Integrated CPU Cache Power Management in Multiple Clock Domain Processors

  • Nevine AbouGhazaleh
  • Bruce Childers
  • Daniel Mossé
  • Rami Melhem
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4917)

Abstract

Multiple clock domain (MCD) chip design addresses the problem of increasing clock skew in different chip units. Importantly, MCD design offers an opportunity for fine grain power/energy management of the components in each clock domain with dynamic voltage scaling (DVS). In this paper, we propose and evaluate a novel integrated DVS approach to synergistically manage the energy of chip components in different clock domains. We focus on embedded processors where core and L2 cache domains are the major energy consumers. We propose a policy that adapts clock speed and voltage in both domains based on each domain’s workload and the workload experienced by the other domain. In our approach, the DVS policy detects and accounts for the effect of inter-domain interactions. Based on the interaction between the two domains, we select an appropriate clock speed and voltage that optimizes the energy of the entire chip. For the Mibench benchmarks, our policy achieves an average improvement over no-power-management of 15.5% in energy-delay product and 19% in energy savings. In comparison to a traditional DVS policy for MCD design that manages domains independently, our policy achieves an 3.5% average improvement in energy-delay and 4% less energy, with a negligible 1% decrease in performance. We also show that an integrated DVS policy for MCD design with two domains is more energy efficient for simple embedded processors than high-end ones.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    National Semiconductor, PowerWise Technology (2007), http://www.national.com/appinfo/power/powerwise.html
  2. 2.
    Magklis, G., Semeraro, G., Albonesi, D.H., Dropsho, S.G., Dwarkadas, S., Scott, M.L.: Dynamic Frequency and Voltage Scaling for a Multiple-Clock-Domain Microprocessor. IEEE Micro 23(6), 62–68 (2003)CrossRefGoogle Scholar
  3. 3.
    Semeraro, G., Albonesi, D.H., Dropsho, S.G., Magklis, G., Dwarkadas, S., Scott, M.L.: Dynamic frequency and voltage control for a multiple clock domain microarchitecture. In: MICRO 1935. Proc Intl Symp on Microarchitecture, pp. 356–367 (2002)Google Scholar
  4. 4.
    Iyer, A., Marculescu, D.: Power and performance evaluation of globally asynchronous locally synchronous processors. In: ISCA 2002. Proc Intl Symp on Computer architecture, pp. 158–168 (2002)Google Scholar
  5. 5.
    Magklis, G., Scott, M.L., Semeraro, G., Albonesi, D.H., Dropsho, S.: Profile-based dynamic voltage and frequency scaling for a multiple clock domain microprocessor. In: ISCA 2003. Proc Intl Symp on Computer Architecture, pp. 14–27 (2003)Google Scholar
  6. 6.
    Wu, Q., Juang, P., Martonosi, M., Clark, D.W.: Formal online methods for voltage/frequency control in multiple clock domain microprocessors. In: ASPLOS-XI. Proc Intl Conf on Architectural support for programming languages and operating systems, pp. 248–259 (2004)Google Scholar
  7. 7.
    Ben Naser, M., Moritz, C.A.: A Step-by-Step Design and Analysis of Low Power Caches for Embedded Processors (2005), http://www.lems.brown.edu/iris/BARC2005/Webpage/BARCpresentations/ben-naser.pdf
  8. 8.
    Kaxiras, S., Hu, Z., Martonosi, M.: Cache decay: exploiting generational behavior to reduce cache leakage power. In: ISCA 2001. Proc Intl Symp on Computer Architecture, pp. 240–251 (2001)Google Scholar
  9. 9.
    Zhu, Y., Albonesi, D.H., Buyuktosunoglu, A.: A High Performance, Energy Efficient GALS Processor Microarchitecture with Reduced Implementation Complexity. In: ISPASS 2005. Proc Intl Symp on Performance Analysis of Systems and Software (2005)Google Scholar
  10. 10.
    SimpleScalar/ARM. SimpleScalar-Arm Version 4.0 Test Releases, http://www.simplescalar.com/v4test.html/
  11. 11.
    Intel Embedded products. High-Performance Energy-Efficient Processors for Embedded Market Segments (2006), http://www.intel.com/design/embedded/downloads/315336.pdf
  12. 12.
    Pennanen, J.: Optimizing the Power for Multiple Voltage Domains. Spring Processor Forum, Japan (2006)Google Scholar
  13. 13.
    Rusu, C., AbouGhazaleh, N., Ferreria, A., Xu, R., Childers, B., Melhem, R., Mossé, D.: Integrated CPU and L2 cache Frequency/Voltage Scaling using Supervised Learning. In: Workshop on Statistical and Machine learning approaches applied to ARchitectures and compilation (SMART) (2007)Google Scholar
  14. 14.
    AbouGhazaleh, N., Ferreria, A., Rusu, C., Xu, R., Childers, B., Melhem, R., Mossé, D.: Integrated CPU and L2 cache Voltage Scaling using Supervised Learning. In: LCTES 2007. Proc. of ACM SIGPLAN on Language, compiler, and tool for embedded systems (2007)Google Scholar
  15. 15.
    Wu, Q., Juang, P., Martonosi, M., Clark, D.W.: Voltage and Frequency Control With Adaptive Reaction Time in MCD Processors. In: HPCA 2005: Proc Intl Symp on High-Performance Computer Architecture, pp. 178–189 (2005)Google Scholar
  16. 16.
    Oliver, J., Rao, R., Sultana, P., Crandall, J., Czernikowski, E., Jones IV, L.W., Franklin, D., Akella, V., Chong, F.T.: Synchroscalar: A Multiple Clock Domain, Power-Aware, Tile-Based Embedded Processor. In: ISCA 2004. Proc Intl Symp on Computer Architecture (2004)Google Scholar
  17. 17.
    Juang, P., Wu, Q., Peh, L.S., Martonosi, M., Clark, D.W.: Coordinated, distributed, formal energy management of chip multiprocessors. In: ISLPED 2005: Proc Intl Symp on Low Power Electronics and Design, pp. 127–130 (2005)Google Scholar
  18. 18.
    Lopez, S., Dropsho, S., Albonesi, D., Garnica, O., Lanchares, J.: Dynamic Capacity-Speed Tradeoffs in SMT Processor Caches. In: High Performance Embedded Architecure and Compilation (HiPEAC) (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Nevine AbouGhazaleh
    • 1
  • Bruce Childers
    • 1
  • Daniel Mossé
    • 1
  • Rami Melhem
    • 1
  1. 1.Department of Computer ScienceUniversity of Pittsburgh 

Personalised recommendations