AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (581.7 KB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Accurate Reliability Analysis Methods for Approximate Computing Circuits

School of the Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
School of Software Engineering, Tongji University, Shanghai 200092, China
Show Author Information

Abstract

In recent years, Approximate Computing Circuits (ACCs) have been widely used in applications with intrinsic tolerance to errors. With the increased availability of approximate computing circuit approaches, reliability analysis methods for assessing their fault vulnerability have become highly necessary. In this study, two accurate reliability evaluation methods for approximate computing circuits are proposed. The reliability of approximate computing circuits is calculated on the basis of the iterative Probabilistic Transfer Matrix (PTM) model. During the calculation, the correlation coefficients are derived and combined to deal with the correlation problem caused by fanout reconvergence. The accuracy and scalability of the two methods are verified using three sets of approximate computing circuit instances and more circuits in EvoApprox8b, which is an approximate computing circuit open source library. Experimental results show that relative to the Monte Carlo simulation, the two methods achieve average error rates of 0.46% and 1.29% and time overheads of 0.002% and 0.1%. Different from the existing approaches to reliability estimation for approximate computing circuits based on the original PTM model, the proposed methods reduce the space overheads by nearly 50% and achieve time overheads of 1.78% and 2.19%.

References

[1]
M. A. Breuer, Intelligible test techniques to support error-tolerance, in Proc. of Asia Test Symposium, Kenting, China, 2004, pp. 386-393.
[2]
Y. Song and W. Liang, Experimental study of discriminative adaptive training and MLLR for automatic pronunciation evaluation, Tsinghua Science and Technology, vol. 16, no. 2, pp. 189—193, 2011.
[3]
S. K. Min, A. D. Barrio, R. Hermida, and N. Bagherzadeh, Low-power implementation of Mitchell’s approximate logarithmic multiplication for convolutional neural networks, in Proc. of Asia & South Pacific Design Automation Conference, Jeju Island, Korea, 2018, pp. 617-622.
[4]
G. Liu and Z. R. Zhang, Statistically certified approximate logic synthesis, in Proc. of IEEE International Conference on Computer-Aided Design, Irvine, CA, USA, 2017, pp. 344-351.
[5]
C. Y. Chen, J. Choi, K. Gopalakrishnan, V. Srinivasan, and S. Venkataramani, Exploiting approximate computing for deep learning acceleration, in Proc. of Design, Automation & Test in Europe Conference & Exhibition, Dresden, Germany, 2018, pp. 821-826.
[6]
J. Han and M. Orshansky, Approximate computing: An emerging paradigm for energy-efficient design, in Proc. IEEE European Test Symposium, Avignon, France, 2013, pp. 1-6.
[7]
A. Yazdanbakhsh, J. Park, H. Sharma, P. Lotfi-Kamran, and H. Esmaeilzadeh, Neural acceleration for GPU throughput processors, in Proc. of IEEE International Symposium on Microarchitecture, Waikiki, HI, USA, 2015, pp. 482-493.
[8]
N. Jing, W. Bi, and Q. Yue, Attack simulation model and channel statistics in underwater acoustic sensor networks, Tsinghua Science and Technology, vol. 16, no. 6, pp. 611-621, 2011.
[9]
S. Sidiroglou-Douskos, S. Misailovic, H. Hoffmann, and M. Rinard, Managing performance vs. accuracy trade-offs with loop perforation, in Proc. ACM SIGSOFT Symposium and the 13th European Conference on Foundations of Software Engineering, Szeged, Hungary, 2011, pp. 124-134.
[10]
M. Shafique, R. Hafiz, S. Rehman, W. El-Harouni, and J. Henkel, Invited: Cross-layer approximate computing: From logic to architectures, in Proc. of 53nd ACM/EDAC/IEEE Design Automation Conference, Austin, TX, USA, 2016, pp. 99:1-99:6.
[11]
A. Yan, C. Lai, Y. Zhang, J. Cui, Z. Huang, J. Song, J. Guo, and X. Wen, Novel low cost, double-and-triple-node-upset-tolerant latch designs for nano-scale CMOS, IEEE Transactions on Emerging Topics in Computing, .
[12]
J. Jiang, G. Lu, and Z. Wang, Methods for approximate adders reliability estimation based on PTM model, in Proc. of IEEE 23th Pacific Rim International Symposium on Dependable Computing, Taipei, China, 2018, pp. 221-222.
[13]
S. Krishnaswamy, G. F. Viamontes, I. L. Markov, and J. P. Hayes, Accurate reliability evaluation and enhancement via probabilistic transfer matrices, in Proc. of the Design, Automation and Test in Europe Conference and Exhibition, Munich, Germany, 2005, pp. 282-287.
[14]
R. Venkatesan, A. Agarwal, K. Roy, and A. Raghunathan, MACACO: Modeling and analysis of circuits for approximate computing, in Proc. of IEEE International Conference on Computer-Aided Design, San Jose, CA, USA, 2011, pp. 667-673.
[15]
J. H. Liang, J. Han, and F. Lombardi, On the reliable performance of sequential adders in soft computing, in Proc. of IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, Vancouver, Canada, 2011, pp. 3-10.
[16]
J. H. Liang, J. Han, and F. Lombardi, New metrics for the reliability of approximate and probabilistic adders, IEEE Transactions on Computers, vol. 62, no. 9, pp. 1760-1771, 2013.
[17]
C. Liu, J. Han, and F. Lombardi, An analytical framework for evaluating the error characteristics of approximate adders, IEEE Transactions on Computers, vol. 64, no. 5, pp. 1268-1281, 2015.
[18]
Y. Wu, Y. Li, X. Ge, Y. Gao, and W. Qian, An efficient method for calculating the error statistics of block-based approximate adders, IEEE Transactions on Computers, vol. 68, no. 1, pp. 21-38, 2019.
[19]
H. Jiang and G. Liu, A review, classification, and comparative evaluation of approximate arithmetic circuits, ACM Journal on Emerging Technologies in Computing Systems, vol. 13, no. 4, pp. 1-34, 2017.
[20]
L. Chen, J. Han, W. Liu, P. Monstuschi, and F. Lombardi, Design, evaluation and application of approximate high-radix dividers, IEEE Transactions on MultiScale Computing Systems, vol. 4, no. 3, pp. 299-312, 2018.
[21]
M. Bruestel and A. Kumar, Accounting for systematic errors in approximate computing, in Proc. of IEEE Design, Automation & Test in Europe Conference & Exhibition, Lausanne, Switzerland, 2017, pp. 298-301.
[22]
Ilia Polian, Test and reliability challenges for approximate circuitry, IEEE Embedded Systems Letters, vol. 10, no. 1, pp. 26-29, 2018.
[23]
L. Anghel, M. Benabdenbi, and A. Bosio, Test and reliability in approximate computing, in Proc. of International Mixed Signals Testing Workshop, Thessaloniki, Greece, 2017, pp. 375-387.
[24]
Y. Fang, H. Li, and X. Li, A fault criticality evaluation framework of digital systems for error tolerant video applications, in Proc. of Asian Test Symposium, New Delhi, India, 2011, pp. 329-334.
[25]
Z. Wang, J. Jiang, and T. Wang, Failure probability analysis and critical node determination for approximate circuits integration, the VLSI Journal, vol. 68, no. 5, pp. 122-128, 2019.
[26]
S. Krishnaswamy, G. F. Viamontes, I. L. Markov, and J. P. Hayes, Probabilistic transfer matrices in symbolic reliability analysis of logic circuits, ACM Trans. on Design Automation of Electronic Systems, vol. 13, no. 1, pp. 1-35, 2008.
[27]
J. Xiao, W. Lee, J. H. Jiang, and X. H. Yang, Circuit reliability estimation based on an iterative PTM model with hybrid coding, Microelectronics Journal, vol. 52, pp. 117-123, 2016.
[28]
S. Ercolani, M. Favalli, M. Damiani, P. Olivo, and B. Ricco, Estimate of signal probability in combinational logic networks, in Proc. of 1st European Test Conference, Paris, France, 1989, pp. 132-138.
[29]
V. Mrazek, R. Hrbacek, Z. Vasicek, and L. Sekanina, EvoApprox8b: Library of approximate adders and multipliers for circuit design and benchmarking of approximation methods, in Proc. of Design, Automation & Test in Europe Conference & Exhibition, Lausanne, Switzerland, 2017, pp. 258-261.
Tsinghua Science and Technology
Pages 729-740
Cite this article:
Wang Z, Zhang G, Ye J, et al. Accurate Reliability Analysis Methods for Approximate Computing Circuits. Tsinghua Science and Technology, 2022, 27(4): 729-740. https://doi.org/10.26599/TST.2020.9010032

780

Views

71

Downloads

8

Crossref

5

Web of Science

8

Scopus

1

CSCD

Altmetrics

Received: 29 July 2020
Accepted: 03 September 2020
Published: 09 December 2021
© The author(s) 2022

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return