Browse > Article
http://dx.doi.org/10.5207/JIEIE.2008.22.4.093

Dynamic Voltage Scaling based on Workload of Application for Embedded Processor  

Wang, Hong-Moon (성균관대학교 전자전기컴퓨터공학과)
Kim, Jong-Tae (성균관대학교 정보통신공학부)
Publication Information
Journal of the Korean Institute of Illuminating and Electrical Installation Engineers / v.22, no.4, 2008 , pp. 93-99 More about this Journal
Abstract
Portable devices generally have limited energy sources, so there is a need to minimize the power consumption of processor using energy conservation methods. One of the most common energy conservation methods is dynamic voltage scaling (DVS). In this paper, we propose a new DVS algorithm which uses workload of application to determine frequency and voltage of processors. The posed DVS algorithm consists of DVS module in kernel and specified function in application. The DVS module monitors the processor utilization and changes frequency and voltage periodically. The other part monitors workload of application. With these two procedures, the processor can change the performance level to meet their deadline while consuming less energy. We implemented the proposed DVS algorithm on PXA270 processor with Linux 2.6 kernel.
Keywords
Dynamic voltage scaling; Workload;
Citations & Related Records
연도 인용수 순위
  • Reference
1 T. Ishihara and H. Yasuura, "Voltage scheduling problem for dynamically variable voltage processors", Proceedings of the International Symposium on Low Power Electronics and Design, Aug. 1998
2 J. Pouwelse, K. Langendoen and H. Sips, "Dynamic voltage scaling on a low-power microprocessor", International Conference on Mobile Computing and Networking, 2001
3 Transmeta Corporation, "LongRun2 technologies", http://www.transmeta.com/tech/longrun2.html, visited on 19/9/2007
4 Intel Corporation, "Enhanced intel speedstep technology", http://www.intel.com/support/processors/mobile/pentium4/sb/CS-007499.htm
5 "Intel PXA270 processor electrical, mechanical and thermal specification", data sheet, Intel
6 K. Flautner and T. Mudge, "Vertigo: automatic performance-setting for linux", Proceedings 5th Symposium on Operating Systems Design and Implementation, Boston, 2002
7 K. Govil, E. Chan, and H. Wasserman, "Comparing algorithms for dynamic speed-setting of a low-power CPU", Proceedings the First International Conference on Mobile Computing and Networking, California, 1995