Application-Aware Power Management

This paper presents our approach for application-aware power management. We combine continuous monitoring of critical workload indicators, online power and performance model usage and timely p-state control to realize application-aware power management. We present two new power management solutions enabled by our methodology: PerformanceMaximizer (PM) finds the best possible performance under specified power constraints and PowerSave (PS) saves energy while keeping performance above specified requirements. We evaluate both using the SPEC-CPU2000 suite on a Pentium M platform discussing implications of workload characteristics and benefits of being workload-aware

[1]  Margaret Martonosi,et al.  An Analysis of Efficient Multi-Core Global Power Management Policies: Maximizing Performance for a Given Power Budget , 2006, 2006 39th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'06).

[2]  Gilberto Contreras,et al.  Power prediction for Intel XScale processors using performance monitoring unit events , 2005 .

[3]  Karthick Rajamani,et al.  IBM Research Report Online Power and Performance Estimation for Dynamic Power Management , 2006 .

[4]  Lizy Kurian John,et al.  Runtime identification of microprocessor energy saving opportunities , 2005, ISLPED '05. Proceedings of the 2005 International Symposium on Low Power Electronics and Design, 2005..

[5]  Benjamin C. Lee,et al.  Statistically Rigorous Regression Modeling for the Microprocessor Design Space , 2006 .

[6]  S. Naffziger,et al.  Power and temperature control on a 90-nm Itanium family processor , 2006, IEEE Journal of Solid-State Circuits.

[7]  Frank Bellosa,et al.  The benefits of event: driven energy accounting in power-sensitive systems , 2000, ACM SIGOPS European Workshop.

[8]  Alan Jay Smith,et al.  Operating System Modifications for Task-Based Speed and Voltage , 2003, MobiSys '03.

[9]  Margaret Martonosi,et al.  A dynamic compilation framework for controlling microprocessor energy and performance , 2005, 38th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'05).

[10]  Karthick Rajamani,et al.  A performance-conserving approach for reducing peak power consumption in server systems , 2005, ICS '05.

[11]  S. Naffziger,et al.  Power and temperature control on a 90nm Itanium/sup /spl reg//-family processor , 2005, ISSCC. 2005 IEEE International Digest of Technical Papers. Solid-State Circuits Conference, 2005..

[12]  Ramakrishna Kotla,et al.  Scheduling processor voltage and frequency in server and cluster systems , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[13]  Margaret Martonosi,et al.  Power prediction for Intel XScale/spl reg/ processors using performance monitoring unit events , 2005, ISLPED '05. Proceedings of the 2005 International Symposium on Low Power Electronics and Design, 2005..

[14]  Krisztián Flautner,et al.  Vertigo: Automatic Performance-Setting for Linux , 2002, OSDI.

[15]  Frank Bellosa,et al.  Process cruise control: event-driven clock scaling for dynamic power management , 2002, CASES '02.