Anton Yrjönen
ABSTRACT
Dynamic Performance Scaling is highly efficient in reducing power consumption of computers. However, it causes a tradeoff between energy efficiency and performance if based on processor utilization history. In this paper we present an algorithm called PROPHET aimed at boosting load prediction used within dynamic performance scaling systems. PROPHET is a binary search-like speculative approach for determining current processing load and setting the performance level accordingly. PROPHET guarantees that performance degradation does not exceed a worst-case boundary value. A performance hit metric is defined and utilized for determining the maximum performance hit of the algorithm. PROPHET is applied to and tested in embedded multimedia device, as well as in a simulated environment. Test results on real device show 27% to 32% energy savings in a user-interactive use case with feasible performance. Comparison to existing energy-equal performance scaling algorithms shows up to 35% smaller performance hit on real device and even more in the simulated execution environment.
- V. Gutnik and A.P. Chandrakasan. Embedded Power Supply for Low-power DSP. In IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 5(4):425--435, Dec 1997. Google Scholar
Digital Library
- T.D. Burd, T.A. Pering, A.J. Stratakos and R.W. Brodersen. A dynamic voltage scaled microprocessor system. In IEEE Journal of Solid-State Circuits, 35(11):1571--1580, Nov 2000.Google ScholarCross Ref
- H. Aydin and Q. Yang. Energy -- Responsiveness Tradeoffs for Real-time Systems with Mixed Workload. In Proceedings of 10th IEEE Real-Time and Embedded Technology and Applications Symposium, pages 74--83. 25-28 May 2004. Google ScholarDigital Library
- M. Marinoni and G. Buttazzo. Balancing Energy vs. Performance in Processors with Discrete Voltage/Frequency Modes. In Proceedings of the 12th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, pages 294--304. 16-18 Aub 2006. Google ScholarDigital Library
- M. Hongisto and K. Kolehmainen. Dynamic Voltage Scaling Framework for Mobile Multimedia Systems. In Proceedings of the 4th IASTED International Conference on Communications, Internet and Information Technology (CIIT 2006), pages 136--142. 29 Nov - 1 Dec 2006, St Thomas, USVI, USA.Google Scholar
- L. Yan, L. Zhong, and N.K. Jha. User-perceived Latency Driven Voltage Scaling for Interactive Applications. In Proceedings of the 42nd Design Automation Conference, pages 624--627. 13-17 2005. Google ScholarDigital Library
- A. Sinha and A.P. Chandrakasan. Dynamic Voltage Scheduling Using Adaptive Filtering of Workload Traces. In Proceedings of the 14th International Conference on VLSI Design (VLSI'01), pages 221--226. 3-7 Jan 2001. Google ScholarDigital Library
- V. Venkatachalam and M. Franz. Power Reduction Techniques for Microprocessor Systems. ACM Computing Surveys, 37(3):195--237, Jun 2005. Google ScholarDigital Library
- D. Grunwald, P. Lewis, K. Farkas, C. B. Morrey III, and M. Neufeld. Policies for Dynamic Clock Scheduling. In Proceedings of the 4th Symposium On Operating Systems Design and Implementation (OSDI'00), pages 73--86, 2000. Google ScholarDigital Library
- J. Mao, C.G. Cassandras and Q. Zhao. Optimal Dynamic Voltage Scaling in Energy-Limited Nonpreemptive Systems with Real-Time Constraints In IEEE Transactions on Mobile Computing, 6(6):678--688, June 2007. Google ScholarDigital Library
- F. Zhang and S.T. Chanson. Processor Voltage Scheduling for Real-time Tasks with Non-preemptible Sections. In 23rd IEEE Real-Time Systems Symposium (RTSS 2002), pages 235--245. 3-5 Dec 2002. Google ScholarDigital Library
- H. Aydin, R. Melhem, D. Mosse, and P. Mejia-Alvarez. Dynamic and Aggressive Scheduling Techniques for Power-aware Real-time Systems. In Proceedings of the 22nd IEEE Real-Time Systems Symposium (RTSS 2001), pages 95--105. 3-6 Dec 2001. Google ScholarDigital Library
- P. Mejia-Alvarez, E. Levner and D. Mosse. Adaptive Scheduling Server for Power-Aware Real-time Tasks In ACM Transactions on Embedded Computing Systems., 3(2):284--306, May 2004. Google ScholarDigital Library
- T. Kanstrén, M. Hongisto and K. Kolehmainen. Integrating and Testing a System-Wide Feature in a Legacy System: An Experience Report. In Proceedings of the 11th European Conference on Software Maintenance and Reengineering, 21--23 Mar 2007, Amsterdam, Netherlands. Google ScholarDigital Library
Index Terms
- PROPHET: speculative load prediction algorithm for dynamic performance scaling
Recommendations
PEAK—a fast and effective performance tuning system via compiler optimization orchestration
Compile-time optimizations generally improve program performance. Nevertheless, degradations caused by individual compiler optimization techniques are to be expected. Feedback-directed optimization orchestration systems generate optimized code versions ...
Writing efficient programs: performance issues in an undergraduate CS curriculum
Performance is an essential aspect of many software systems, and it is important for programmers to understand performance issues. However, most undergraduate curricula do not explicitly cover performance issues---performance monitoring and profiling ...
Writing efficient programs: performance issues in an undergraduate CS curriculum
SIGCSE '04: Proceedings of the 35th SIGCSE technical symposium on Computer science educationPerformance is an essential aspect of many software systems, and it is important for programmers to understand performance issues. However, most undergraduate curricula do not explicitly cover performance issues---performance monitoring and profiling ...
Comments