors, we propose two novel power-aware scheduling algorithms for task sets with and without precedence constraints executing on multiprocessor systems. These scheduling techniques reclaim the time unused by a task to reduce the execution speed of future tasks and, thus, reduce the total energy consumption of the system. We also study the effect of discrete voltage/speed levels on the energy savings for multiprocessor systems and propose a new scheme of slack reservation to incorporate voltage/speed adjustment overhead in the scheduling algorithms. Simulation and trace-based results indicate that our algorithms achieve substantial energy savings on systems with variable voltage processors. Moreover, processors with a few discrete voltage/speed levels obtain nearly the same energy savings as processors with continuous voltage/speed, and the effect of voltage/speed adjustment overhead on the energy savings is relatively small.