Advertisement

Approximate Arithmetic Circuits: Design and Evaluation

  • Honglan Jiang
  • Leibo Liu
  • Fabrizio Lombardi
  • Jie Han
Chapter

Abstract

Arithmetic circuits are important computing modules in a processor. They play a key role in the performance and the energy consumption of many image processing applications. In this chapter, a classification is presented for the current designs of approximate arithmetic circuits including adders, multipliers, and dividers. To understand the features of various designs, a comparative evaluation of their error and circuit characteristics is performed. The accuracy of approximate arithmetic circuits is evaluated by carrying out Monte Carlo simulations. The circuit measurements are assessed by synthesizing approximate designs in an STM CMOS 28 nm process. The simulation and synthesis results show the trade-offs of approximate arithmetic circuits between accuracy and hardware efficiency.

References

  1. 1.
    Angizi S, Jiang H, DeMara RF, Han J, Fan D (2018) Majority-based spin-CMOS primitives for approximate computing. IEEE Trans Nanotechnol 17(4):795–806Google Scholar
  2. 2.
    Baran D, Aktan M, Oklobdzija VG (2010) Energy efficient implementation of parallel CMOS multipliers with improved compressors. In: Proceedings of the 16th ACM/IEEE international symposium on Low power electronics and design. ACM, New York, pp 147–152Google Scholar
  3. 3.
    Bhardwaj K, Mane PS, Henkel J (2014) Power- and area-efficient approximate Wallace tree multiplier for error-resilient systems. In: International symposium on quality electronic design. IEEE, Piscataway, pp 263–269CrossRefGoogle Scholar
  4. 4.
    Cai H, Wang Y, Naviner LA, Wang Z, Zhao W (2016) Approximate computing in MOS/spintronic non-volatile full-adder. In: International symposium on nanoscale architectures. IEEE, Piscataway, pp 203–208Google Scholar
  5. 5.
    Camus V, Schlachter J, Enz C (2015) Energy-efficient inexact speculative adder with high performance and accuracy control. In: International symposium on circuits and systems. IEEE, Piscataway, pp 45–48Google Scholar
  6. 6.
    Camus V, Schlachter J, Enz C (2016) A low-power carry cut-back approximate adder with fixed-point implementation and floating-point precision. In: Design automation conference. IEEE, Piscataway, pp 1–6Google Scholar
  7. 7.
    Chen YH, Chang TY (2012) A high-accuracy adaptive conditional-probability estimator for fixed-width Booth multipliers. IEEE Trans Circuits Syst Regul Pap 59(3):594–603MathSciNetCrossRefGoogle Scholar
  8. 8.
    Chen L, Han J, Liu W, Lombardi F (2015) Design of approximate unsigned integer non-restoring divider for inexact computing. In: Proceedings of the on great lakes symposium on VLSI. ACM, New York, pp 51–56Google Scholar
  9. 9.
    Chen L, Han J, Liu W, Lombardi F (2016) On the design of approximate restoring dividers for error-tolerant applications. IEEE Trans Comput 65(8):2522–2533MathSciNetCrossRefGoogle Scholar
  10. 10.
    Chen L, Montuschi P, Han J, Liu W, Lombardi F (2017) Design of approximate high-radix dividers by inexact binary signed-digit addition. In: Proceedings of the on great lakes symposium on VLSI. ACM, New York, pp 293–298Google Scholar
  11. 11.
    Cho KJ, Lee KC, Chung JG, Parhi, KK (2004) Design of low-error fixed-width modified booth multiplier. IEEE Trans VLSI Syst 12(5):522–531CrossRefGoogle Scholar
  12. 12.
    Du K, Varman P, Mohanram K (2012) High performance reliable variable latency carry select addition. In: Proceedings of the conference on design, automation and test in Europe. EDA Consortium, San Jose, pp 1257–1262Google Scholar
  13. 13.
    Farshchi F, Abrishami MS, Fakhraie SM (2013) New approximate multiplier for low power digital signal processing. In: International symposium on computer architecture and digital systems. IEEE, Piscataway, pp 25–30Google Scholar
  14. 14.
    Flynn MJ (1970) On division by functional iteration. IEEE Trans Comput 100(8):702–706CrossRefGoogle Scholar
  15. 15.
    Gupta V, Mohapatra D, Raghunathan A, Roy K (2013) Low-power digital signal processing using approximate adders. IEEE Trans Comput-Aided Des Integr Circuits Syst 32(1):124–137CrossRefGoogle Scholar
  16. 16.
    Han J (2016) Introduction to approximate computing. In: VLSI Test symposium. IEEE, Piscataway, pp 1–1Google Scholar
  17. 17.
    Han J, Orshansky M (2013) Approximate computing: an emerging paradigm for energy-efficient design. In: European test symposium. IEEE, Piscataway, pp 1–6Google Scholar
  18. 18.
    Hashemi S, Bahar R, Reda S (2015) Drum: a dynamic range unbiased multiplier for approximate applications. In: Proceedings of the IEEE/ACM international conference on computer-aided design. IEEE, Piscataway, pp 418–425Google Scholar
  19. 19.
    Hashemi S, Bahar R, Reda S (2016) A low-power dynamic divider for approximate applications. In: Proceedings of the 53rd annual design automation conference. ACM, New York, pp 105Google Scholar
  20. 20.
    Hu J, Qian W (2015) A new approximate adder with low relative error and correct sign calculation. In: Proceedings of the design, automation and test in Europe conference and exhibition. EDA Consortium, San Jose, pp 1449–1454Google Scholar
  21. 21.
    Jiang H, Han J, Lombardi F (2016) Approximate radix-8 booth multiplier for low-power and high-performance operation. IEEE Trans Comput 65(8):2638–2644MathSciNetCrossRefGoogle Scholar
  22. 22.
    Jiang H, Liu C, Lombardi F, Han J (2018) Low-power approximate unsigned multipliers with configurable error recovery. IEEE Trans Circuits Sys I 99:1–14Google Scholar
  23. 23.
    Kahng AB, Kang S (2012) Accuracy-configurable adder for approximate arithmetic designs. In: Design automation conference. IEEE, Piscataway, pp 820–825Google Scholar
  24. 24.
    Kim Y, Zhang Y, Li P (2013) An energy efficient approximate adder with carry skip for error resilient neuromorphic VLSI systems. In: Proceedings of the international conference on computer-aided design. IEEE, Piscataway, pp 130–137Google Scholar
  25. 25.
    Kulkarni P, Gupta P, Ercegovac M (2011) Trading accuracy for power with an underdesigned multiplier architecture. In: International conference on VLSI design. IEEE, Piscataway, pp 346–351Google Scholar
  26. 26.
    Kyaw KY, Goh WL, Yeo KS (2010) Low-power high-speed multiplier for error-tolerant application. In: International conference on electron devices and solid-state circuits. IEEE, Piscataway, pp 1–4Google Scholar
  27. 27.
    Li L, Zhou H (2014) On error modeling and analysis of approximate adders. In: Proceedings of the international conference on computer-aided design. IEEE, Piscataway, pp 511–518Google Scholar
  28. 28.
    Liang J, Han J, Lombardi F (2013) New metrics for the reliability of approximate and probabilistic adders. IEEE Trans Comput 62(9):1760–1771MathSciNetCrossRefGoogle Scholar
  29. 29.
    Lin CH, Lin C (2013) High accuracy approximate multiplier with error correction. In: International conference on computer design. IEEE, Piscataway, pp 33–38Google Scholar
  30. 30.
    Lin IC, Yang YM, Lin CC (2015) High-performance low-power carry speculative addition with variable latency. IEEE Trans VLSI Syst 23(9):1591–1603CrossRefGoogle Scholar
  31. 31.
    Liu C (2014) Design and analysis of approximate adders and multipliers. University of Alberta, EdmontonGoogle Scholar
  32. 32.
    Liu W, Nannarelli A (2012) Power efficient division and square root unit. IEEE Trans Comput 61(8):1059–1070MathSciNetCrossRefGoogle Scholar
  33. 33.
    Liu C, Han J, Lombardi F (2014) A low-power, high-performance approximate multiplier with configurable partial error recovery. In: Design, automation and test in Europe conference and exhibition. IEEE, Piscataway, pp 1–4Google Scholar
  34. 34.
    Liu W, Qian L, Wang C et al (2017) Design of approximate radix-4 booth multipliers for error-tolerant computing. IEEE Trans Comput 66(8):1435–1441MathSciNetCrossRefGoogle Scholar
  35. 35.
    Low JYL, Jong CC (2013) Non-iterative high speed division computation based on Mitchell logarithmic method. In: International symposium on circuits and systems. IEEE, Piscataway, p 2219–2222Google Scholar
  36. 36.
    Lu SL (2003) Speeding up processing with approximation circuits. Computer 37(3):67–73Google Scholar
  37. 37.
    Ma J, Man KL, Zhang N, Guan SU, Jeong TT (2013) High-speed area-efficient and power-aware multiplier design using approximate compressors along with bottom-up tree topology. In: International conference on machine vision: algorithms, pattern recognition, and basic technologies, vol 8784. International Society for Optics and Photonics, Bellingham, p 87841ZGoogle Scholar
  38. 38.
    Mahdiani HR, Ahmadi A, Fakhraie SM, Lucas C (2010) Bio-inspired imprecise computational blocks for efficient VLSI implementation of soft-computing applications. IEEE Trans Circuits Syst 57(4):850–862MathSciNetCrossRefGoogle Scholar
  39. 39.
    Miao J, He K, Gerstlauer A, Orshansky M (2012) Modeling and synthesis of quality-energy optimal approximate adders. In: International conference on computer-aided design. IEEE, Piscataway, p 728–735Google Scholar
  40. 40.
    Min-An S, Lan-Da V, Sy-Yen K (2007) Adaptive low-error fixed-width Booth multipliers. IEICE Trans Fundam Electron Commun Comput Sci 90(6):1180–1187Google Scholar
  41. 41.
    Mitchell JN (1962) Computer multiplication and division using binary logarithms. IRE Trans Electron Comput 4:512–517MathSciNetCrossRefGoogle Scholar
  42. 42.
    Mohapatra D, Chippa VK, Raghunathan A, Roy K (2011) Design of voltage-scalable meta-functions for approximate computing. In: Design, automation and test in Europe conference and exhibition. IEEE, Piscataway, pp 1–6Google Scholar
  43. 43.
    Momeni A, Han J, Montuschi P, Lombardi F (2014) Design and analysis of approximate compressors for multiplication. IEEE Trans Comput 64(4):984–994MathSciNetCrossRefGoogle Scholar
  44. 44.
    Narayanamoorthy S, Moghaddam HA, Liu Z, Park T, Kim NS (2015) Energy-efficient approximate multiplication for digital signal processing and classification applications. IEEE Trans VLSI Syst 23(6):1180–1184CrossRefGoogle Scholar
  45. 45.
    Oklobdzija VG, Villeger D, Liu SS (1996) A method for speed optimized partial product reduction and generation of fast parallel multipliers using an algorithmic approach. IEEE Trans Comput 45(3):294–306CrossRefGoogle Scholar
  46. 46.
    Parhami B (2000) Computer arithmetic. Oxford University Press, OxfordGoogle Scholar
  47. 47.
    Venkatesan R, Agarwal A, Roy K, Raghunathan A (2011) MACACO: modeling and analysis of circuits for approximate computing. In: International conference on computer-aided design. IEEE, Piscataway, p 667–673Google Scholar
  48. 48.
    Verma AK, Brisk, P, Ienne, P (2008) Variable latency speculative addition: a new paradigm for arithmetic circuit design. In: Proceedings of the conference on design, automation and test in Europe. ACM, New York, pp 1250–1255CrossRefGoogle Scholar
  49. 49.
    Wang JP, Kuang SR, Liang SC (2011) High-accuracy fixed-width modified Booth multipliers for lossy applications. IEEE Trans VLSI Syst 19(1):52–60CrossRefGoogle Scholar
  50. 50.
    Wu L, Jong CC (2015) A curve fitting approach for non-iterative divider design with accuracy and performance trade-off. In: New circuits and systems conference. IEEE, Piscataway, pp 1–4Google Scholar
  51. 51.
    Yang Z, Jain A, Liang J, Han J, Lombardi F (2013) Approximate XOR/XNOR-based adders for inexact computing. In: IEEE conference on nanotechnology. IEEE, Piscataway, pp 690–693Google Scholar
  52. 52.
    Yang X, Xing Y, Qiao F, Wei Q, Yang H (2016) Approximate adder with hybrid prediction and error compensation technique. In: IEEE computer society annual symposium on VLSI. IEEE, Piscataway, pp 373–378Google Scholar
  53. 53.
    Ye R, Wang T, Yuan F, Kumar R, Xu Q (2013) On reconfiguration-oriented approximate adder design and its application. In: Proceedings of the international conference on computer-aided design. IEEE, Piscataway, pp 48–54Google Scholar
  54. 54.
    Zendegani R, Kamal M, Fayyazi A et al (2016) SEERAD: a high speed yet energy-efficient rounding-based approximate divider. In: Design, automation and test in Europe conference and exhibition. IEEE, Piscataway, pp 1481–1484Google Scholar
  55. 55.
    Zendegani R, Kamal M, Bahadori M, Afzali-Kusha A, Pedram M (2017) RoBA multiplier: a rounding-based approximate multiplier for high-speed yet energy-efficient digital signal processing. IEEE Trans VLSI Syst 25(2):393–401CrossRefGoogle Scholar
  56. 56.
    Zhu N, Goh WL, Yeo, KS (2009) An enhanced low-power high-speed adder for error-tolerant application. In: Proceedings of the international symposium on integrated circuits. IEEE, Piscataway, pp 69–72Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Honglan Jiang
    • 1
  • Leibo Liu
    • 2
  • Fabrizio Lombardi
    • 3
  • Jie Han
    • 1
  1. 1.University of AlbertaEdmontonCanada
  2. 2.Institute of MicroelectronicsTsinghua UniversityBeijingChina
  3. 3.Northeastern UniversityBostonUSA

Personalised recommendations