Power: A First Class Design Constraint for Future Architectures
- 17 Citations
- 371 Downloads
Abstract
In many mobile and embedded environments power is already the leading design constraint. This paper argues that power will also be a limiting factor in general purpose high-performance computers too. It should therefore be considered a “first class” design constraint on a par with performance. A corollary of this view is that the impact of architectural design decisions on power consumption must be considered early in the design cycle at the same time that their performance impact is considered. In this paper we summarize the key equations governing power and performance, and use them to illustrate some simple architectural ideas for power savings. The paper then presents two contrasting research directions where power is important. We conclude with a discussion of the tools needed to conduct research into architecture-power trade-offs.
Keywords
Power Consumption Computer Architecture Power Saving Gray Code Reduce Power ConsumptionPreview
Unable to display preview. Download preview PDF.
References
- [1]D. Singh and V. Tiwari. Power Challenges in the internet World. Cool Chips Tutorial: An Industrial Perspective on Low Power Processor Design, Eds. T. Mudge, S. Manne, D. Grunwald, held in conjunction with MICRO 32, Haifa Israel, Nov. 1999, pp.8–15. (http://www.eecs.umich.edu/~tnm/cool.html)
- [2]K. Wilcox and S. Manne. Alpha processors: A history of power issues and a look to the future. Cool Chips Tutorial: An Industrial Perspective on Low Power Processor Design, Eds. T. Mudge, S. Manne, D. Grunwald, held in conjunction with MICRO 32, Haifa, Israel, Nov. 1999, pp.16–37. (http://www.eecs.umich.edu/~tnm/cool.html)
- [4]R. Gonzalez and M. Horowitz. Energy dissipation in general purpose microprocessors. IEEE Jour. of Solid-State Circuits, Sep. 1996, pp. 1277–1284.Google Scholar
- [5]S. Furber, J. Garside, and S. Temple. Power Saving Features in Amulet2e. Power-Driven Microarchitecure Workshop, Eds. T. Mudge, S. Manne, D. Grunwald, held in conjunction with ISCA 98, Barcelona, Spain, June 1998. (http://www.cs.colorado.edu/~grunwald/LowPowerWorkshop/agenda.html)
- [6]S. Moore, et al. Self Calibrating Clocks for Globally Asynchronous Locally Synchronous Systems. Int. Conf. on Computer Design, Austin, Texas, Sep. 2000.Google Scholar
- [7]S. Manne, A. Klauser and D. Grunwald. Pipeline gating: Speculation control for energy reduction. Proc. 25th Int. Symp. Computer Architecture, Barcelona, Spain, June 1998, pp. 132–141.Google Scholar
- [8]M. Johnson, M. Gupta and W. Mangione-Smith. Filtering memory references to increase energy efficiency. IEEE Trans. on Computers, vol. 49, no. 1, Jan. 2000, pp. 1–15.CrossRefGoogle Scholar
- [9]A. Park, M. Farrens and G. Tyson,. Modifying VM hardware to reduce address pin requirements. Proc. 25th Int. Symp. Computer Architecture, Portland, Oregon, Dec. 1992, pp. 1–4.Google Scholar
- [10]L. Benini, et al. Address bus encoding techniques for system-level power optimization. Proc. 1998 Design Automation and Test in Europe (DATE’ 98), pp. 861–866.Google Scholar
- [11]C. Lefurgy, E. Piccininni, and T. Mudge. Reducing code size with run-time decompression. Proc. 6th Int. Symp. on High-Performance Computer Architecture, Jan. 2000, pp. 218–227.Google Scholar
- [12]T. Pering, T. Burd, and R. Brodersen, Voltage scheduling in the lpARM microprocessor System, Proc. 2000 Int. Symp. on Low Power Electronics and Design, July 2000.Google Scholar
- [13]G. Cai and C. Lim. Architectural level power/performance optimization and dynamic power estimation. Cool Chips Tutorial: An Industrial Perspective on Low Power Processor Design, Eds. T. Mudge, S. Manne, D. Grunwald, held in conjunction with MICRO 32, Haifa Israel, Nov. 1999, pp.90–113. (http://www.eecs.umich.edu/~tnm/cool.html)
- [14]D. Brooks, V. Tiwari, and M. Martonosi. Wattch: A framework for architectural-level power analysis and optimizations. Proc. 27th Int. Symp. Computer Architecture, Vancouver, Canada, pp. 83–94.Google Scholar
- [15]N. Vijaykrishnan, et al. Energy-driven integrated hardware-software optimizations using SimplePower. Proc. 27th Int. Symp. Computer Architecture, Vancouver, British Columbia, Canada, June 2000, pp. 95–106.Google Scholar
- [16]D. Burger and T. Austin. The SimpleScalar toolset, version 2.0. Tech Rept. Computer Science Dept., Univ. Wisconsin, June 1997. (see also http://www.simplescalar.org)