Florian Neugebauer
John P. Hayes
Abstract
Stochastic circuits (SCs) offer considerable area- and power-consumption benefits in various applications at the expense of computational inaccuracies. Unlike conventional logic synthesis, managing accuracy is a central problem in SC design. It is usually tackled in ad hoc fashion by multiple trial-and-error simulations that vary relevant parameters like the stochastic number length n. We present, for the first time, a systematic design approach to controlling the accuracy of SCs and balancing it against other design parameters. We express the (in)accuracy of a circuit processing n-bit stochastic numbers by the numerical deviation of the computed value from the expected result, in conjunction with a confidence level. Using the theory of Monte Carlo simulation, we derive expressions for the stochastic number length required for a desired level of accuracy or vice versa. We discuss the integration of the theory into a design framework that is applicable to both combinational and sequential SCs. We show that for combinational SCs, accuracy is independent of the circuit’s size or complexity, a surprising result. We also show how the analysis can identify subtle errors in both combinational and sequential designs. Finally, we apply the proposed methods to a case study on filtering noisy EKG signals.
- Physionet. 2017. Retrieved from https://physionet.org/.Google Scholar
- Armin Alaghi and John P. Hayes. 2013. Survey of stochastic computing. ACM Trans. Embed. Comput. Syst. 12, 2s (2013), 92. Google ScholarDigital Library
- Armin Alaghi and John P. Hayes. 2015. STRAUSS: Spectral transform use in stochastic circuit synthesis. IEEE Trans. Comput.-Aided Des. Integr. Circ. Syst. 34, 11 (2015), 1770--1783.Google ScholarDigital Library
- Armin Alaghi, Cheng Li, and John P. Hayes. 2013. Stochastic circuits for real-time image-processing applications. In Proceedings of the 50th ACM/EDAC/IEEE Design Automation Conference (DAC’13). IEEE, 1--6. Google ScholarDigital Library
- Bradley D. Brown and Howard C. Card. 2001. Stochastic neural computation. I. computational elements. IEEE Trans. Comput. 50, 9 (2001), 891--905. Google ScholarDigital Library
- Michael Bushnell and Vishwani Agrawal. 2004. Essentials of Electronic Testing for Digital, Memory, and Mixed-signal VLSI Circuits. Vol. 17. Springer Science 8 Business Media. Google ScholarDigital Library
- Jienan Chen and Jianhao Hu. 2013. A novel FIR filter based on stochastic logic. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS’13). IEEE, 2050--2053.Google Scholar
- Te-Hsuan Chen and John P. Hayes. 2014. Analyzing and controlling accuracy in stochastic circuits. In Proceedings of the 32nd IEEE International Conference on Computer Design (ICCD’14). IEEE, 367--373.Google Scholar
- Te-Hsuan Chen and John P. Hayes. 2016. Design of division circuits for stochastic computing. In Proceedings of the IEEE Computer Society Annual Symposium on Very Large Scale Integration Systems (ISVLSI’16). IEEE, 116--121.Google Scholar
- Brian R. Gaines et al. 1969. Stochastic computing systems. Adv. Info. Syst. Sci. 2, 2 (1969), 37--172.Google ScholarCross Ref
- John Michael Hammersley and David Christopher Handscomb. 1964. Monte Carlo Methods. J. Wiley, Methuen.Google Scholar
- Hideyuki Ichihara, Tatsuyoshi Sugino, Syota Ishii, Tsuyoshi Iwagaki, and Tomoo Inoue. 2017. Compact and accurate digital filters based on stochastic computing. IEEE Trans. Emerg. Topics Comput. (2017).Google Scholar
- Peng Li and David J. Lilja. 2011. Using stochastic computing to implement digital image processing algorithms. In Proceedings of the IEEE 29th International Conference on Computer Design (ICCD’11). IEEE, 154--161. Google ScholarDigital Library
- Thomas Müller-Gronbach, Erich Novak, and Klaus Ritter. 2012. Monte Carlo-Algorithmen. Springer-Verlag.Google Scholar
- Ali Naderi, Shie Mannor, Mohamad Sawan, and Warren J. Gross. 2011. Delayed stochastic decoding of LDPC codes. IEEE Trans. Signal Process. 59, 11 (2011), 5617--5626. Google ScholarDigital Library
- Alexandru Paler, Josef Kinseher, Ilia Polian, and John P. Hayes. 2013. Approximate simulation of circuits with probabilistic behavior. In Proceedings of the IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT’13). IEEE, 95--100.Google Scholar
- Megha Parhi, Marc D. Riedel, and Keshab K. Parhi. 2015. Effect of bit-level correlation in stochastic computing. In Proceedings of the IEEE International Conference on Digital Signal Processing (DSP’15). IEEE, 463--467.Google Scholar
- Weikang Qian, Xin Li, Marc D. Riedel, Kia Bazargan, and David J. Lilja. 2011. An architecture for fault-tolerant computation with stochastic logic. IEEE Trans. Comput. 60, 1 (2011), 93--105. Google ScholarDigital Library
- Naman Saraf and Kia Bazargan. 2016. Polynomial arithmetic using sequential stochastic logic. In Proceedings of the 26th Edition on Great Lakes Symposium on Very Large Scale Integration. ACM, 245--250. Google ScholarDigital Library
- Ran Wang, Jie Han, Bruce F. Cockburn, and Duncan G. Elliott. 2016. Design, evaluation, and fault-tolerance analysis of stochastic FIR filters. Microelectron. Reliabil. 57 (2016), 111--127.Google ScholarCross Ref
- Ran Wang, Jie Han, Bruce F. Cockburn, and Duncan G. Elliott. 2016. Stochastic circuit design and performance evaluation of vector quantization for different error measures. IEEE Trans. Very Large Scale Integr. Syst. 24, 10 (2016), 3169--3183. Google ScholarDigital Library
Index Terms
- Framework for Quantifying and Managing Accuracy in Stochastic Circuit Design
Recommendations
Framework for quantifying and managing accuracy in stochastic circuit design
DATE '17: Proceedings of the Conference on Design, Automation & Test in EuropeStochastic circuits (SCs) offer tremendous area-and power-consumption benefits at the expense of computational inaccuracies. Managing accuracy is a central problem in SC design and has no counterpart in conventional circuit synthesis. It raises a basic ...
Stochastic circuit synthesis via satisfiability
AbstractBinary numbers converted into stochastic bitstreams enable computationally complex arithmetic to be performed using stochastic computing (SC). The fault-tolerant nature of stochastic computing has made it useful in a large number of ...
Highlights- An exact synthesis method is proposed for stochastic circuit synthesis.
- The ...
Polynomial Arithmetic Using Sequential Stochastic Logic
GLSVLSI '16: Proceedings of the 26th edition on Great Lakes Symposium on VLSIWe present the design of stochastic computing systems based on sequential logic to implement arbitrary polynomial functions. Stochastic computing is an emerging alternative computing paradigm that performs arithmetic operations on real-valued data ...
Comments