Exploring the fidelity-efficiency design space using imprecise arithmetic

Recently many imprecise circuit design techniques have been proposed for implementation of error-tolerant applications, such as multimedia and communications. These algorithms do not mandate absolute correctness of their results, and imprecise circuit components can therefore leverage this relaxed fidelity requirement to provide performance and energy benefits. In this paper, several imprecise adder design techniques are classified and compared in terms of their error characteristics and power-delay efficiency. A general methodology for fidelity-efficiency design space exploration is presented and is applied to a case study implementing the CORDIC algorithm in 130nm technology. The case study reveals that simple precision scaling often provides better power-delay efficiency for a given fidelity than more complex imprecise adders, but different choice of algorithm and fidelity can influence the outcome.

[1]  R.W. Brodersen,et al.  Methods for true energy-performance optimization , 2004, IEEE Journal of Solid-State Circuits.

[2]  Douglas L. Jones,et al.  Scalable stochastic processors , 2010, 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010).

[3]  Magdy Bayoumi,et al.  A low-power multiplication algorithm for signal processing in wireless sensor networks , 2009, 2009 52nd IEEE International Midwest Symposium on Circuits and Systems.

[4]  Shohaib Aboobacker.  RAZOR: circuit-level correction of timing errors for low-power operation , 2011 .

[5]  De Figueiredo,et al.  Self-validated numerical methods and applications , 1997 .

[6]  Kaushik Roy,et al.  Design methodology to trade off power, output quality and error resiliency: application to color interpolation filtering , 2007, 2007 IEEE/ACM International Conference on Computer-Aided Design.

[7]  J. S. Walther,et al.  A unified algorithm for elementary functions , 1899, AFIPS '71 (Spring).

[8]  S. Mitra,et al.  Error Resilient System Architecture ( ERSA ) For Probabilistic Applications , .

[9]  Gang Wang,et al.  Enhanced low-power high-speed adder for error-tolerant application , 2009, 2010 International SoC Design Conference.

[10]  Paolo Ienne,et al.  Variable Latency Speculative Addition: A New Paradigm for Arithmetic Circuit Design , 2008, 2008 Design, Automation and Test in Europe.

[11]  John Lach,et al.  ColSpace: Towards algorithm/implementation co-optimization , 2009, 2009 IEEE International Conference on Computer Design.

[12]  Zhenyu Qi,et al.  CORDIC implementation with parameterizable ASIC/SoC flow , 2010, Proceedings of the IEEE SoutheastCon 2010 (SoutheastCon).

[13]  Jan M. Rabaey,et al.  Multi-Dimensional Circuit and Micro-Architecture Level Optimization , 2007, 8th International Symposium on Quality Electronic Design (ISQED'07).

[14]  Quinn Jacobson,et al.  ERSA: error resilient system architecture for probabilistic applications , 2010, DATE 2010.