ABSTRACT
We develop a theoretical foundation to characterize a novel methodology for low energy and high performance dsp for embedded computing. Computing elements are operated at a frequency higher than that permitted by a conventionally correct circuit design, enabling a trade-off between error that is deliberately introduced, and the energy consumed. Similar techniques considered previously were relevant to deeply scaled future technology generations. Our work extends this idea to be applicable to current-day designs through: (i) a mathematically rigorous foundation characterizing a tradeoff between energy consumed and the quality of solution, and (ii) a means of achieving this trade off through very aggressive voltage scaling beyond that of a conventionally designed circuit. Through our "cmos inspired" mathematical model, we show that our approach is better (by an exponential factor) than the conventional uniform voltage scaling approach for comparable computational speed or performance. We further establish through experimental study that a similar improvement by a factor of 3.4x to the snr over conventional voltage-scaled approaches can be achieved in the context of the ubiquitous discrete Fourier transform.
- V. Ananthashayana. Comments on 'Fourier analysis and signal processing by use of the mobius inversion formula' by I.S. Reed et. al. IEEE Transactions on Signal Processing, 40(3):676, Mar 1992.Google ScholarDigital Library
- G. Boudreaux-Bartels and T. Parks. Discrete Fourier transform using summation by parts. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 12, pages 1827--1830, apr 1987.Google ScholarCross Ref
- J. Chang and M. Pedram. Energy minimization using multiple supply voltages. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 5(4):436--443, Dec. 1997. Google ScholarDigital Library
- S. Cheemalavagu, P. Korkmaz, K. V. Palem, B. E. S. Akgul, and L. N. Chakrapani. A probabilistic CMOS switch and its realization by exploiting noise. In Proceedings of the IFIP International Conference on Very Large Scale Integration (VLSI-SoC), pages 452--457, 2005.Google Scholar
- D. Ernst, N. S. Kim, S. Das, S. Pant, T. Pham, R. Rao, C. Ziesler, D. Blaauw, T. Austin, and T. Mudge. Razor: A low-power pipeline based on circuit-level timing speculation. In Proceedings of the 36th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pages 7--18, October 2003. Google ScholarDigital Library
- J. George, B. Marr, B. E. S. Akgul, and K. Palem. Probabilistic arithmetic and energy efficient embedded signal processing. In Proceedings of the The IEEE/ACM International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, pages 158--168, 2006. Google ScholarDigital Library
- R. Hegde and N. R. Shanbhag. Soft digital signal processing. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 9(6):813--823, Dec. 2001. Google ScholarDigital Library
- M. Lamoureux. The Poorman's transform: approximating the Fourier transform without multiplication. IEEE Transactions on Signal Processing, 41(3):1413--1415, Mar 1993.Google ScholarDigital Library
- A. Manzak and C. Chaktrabarti. Variable voltage task scheduling algorithms for minimizing energy/power. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 11(2):270--276, Apr. 2003. Google ScholarDigital Library
- S. M. Martin, K. Flautner, T. Mudge, and D. Blaauw. Combined dynamic voltage scaling and adaptive body biasing for lower power microprocessors under dynamic workloads. In Proceedings of the International Conference on Computer Aided Design, November 2002. Google ScholarDigital Library
- T. Pering, T. Burd, and R. Brodersen. The simulation and evaluation of dynamic voltage scaling algorithms. In Proceedings of the International Symposium on Low Power Electronics and Design, pages 76--81, 1998. Google ScholarDigital Library
- N. Pippenger. Analysis of carry propagation in addition: An elementary approach. Technical report, University of British Columbia, Vancouver, BC, Canada, Canada, 2001. Google ScholarDigital Library
- I. Reed, D. Tufts, X. Yu, T. Truong, M.-T. Shih, and X. Yin. Fourier analysis and signal processing by use of the mobius inversion formula. IEEE Transactions on Acoustics, Speech, and Signal Processing, 38(3):458--470, Mar 1990.Google ScholarCross Ref
- B. Shim, S. R. Sridhara, and N. R. Shanbhag. Reliable low-power digital signal processing via reduced precision redundancy. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 12(5):497--510, May 2004. Google ScholarDigital Library
- J. M. Tour and D. K. James. Molecular electronic computing architectures: A review. In I. Goddard, W. A., D. W. Brenner, S. E. Lyshevski, and G. J. Iafrate, editors, Handbook of Nanoscience, Engineering and Technology, Second Edition, pages 5.1--5.28. CRC Press, New York, 2007.Google Scholar
- L. Wang and N. R. Shanbhag. Low-power filtering via adaptive error-cancellation. IEEE Transactions on Signal Processing, 51:575--583, Feb. 2003. Google ScholarDigital Library
- Y. Yeh and S. Kuo. An optimization-based low-power voltage scaling technique using multiple supply voltages. In Proceedings of the IEEE International Symposium on Circuits and Systems, volume 5, pages 535--538, May 2001.Google Scholar
- Y. Yeh, S. Kuo, and J. Jou. Converter-free multiple-voltage scaling techniques for low-power CMOS digital design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 20(1):172--176, Jan. 2001. Google ScholarDigital Library
Index Terms
- Highly energy and performance efficient embedded computing through approximately correct arithmetic: a mathematical foundation and preliminary experimental validation
Recommendations
Minimum-Energy Operation Via Error Resiliency
Error resiliency has demonstrated significant robustness and energy benefits in superthreshold performance-constrained applications (Shanbhag, Proc. Des. Autom. Conf., Jun. 2010). In this letter, we study the impact of error resiliency, in particular ...
Performance evaluation of energy efficient ethernet
Until very recently, energy efficiency has received little attention in many wired communications environments. For example, in most current Ethernet standards the transmitter and receiver operate at full power even when no data is being sent. However, ...
A highly energy-efficient, area-efficient switching scheme for SAR ADC in biomedical applications
AbstractSuccessive approximation register (SAR) analogue-to-digital converter (ADC) is a good choice for low-power applications owing to its high energy-efficiency. However, in the biomedical applications which require ultra-low power consumption, the ...
Comments