Advertisement

Micro-Architecture Design and Control Speculation for Energy Reduction

  • Dirk Grunwald
Part of the Series in Computer Science book series (SCS)

Abstract

Conventional wisdom states that the best way to design an energy-efficient microprocessor is to design it for high performance, since a high performance processor will complete a task quicker than an energy-conscious design. However, our research group has found ways to reduce energy without impacting performance by controlling the amount of speculation used by the processor in its quest for performance.

Keywords

Critical Path Register File Confidence Estimator Confidence Estimation Execution Unit 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D. Carmean. Power, a perspective from the desktop. In Kool Chips Workshop, invited talk. ACM, Dec 2000.Google Scholar
  2. [2]
    J. Casmira and D. Grunwald. Dynamic instruction scheduling slack. In Kool Chips Workshop. ACM, Dec 2000.Google Scholar
  3. [3]
    A. Chandrakasan and R. Brodersen (Eds.). Low-Power CMOS Design. IEEE Press, 1998.Google Scholar
  4. [4]
    A. P. Chandrakasan, S. Sheng, and R. W. Brodersen. Low-power cmos digital design. IEEE Journal of Solid-State Circuits, 27 (4): 473–484, 1992.CrossRefGoogle Scholar
  5. [5]
    Intel Corporation. Pentium 4 Processor Datasheet. http://developer.intel.com/design/Pentium4/datashts/. Google Scholar
  6. [6]
    A. Dhodapkar, C. Lim, G. Cai, and W. Daasch. Tempest: A thermal enabled multi-model power/performance estimator. In Workshop on Power Aware Computer Sytstems. ACM, Nov 2000.Google Scholar
  7. [7]
    D. Folegnani and A. Gonzalez. Energy-effective issue logic. In Proc. of 28th. Int. Symposium on Computer Architecture, June 2001.Google Scholar
  8. [8]
    Richard Fromm, Stylianos Perissakis, Neal Cardwell, Christoforos Kozyrakis, Bruce McGaughy, and David Patterson. The Energy Efficiency of IRAM Architectures. Technical report, May 1997.Google Scholar
  9. [9]
    Soraya Ghiasi and Dirk Grunwald. A comparison of two architectural power models. In Workshop on Power Aware Computer Sytstems. ACM, Nov 2000.Google Scholar
  10. [10]
    Ricardo Gonzalez and Mark Horowitz. Energy Dissipation in General Purpose Microprocessors. IEEE Journal of Solid-State Circuits, 31 (9): 1277–1284, September 1996.CrossRefGoogle Scholar
  11. [11]
    Dirk Grunwald, Artur Klauser, Srilatha Manne, and Andrew Pleszkun. Confidence estimation for speculation control. In Proceedings 25th Annual Annual International Symposium on Computer Architecture,Barcelona, Spain, June 1998. ACM.Google Scholar
  12. [12]
    Steve Gunther and Intel Corp. Suresh Rajgopal. Personal communication.Google Scholar
  13. [13]
    Mutsunori Igarashi, Kimiyoshi Usami, Kazutaka Nogami, Fumihiro Minami, Yukio Kawasaki, Takahiro Aoki, Midori Takano, Chiharu Mizuno adn Takashi Ishikara, Masahiro Kanazawa, Shinji Sonoda, Makoto Ichida, and Naoyuki Hatanaka. Clustered voltage scaling techniques for low-power design. In IEEE Symposium on Low Power Electronics, 1997.Google Scholar
  14. [14]
    Erik Jacobsen, Eric Rotenberg, and J. E. Smith. Assigning confidence to conditional branch predictions. In Proceedings of the 29th Annual Inter- Google Scholar
  15. national Symposium on Microarchitecture,pages 142–152, Paris, France, December 2–4, 1996.Google Scholar
  16. [15]
    M.C. Johnson and K. Roy. Optimal selection of supply voltages and level conversions during data path scheduling under resource constraints. In Proceedings of the International Conference on Computer Design, 1996.Google Scholar
  17. [16]
    J. Kin, M. Gupta, and W. Mangione-Smith. The Filter Cache: An Energy Efficient Memory Structure. IEEE Micro, December 1997.Google Scholar
  18. [17]
    Artur Klauser, Abhijit Paithankar, and Dirk Grunwald. Selective eager execution on the polypath architecture. In Proceedings 25th Annual Annual International Symposium on Computer Architecture,Barcelona, Spain, June 1998. ACM.Google Scholar
  19. [18]
    U. Ko, P. T. Balsara, and A. K. Nanda. Energy optimization of multilevel processor cache architectures. In Proceedings of the International Symposium on Low Power Design, 1995.Google Scholar
  20. [19]
    Mikko Lipasti. Value Locality and Speculative Execution. PhD thesis, Carnegie Mellon University, April 1997.Google Scholar
  21. [20]
    Srilatha Manne, Artur Klauser, and Dirk Grunwald. Pipeline gating: Speculation control for energy reduction. In Proceedings 25th Annual Annual International Symposium on Computer Architecture,Barcelona, Spain, June 1998. ACM.Google Scholar
  22. [21]
    Srilatha Manne, Artur Klauser, and Dirk Grunwald. Branch prediction using selective branch inversion. In Proceedings of Parallel Architectures and Compilation Techniques PACT’99, Oct 1999.Google Scholar
  23. [22]
    J. Montanaro and et. al. A 160-MHz, 32-b, 0.5-W CMOS RISC Microprocessor. In Digital Technical Journal, volume 9. Digital Equipment Corporation, 1997.Google Scholar
  24. [23]
    M. Srivastava, A. Chandrakasan, and R. Broderen. Predictive system shutdown and other architectural techniques or energy efficient programmable computation. IEEE Transactions on Very Large Scale Integration Systems, 4 (1): 42–55, March 1996.Google Scholar
  25. [24]
    C. Su and A. Despain. Cache design trade-offs for power and performance optimization: A case study. In Proceedings of the International Symposium on Low Power Design, 1995.Google Scholar
  26. [25]
    Kimiyoshi Usami and Mark Horowitz. Clustered voltage scaling techniques for low-power design. In IEEE Symposium on Low Power Electronics, 1995.Google Scholar

Copyright information

© Springer Science+Business Media New York 2002

Authors and Affiliations

  • Dirk Grunwald
    • 1
  1. 1.Dept. of Computer ScienceUniversity of ColoradoBoulderUSA

Personalised recommendations