Analysis of dynamic power management on multi-core processors

ABSTRACT

Power management of multi-core processors is extremely important because it allows power/energy savings when all cores are not used. OS directed power management according to ACPI (Advanced Power and Configurations Interface) specifications is the common approach that industry has adopted for this purpose. While operating systems are capable of such power management, heuristics for effectively managing the power are still evolving. The granularity at which the cores are slowed down/turned off should be designed considering the phase behavior of the workloads. Using 3-D, video creation, office and e-learning applications from the SYSmark benchmark suite, we study the challenges in power management of a multi-core processor such as the AMD Quad-Core Opteron" and Phenom". We unveil effects of the idle core frequency on the performance and power of the active cores. We adjust the idle core frequency to have the least detrimental effect on the active core performance. We present optimized hardware and operating system configurations that reduce average active power by 30% while reducing performance by an average of less than 3%. We also present complete system measurements and power breakdown between the various systems components using the SYSmark and SPEC CPU workloads. It is observed that the processor core and the disk consume the most power, with core having the highest variability.

REFERENCES

• 1: Advanced Configuration & Power Interface. http://www.acpi.info. November 2007.
• 2: BIOS and Kernel Developer's Guide for AMD Family 10h Processor. http://www.amd.com. November 2007.
• 3: Bircher, W. L. Measurement Based Power Phase Analysis of a Commercial Workload. Workshop on Unique Chips and Systems (Austin, Texas, March 2006).
• 4: W. L. Bircher , L. K. John, Power phase variation in a commercial server workload, Proceedings of the 2006 international symposium on Low power electronics and design, October 04-06, 2006, Tegernsee, Bavaria, Germany [doi>10.1145/1165573.1165656]
• 5: Bohrer, P., Elnozahy, E. N., Keller, T., Kistler, M., Lefurgy, C., McDowell, C., and Rajamony, R. The Case for Power Management in Web Servers. IBM Research, Austin TX 78758, USA. www.research.ibm.com/arl
• 6: Xiaobo Fan , Wolf-Dietrich Weber , Luiz Andre Barroso, Power provisioning for a warehouse-sized computer, Proceedings of the 34th annual international symposium on Computer architecture, June 09-13, 2007, San Diego, California, USA
• 7: Xizhou Feng , Rong Ge , Kirk W. Cameron, Power and Energy Profiling of Scientific Applications on Distributed Systems, Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Papers, p.34, April 04-08, 2005 [doi>10.1109/IPDPS.2005.346]
• 8: Hanson, H., Keckler, S.W. Power and Performance Optimization: A Case Study with the Pentium M Processor. The Austin Center for Advanced Studies Conference (February 2006).
• 9: Hanson, H., Keckler, S.W., Rajamani, K., Ghiasi, S., Rawson, F., and Rubio, J. Power, Performance, and Thermal Management for High-Performance Systems. 3rd Workshop on High-Performance, Power-Aware Computing, held in conjunction with 21st Annual International Parallel & Distributed Processing Symposium (Long Beach, California, March 2007).
• 10: Canturk Isci , Alper Buyuktosunoglu , Chen-Yong Cher , Pradip Bose , Margaret Martonosi, An Analysis of Efficient Multi-Core Global Power Management Policies: Maximizing Performance for a Given Power Budget, Proceedings of the 39th Annual IEEE/ACM International Symposium on Microarchitecture, p.347-358, December 09-13, 2006 [doi>10.1109/MICRO.2006.8]
• 11: Kotla, R., Devgan, A., Ghiasi, S., Keller, T., and Rawson, F. Characterizing the Impact of Different Memory--Intensity Levels. IEEE 7th Annual Workshop on Workload Characterization (Austin, Texas, October 2004).
• 12: J. Lau , S. Schoemackers , B. Calder, Structures for phase classification, Proceedings of the 2004 IEEE International Symposium on Performance Analysis of Systems and Software, p.57-67, March 10-12, 2004
• 13: Li, J. and Martinez, J. Dynamic Power--Performance Adaptation of Parallel Computation on Chip Multiprocessors. The 12th International Symposium on High--Performance Computer Architecture (Austin, Texas, February 2006).
• 14: Yingmin Li , David Brooks , Zhigang Hu , Kevin Skadron, Performance, Energy, and Thermal Considerations for SMT and CMP Architectures, Proceedings of the 11th International Symposium on High-Performance Computer Architecture, p.71-82, February 12-16, 2005 [doi>10.1109/HPCA.2005.25]
• 15: Mahesri, A. and Vardhan, V. Power Consumption Breakdown on a Modern Laptop. Workshop on Power Aware Computing Systems, 37th International Symposium on Microarchitecture (Portland, Oregon, December 2004).
• 16: Processor Power Management in Windows Vista and Windows Server 2008. http://www.microsoft.com . November 2007.
• 17: National Instruments Data Acquisition Hardware. http://www.ni.com/dataacquisition/. April 2008.
• 18: Rajamani, K., Hanson, H., Rubio, J., Ghiasi, S., and Rawson, F. Application-Aware Power Management. IEEE International Symposium on Workload Characterization pages 39--48 (San Jose, California, October 2006).
• 19: Inside Barcelona: AMD's Next Generation http://www.realworldtech.com . November 2007.
• 20: Siddah, S., Pallipadi, V., and Van de Ven, A. Getting Maximum Mileage Out of Tickless. The Linux Symposium. (Ottawa, Canada, June 2007).

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.0 GENERAL

General Terms:
Design, Measurement, Performance

Keywords:
ACPI, multi-core, operating system, performance, power management