Research PapersNo Access

Multistage Latency Adders Architecture Employing Approximate Computing

Xinghua Yang

Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China

Search for more papers by this author

Yue Xing

Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China

Search for more papers by this author

Fei Qiao

Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China

E-mail Address: qiaofei@tsinghua.edu.cn

Corresponding author.

Search for more papers by this author

, and

Huazhong Yang

Department of Electronic Engineering, Tsinghua University, Beijing 100084, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0218126617500396Cited by:3 (Source: Crossref)

Abstract

This paper proposed an energy efficient adder employing multistage latency and approximate computing technology. The delay of the adder decreases after the critical path of the adder is divided into multiple short stages with series of predictors, then the approximate computing technology is exploited to make a tradeoff between output quality and energy efficiency. The proposed design is applied into discrete cosine transformation (DCT) in image processing and support vector machine (SVM) algorithm in machine learning to verify its availability, the simulation results demonstrate that the proposed approximate adder provides 25.6% power-delay-product (PDP) reduction and 2 orders of magnitude reduction in output error than the recent counterpart designs. Compared with the conventional accurate ripple carry adder (RCA) and Kogge stone adde (KSA), the proposed design presents 66.5% to 37.6% PDP reduction, at the cost of negligible output quality reduction, which are qualified as peak signal-to-noise ratio (PSNR) for DCT (decreases from 33.88dB to 33.84dB) and classification accuracy for SVM (decreases from 80.46% to 79.19%).

This paper was recommended by Regional Editor Piero Malcovati.

Keywords:

References

1. D. Mohapatra, V. K. Chippa, A. Raghunathan and K. Roy, Design of voltage-scalable meta-functions for approximate computing, in Design, Automation & Test in Europe Conf. Exhibition (DATE), 2011, IEEE 2011, pp. 1–6. Google Scholar
2. I. Koren, Computer Arithmetic Algorithms (Universities Press, 2002). Google Scholar
3. A. A. Del Barrio, R. Hermida, S. O. Memik, J. M. Mendias and M. C. Molina, Multispeculative addition applied to datapath synthesis, IEEE Trans. Computer-Aided Des. Integr. Circuits Syst. 31 (12) (2012) 1817–1830. Crossref, Web of Science, Google Scholar
4. C. Lin, Y.-M. Yang and C.-C. Lin, High-performance low-power carry speculative addition with variable latency, IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 23 (9) (2015) 1591–1603. Crossref, Web of Science, Google Scholar
5. W. Shan, H. Gu, B. Li, X. Wu, H. Jin, Y. Guo and P. Cao, An improved timing monitor for deep dynamic voltage scaling system, IEICE Electron. Express 10 (6) (2013) 20130089–20130089. Crossref, Web of Science, Google Scholar
6. S. Yinan, L. Yongpan, W. Zhibo and Y. Huazhong, Multistage function speculation adders, IEICE Trans. Fundamentals Electron. Commun. Comput. Sci. 98 (4) (2015) 954–965. Google Scholar
7. A. K. Verma, P. Brisk and P. Ienne, Variable latency speculative addition: A new paradigm for arithmetic circuit design, in Proc. Conf. Design, Automation and Test in Europe, ACM 2008, pp. 1250–1255. Google Scholar
8. D. Mohapatra, G. Karakonstantis and K. Roy, Low-power process-variation tolerant arithmetic units using input-based elastic clocking, in Proc. 2007 Int. Symp. Low Power Electronics and Design, ACM 2007, pp. 74–79. Google Scholar
9. Y. Chen, H. Li, C.-K. Koh, G. Sun, J. Li, Y. Xie and K. Roy, Variable-latency adder (vl-adder) designs for low power and nbti tolerance, IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 18 (11) (2010) 1621–1624. Crossref, Web of Science, Google Scholar
10. V. Gupta, D. Mohapatra, A. Raghunathan and K. Roy, Low-power digital signal processing using approximate adders, IEEE Trans. Computer-Aided Des. Integr. Circuits and Syst. 32 (1) (2013) 124–137. Crossref, Web of Science, Google Scholar
11. J. Kim and S. Tiwari, Inexact computing for ultra low-power nanometer digital circuit design, in 2011 IEEE/ACM Int. Symp. Nanoscale Architectures (NANOARCH), IEEE 2011, pp. 24–31. Google Scholar
12. V. Gupta, D. Mohapatra, S. P. Park, A. Raghunathan and K. Roy, Impact: Imprecise adders for low-power approximate computing, in Proc. 17th IEEE/ACM Int. Symp. Low-Power Electronics and Design, IEEE Press, 2011, pp. 409–414. Google Scholar
13. Y. Kim, Y. Zhang and P. Li, An energy efficient approximate adder with carry skip for error resilient neuromorphic vlsi systems, in Proc. Int. Conf. Computer-Aided Design, IEEE Press, 2013, pp. 130–137. Google Scholar
14. N. Zhu, W. L. Goh and K. S. Yeo, An enhanced low-power high-speed adder for error-tolerant application, in Proc. 2009 12th Int. Symp. Integrated Circuits, ISIC’09, IEEE 2009, pp. 69–72. Google Scholar
15. A. B. Kahng and S. Kang, Accuracy-configurable adder for approximate arithmetic designs, in Proc. 49th Annual Design Automation Conf., ACM 2012, pp. 820–825. Google Scholar
16. R. Ye, T. Wang, F. Yuan, R. Kumar and Q. Xu, On reconfiguration-oriented approximate adder design and its application, in Proc. Int. Conf. Computer-Aided Design, IEEE Press, 2013, pp. 48–54. Google Scholar
17. J. Hu and W. Qian, A new approximate adder with low relative error and correct sign calculation, in Proc. 2015 Design, Automation & Test in Europe Conference & Exhibition, EDA Consortium, 2015, pp. 1449–1454. Google Scholar
18. D. Mohapatra and K. Adviser-Roy, Approximate computing: Enabling voltage over-scaling in multimedia applications (2011). Google Scholar
19. Z. Yang, A. Jain, J. Liang, J. Han and F. Lombardi, Approximate xor/xnor-based adders for inexact computing, in 2013 13th IEEE Conf. Nanotechnology (IEEE-NANO), IEEE, 2013, pp. 690–693. Google Scholar
20. W.-T. J. Chan, A. Kahng, S. Kang, R. Kumar and J. Sartori, Statistical analysis and modeling for error composition in approximate computation circuits, in 2013 IEEE 31st International Conference on Computer Design (ICCD), IEEE 2013, pp. 47–53. Google Scholar
21. H. Jiang, J. Han and F. Lombardi, A comparative review and evaluation of approximate adders, in Proc. 25th Edition on Great Lakes Symp. VLSI, ACM 2015, pp. 343–348. Google Scholar
22. R. Hegde and N. R. Shanbhag, Energy-efficient signal processing via algorithmic noise-tolerance, in Proc. 1999 Int. Symp. Low Power Electronics and Design, ACM, 1999, pp. 30–35. Google Scholar
23. D. Mohapatra, V. K. Chippa, A. Raghunathan and K. Roy, Design of voltage-scalable meta-functions for approximate computing, in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2011, IEEE 2011, pp. 1–6. Google Scholar
24. B. Baassou, M. He and S. Mei, An accurate svm-based classification approach for hyperspectral image classification, in 2013 21st Int. Conf. Geoinformatics (GEOINFORMATICS), IEEE 2013, pp. 1–7. Google Scholar
25. C. Liu, F. Qiao, X. Yang and H. Yang, Hardware acceleration with pipelined adder for support vector machine classifier, in Digital Information and Communication Technology and it's Applications (DICTAP), 2014 Fourth International Conference on 2014 May 6, IEEE, pp. 13–16. Google Scholar
26. R. G. Congalton, A review of assessing the accuracy of classifications of remotely sensed data, Remote Sens. Environ 37 (1) (1991) 35–46. Crossref, Web of Science, Google Scholar