Co-optimization of Performance and Power in a Superscalar Processor Design

  • Yongxin Zhu
  • Weng-Fai Wong
  • Ştefan Andrei
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4097)


As process technology scales down, power wall starts to hinder improvements in processor performance. Performance optimization has to proceed under a power constraint. The co-optimization requires exploration into a huge design space containing both performance and power factors, whose size is over costly for extensive traditional simulations. This paper describes a unified model covering both performance and power. The model consists of workload parameters, architectural parameters plus corresponding power parameters with a good degree of accuracy compared with physical processors and simulators. We apply the model to the problem of co-optimizing the power and performance. Concrete insights into the tradeoffs of designs for performance and power are obtained in the process of co-optimization.


Power Constraint Dynamic Power Clock Frequency Very Large Scale Integration Leakage Power 
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.


  1. 1.
    Aloul, F.A., Hassoun, S., Sakallah, K.A., Blaauw, D.: Robust sat-based search algorithm for leakage power reduction. In: Proc. of the 12th Int’l Workshop on Integrated Circuit Design, Power and Timing Modeling, Optimization and Simulation, pp. 167–177. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  2. 2.
    Bergamaschi, R.N., Wang, Y.W.: State-based power analysis for systems-on-chip. In: Proc. of the 40th Int’l Design Automation Conference (DAC-40), June 2003, pp. 638–641 (2003)Google Scholar
  3. 3.
    Brooks, D., Bose, P., Schuster, S., Jacobson, H., Kudva, P., Buyuktosunoglu, A., Wellman, J., Zyuban, V., Gupta, M., Cook, P.: Power-aware microachitecture: Design and modeling challenges for next-generation microprocessors. Micro. IEEE 20(6), 26–44 (2000)CrossRefGoogle Scholar
  4. 4.
    Brooks, D., Tiwari, V., Martonosi, M.: Wattch: A framework for architectural-level power analysis and optimizations. In: Proc. of 27th Ann. Int’l Symp. Computer Architecture (ISCA), pp. 83–94. IEEE Computer Society Process, Los Alamitos, California (2000)CrossRefGoogle Scholar
  5. 5.
    Cai, G., Lim, C.: Architectural level power/performance optimization and dynamic power estimation. In: Cool Chips Tutorial Colocated with the 32nd Annual IEEE/ACM Int’l Symp. on Microarchitecture (MICRO-32) (November 1999)Google Scholar
  6. 6.
    Conte, T., Menezes, K., Sathaye, S., Toburen, M.: System-level power consumption modeling and tradeoff analysis techniques for superscalar processor design. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 8(2), 129–137 (2000)CrossRefGoogle Scholar
  7. 7.
    Khouri, K., Jha, N.: Leakage power analysis and reduction during behavioral synthesis. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 10(6), 876–885 (2002)CrossRefGoogle Scholar
  8. 8.
    Moreshet, T., Bahar, R.I.: Power-aware issue queue design for speculative instructions. In: Proc. of the 40th Int’l Design Automation Conference (DAC-40), June 2003, pp. 634–637 (2003)Google Scholar
  9. 9.
    Noonburg, D., Shen, J.: Theoretical modeling of superscalar processor performance. In: Proc. of 27th Annual IEEE/ACM Int’l Symposium on Microarchitecture (MICRO-27), pp. 53–62 (1994)Google Scholar
  10. 10.
    Pyun, Y., Park, C., Choi, S.: The effect of instruction window on the performance of superscalar processors. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences E81A(6), 1036–1044 (1998)Google Scholar
  11. 11.
    Srinivasan, V., Brooks, D., Gschwind, M., Bose, P., Zyuban, V., Strenski, P.N., Sylvester, P.G.E.: Optimizing pipelines for power and performance. In: Proc. of MICRO-35, pp. 333–344 (November 2002)Google Scholar
  12. 12.
    Sulstyo, J., Ha, D.S.: A new characterization method for delay and power dissipation of standard library cells. VLSI Design 15(3), 667–678 (2002)CrossRefGoogle Scholar
  13. 13.
    Sylvester, D., Jiang, W., Keutzer, K.: Bacpac - Berkeley Advanced Chip Performance Calculator (1998), Available online.
  14. 14.
    Sylvester, D., Keutzer, K.: Getting to the bottom of deep submicron. In: Proc. of Int’l Conference on CAD, pp. 203–211 (November 1998)Google Scholar
  15. 15.
    Zhu, Y., Wong, W.: Sensitivity analysis of a superscalar processor model. In: Proc. of the 7th Asia-Pacific Computer Systems Architectures Conference, Melbourne, Australia, pp. 109–118 (January 2002)Google Scholar
  16. 16.
    Zhu, Y., Wong, W., Andrei, S.: An integrated performance and power model for superscalar processor designs. In: Proc. of IEEE Asia South Pacific Design Automation Conference (ASP-DAC) 2005, Shanghai, China, pp. 948–951 (2005)Google Scholar
  17. 17.
    Zhu, Y., Wong, W., Koh, C.: A performance and power co-optimization approach for modern processors. In: Proc. of 5th Int’l Conference on Computer and Information Technology (CIT) 2005, Shanghai, China, pp. 822–828 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yongxin Zhu
    • 1
  • Weng-Fai Wong
    • 2
  • Ştefan Andrei
    • 2
  1. 1.School of MicroelectronicsShanghai Jiao Tong University 
  2. 2.School of ComputingNational University of Singapore 

Personalised recommendations