Abstract
The ultimate goal of a computer system is to satisfy its users. The success of architectural or system-level optimizations depends largely on having accurate metrics for user satisfaction. We propose to derive such metrics from information that is "close to flesh" and apparent to the user rather than from information that is "close to metal" and hidden from the user. We describe and evaluate PICSEL, a dynamic voltage and frequency scaling (DVFS) technique that uses measurements of variations in the rate of change of a computer's video output to estimate user-perceived performance. Our adaptive algorithms, one conservative and one aggressive, use these estimates to dramatically reduce operating frequencies and voltages for graphically-intensive applications while maintaining performance at a satisfactory level for the user. We evaluate PICSEL through user studies conducted on a Pentium M laptop running Windows XP. Experiments performed with 20 users executing three applications indicate that the measured laptop power can be reduced by up to 12.1%, averaged across all of our users and applications, compared to the default Windows XP DVFS policy. User studies revealed that the difference in overall user satisfaction between the more aggressive version of PICSEL and Windows DVFS were statistically insignificant, whereas the conservative version of PICSEL actually improved user satisfaction when compared to Windows DVFS.
Supplemental Material
Available for Download
Supplemental material for PICSEL: measuring user-perceived performance to control dynamic frequency scaling
- Brock, B. and Rajamani, K. 2003. Dynamic Power Management for Embedded Systems. In Proc. of the IEEE SOC Conf. (SOC'03).Google Scholar
- Choi, K., Soma, R., and Pedram, M. 2004. Dynamic Voltage and Frequency Scaling based on Workload Decomposition. In Proc. of the 2004 Int. Symp. on Low Power Electronics and Design (ISPLED'04), 174--179. Google Scholar
Digital Library
- Claypool, M., Claypool, K., and Damaa, F. 2006. The Effects of Frame Rate and Resolution on Users Playing First-person Shooter Games. In Proc. of ACM/SPIE Multimedia Computing and Networking (MMCN'06).Google Scholar
- Dhar, S., Maksimovic, D., and Kranzen, B. 2002. Closed-Loop Adaptive Voltage Scaling Controller for Standard Cell ASICs. In Proc. of the 2005 Int. Symp. on Low Power Electronics and Design (ISPLED'05.), 103--107. Google Scholar
Digital Library
- Ernst, D., Kim, N.S., Das, S., Pant, S., Rao, R., Pham, T., Ziesler, C., Blaauw, D., Austin, T., Flautner, K., and Mudge, T. 2003. Razor: A Low-Power Pipeline Based on Circuit-Level Timing Speculation. In Proc. of the 36th ACM/IEEE Int. Symp. on Microarchitecture (MICRO-36), 7--18. Google Scholar
Digital Library
- Fei, Y., Zhong, L., and Jha, N.K. 2004. An Energy-aware Framework for Coordinated Dynamic Software Management in Mobile Computers. In Proc. of the IEEE Computer Society's Int. Symp. on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems (MASCOTS'04), 306--317. Google Scholar
Digital Library
- Flautner, K. and Mudge, T. 2002. Vertigo: Automatic Performance-Setting for Linux. ACM SIGOPS Operating Systems Review 36, SI (Winter 2002), 105--116. Google Scholar
Digital Library
- Ghinea, G. and Thomas, J.P. 2005. Quality of Perception: User Quality of Service in Multimedia Presentations. IEEE T. Multimedia 7, 4 (Aug. 2005), 786--789. Google Scholar
Digital Library
- Gochman, S. Ronen, R., Anati, I., Berkovits, A., Kurts, T., Naveh, A., Saeed, A., Sperber, Z., and Valentine, R.C. 2003. The Intel Pentium M Processor: Microarchitecture and Performance. Intel Technology J. 7, 2 (May 2003), 21--36.Google Scholar
- Gulliver, S.R. and Ghinea, G. 2007. The Perceptual and Attentive Impact of Delay and Jitter in Multimedia Delivery. IEEE T. Broadcast 53, 2 (June 2007), 449--458.Google Scholar
- Gupta, A., Lin, B., and Dinda, P.A. 2004. Measuring and Understanding User Comfort with Resource Borrowing. In Proc. of the 13th IEEE Int. Symp. on High Performance Distributed Computing (HPDC'04), 214--224. Google Scholar
Digital Library
- Gurun, S. and Krintz, C. 2005. AutoDVS: an Automatic, General-purpose, Dynamic Clock Scheduling System for Hand-held Devices. In Proc. of the 5th ACM Int. Conf. on Embedded Software (EMSOFT'05), 218--226. Google Scholar
Digital Library
- Gurun, S. and Krintz, C. 2006. A Run-Time, Feedback-Based Energy Estimation Model for Embedded Devices. In Proc. of the Int. Conf. on Hardware/Software Codesign and System Synthesis. (CODES+ISSS'06). Google Scholar
Digital Library
- Lin, B. and Dinda, P.A. 2006. Towards Scheduling Virtual Machines Based on Direct User Input. In Proc. of the 1st Int. Workshop on Virtualization Technology in Distributed Computing (Tampa, FL, USA, November 17, 2006). VTDC'06. See also technical report NWU-EECS-06-07, Northwestern University, EECS. Google Scholar
Digital Library
- Lorch, J. and Smith, A. 2003. Using User Interface Event Information in Dynamic Voltage Scaling Algorithms. In Proc. of the IEEE Computer Society's Int. Symp. on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems (MASCOTS'03), 46--55.Google Scholar
- Mallik, A., Lin, B. Memik, G., Dinda, P.A., and Dick, R.P. 2006. User-Driven Frequency Scaling. IEEE Computer Architecture Letters 5, 2 (July 2006), 16. A summary of this work also appeared in ACM SIGMETRICS 2007. Google Scholar
Digital Library
- Microsoft Corporation. 2003. Windows Native Processor Performance Control. Windows Platform Design Notes (May 2003). Retrieved from http://www.microsoft.com/whdc/system/pnppwr/powermgmt/ProcPerfCtrl.mspx.Google Scholar
- Podien, W. CPUCool. Retrieved from http://www.cpu-cool.de/index.html.Google Scholar
- Ranganathan, P., Geelhoed, E., Manahan, M, and Nicholas, K. 2006. Energy-Aware User Interfaces and Energy-Adaptive Displays. Computer 39, 3 (March 2006), 31--38. Google Scholar
Digital Library
- Wei, J. Foxton Technology Pushes Processor Frequency, Application Performance. [email protected] Mag. (July 2007). Retrieved from http://www.intel.com/technology/magazine/computing/foxton-technology-0905.htm.Google Scholar
- Wijesekera, D., Srivastava, J., Nerode, A., Forrsti, M. 1999. Experimental Evaluation of Loss Perception in Continuous Media. Multimedia Systems 7, 6 (Nov. 1999), 486--499. Google Scholar
Digital Library
- Wu, Q., Martonosi, M., Clark, D.W., Reddi, V.J., Connors, D., Wu, Y., Lee, J., and Brooks, D. 2005. Dynamic Compilation Framework for Controlling Microprocessor Energy and Performance. In Proc. of the 38th IEEE/ACM Int. Symp. on Microarchitecture (MICRO-38), 271--282. Google Scholar
Digital Library
- Xu, R., Moss, D., and Melhem, R. 2005. Minimizing Expected Energy in Real-time Embedded Systems. In Proc. of the 5th ACM Int. Conf. on Embedded Software (EMSOFT'05), 251--254. Google Scholar
Digital Library
- Yan, L., Zhong, L., and Jha, N.K. 2005. User-perceived Latency-based Dynamic Voltage Scaling for Interactive Applications. In Proc. of ACM/IEEE Design Automation Conf. (DAC'05), 624--627. Google Scholar
Digital Library
Index Terms
PICSEL: measuring user-perceived performance to control dynamic frequency scaling
Recommendations
PICSEL: measuring user-perceived performance to control dynamic frequency scaling
ASPLOS '08The ultimate goal of a computer system is to satisfy its users. The success of architectural or system-level optimizations depends largely on having accurate metrics for user satisfaction. We propose to derive such metrics from information that is "...
PICSEL: measuring user-perceived performance to control dynamic frequency scaling
ASPLOS XIII: Proceedings of the 13th international conference on Architectural support for programming languages and operating systemsThe ultimate goal of a computer system is to satisfy its users. The success of architectural or system-level optimizations depends largely on having accurate metrics for user satisfaction. We propose to derive such metrics from information that is "...
PICSEL: measuring user-perceived performance to control dynamic frequency scaling
ASPLOS '08The ultimate goal of a computer system is to satisfy its users. The success of architectural or system-level optimizations depends largely on having accurate metrics for user satisfaction. We propose to derive such metrics from information that is "...







Comments