Comparing algorithm for dynamic speed-setting of a low-power CPU

Govil, Kinshuk; Chan, Edwin Sing-Long; Wasserman, Hal

doi:10.1145/215530.215546

Cited by 343 publications

(232 citation statements)

References 3 publications

Supporting

Mentioning

225

Contrasting

Unclassified

Order By: Relevance

“…The potential to save energy by combining DVS techniques with operating system scheduling has been demonstrated by prior work, and significant savings have been reported for general-purpose computing systems (Govil et al, 1995;Grunwald et al, 2000;Krishna and Lee, 2000;Lorch and Smith, 2001;Pering et al, 1995;Weiser et al, 1994;Pouwelse et al, 2000;Gruian and Kuchcinski, 2001) as well as real-time systems (Hong et al, 1998a;Hong et al, 1998b;Lee and Krishna, 1999;Shin et al, 2000;Pillai and Shin, 2001; D. Shin and Lee, 2001;Mosse et al, 2000;Gruian, 2001;Aydin et al, 2001;Kang et al, 2002). However, pure DVS techniques do not perform well for dynamic systems where the system workloads vary significantly.…”

Section: Introductionmentioning

confidence: 94%

Feedback EDF Scheduling of Real-Time Tasks Exploiting Dynamic Voltage Scaling

Zhu

Mueller

2005

Real-Time Syst

View full text Add to dashboard Cite

Abstract.Many embedded systems are constrained by limits on power consumption, which are reflected in the design and implementation for conserving their energy utilization. Dynamic voltage scaling (DVS) has become a promising method for embedded systems to exploit multiple voltage and frequency levels and to prolong their battery life. However, pure DVS techniques do not perform well for systems with dynamic workloads where the job execution times vary significantly. In this paper, we present a novel approach combining feedback control with DVS schemes targeting hard real-time systems with dynamic workloads. Our method relies strictly on operating system support by integrating a DVS scheduler and a feedback controller within the earliest-deadline-first (EDF) scheduling algorithm. Each task is divided into two portions. The objective within the first portion is to exploit frequency scaling for the average execution time. Static and dynamic slack is accumulated for each task with slackpassing and preemption handling schemes. The objective within the second portion is to meet the hard real-time deadline requirements up to the worst-case execution time following a lastchance approach. Feedback control techniques make the system capable of selecting the right frequency and voltage settings for the first portion, as well as guaranteeing hard real-time requirements for the overall task. A feedback control model is given to describe our feedback DVS scheduler, which is used to analyze the system's stability. Simulation experiments demonstrate the ability of our algorithm to save up to 29% more energy than previous work for task sets with different dynamic workload characteristics.

show abstract

Section: Introductionmentioning

confidence: 94%

Feedback EDF Scheduling of Real-Time Tasks Exploiting Dynamic Voltage Scaling

Zhu

Mueller

2005

Real-Time Syst

View full text Add to dashboard Cite

show abstract

“…The key idea is to schedule so as to "squeeze out the idle time" in rate-based applications. Several researchers have proposed voltage schedulers for general purpose systems [7,11,28,24]. Lebeck et al [17] explore power-aware page allocation in order to make a more efficient use of memory chips supporting multiple power states, such as the Rambus DRAM chips.…”

Section: Related Workmentioning

confidence: 99%

Energy efficiency through burstiness

Papathanasiou

Scott

2003

Proceedings DARPA Information Survivability Conference and Exposition McSa-03

View full text Add to dashboard Cite

show abstract

“…This control of clock speed can be done by the Operating System Scheduler. Such dynamic speed setting policies have been evaluated by trace-driven simulations on Unix workstations in [5], [6]. Some DVS algorithms for interval-based voltage schedulers have been analyzed with simulation results in [7].…”

Section: Dynamic Voltage Schedulingmentioning

confidence: 99%

Energy efficient software through dynamic voltage scheduling

Konduri

Goodman²,

Chandrakasan³

ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349)

View full text Add to dashboard Cite

The energy usage of computer systems is becoming important, especially for portable battery-operated applications and embedded systems. A significant reduction in the energy consumption of a program can be achieved via code optimizations that transform the code to take advantage of the Instruction Set Architecture (ISA) of the target processor. These code optimizations result in significantly shorter execution times of the software which in turn allow the operating frequency of the processor to be reduced, while maintaining the same throughput as the conventionally coded application. This reduction in operating frequency allows dynamic voltage scheduling to be applied to the processor, which results in energy reduction. This work describes how the operating frequency and the supply voltage can be changed on a low power microprocessor. The examples used show that over an order of magnitude reduction in the energy consumption is possible by using the aforementioned techniques.

show abstract

Comparing algorithm for dynamic speed-setting of a low-power CPU

Cited by 343 publications

References 3 publications

Feedback EDF Scheduling of Real-Time Tasks Exploiting Dynamic Voltage Scaling

Feedback EDF Scheduling of Real-Time Tasks Exploiting Dynamic Voltage Scaling

Energy efficiency through burstiness

Energy efficient software through dynamic voltage scheduling

Contact Info

Product

Resources

About