LORAx: A High-speed Energy-efficient Lower-Order Rounding-based Approximate Multiplier

National Academy Science Letters (2021)Cite this article

Abstract

Applications such as image, audio, and video processing are tolerant to certain amounts of error. This tolerance/resiliency can be exploited to construct approximate circuits with improved design parameters such as area, power, and delay. This paper presents a high-speed yet energy-efficient approximate multiplier for low-power applications. In the proposed scheme, the operands are divided into accurate (significant) and rounded (insignificant) sections at half of the operand bit-length. Further, simplified multiplication operations are performed between these sections to obtain the final product. The proposed multiplier architecture involves an accurate small width multiplier as well as shifter blocks, which leads to delay- and energy-efficient architecture. The performance of proposed multiplier over the existing is evaluated by coding the designs in Verilog implementing on Artix7 family XC7A100TCSG324 FPGA device using Xilinx ISE tool chain. The simulation results show 23–31% and up to 26% in delay and energy savings, respectively, over the existing approximate architectures.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

US$ 39.95

Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3

References

  1. 1.

    Alioto M (2012) Ultra-low power vlsi circuit design demystified and explained: a tutorial. IEEE Trans Circuits Syst I: Regular Papers 59(1):3–29

    MathSciNet  Article  Google Scholar 

  2. 2.

    Gupta V, Mohapatra D, Raghunathan A, Roy K (2012) Low-power digital signal processing using approximate adders. IEEE Trans Computer-Aided Design Integr Circuits Syst 32(1):124–137

    Article  Google Scholar 

  3. 3.

    Mahdiani HR, Ahmadi A, Fakhraie SM, Lucas C (2009) Bio-inspired imprecise computational blocks for efficient vlsi implementation of soft-computing applications. IEEE Trans Circuits Syst I: Regular Papers 57(4):850–862

    MathSciNet  Article  Google Scholar 

  4. 4.

    Venkatesan R, Agarwal A, Roy K, Raghunathan A (2011) Macaco: modeling and analysis of circuits for approximate computing. In: 2011 IEEE/ACM international conference on computer-aided design (ICCAD). IEEE, pp 667–673

  5. 5.

    Narayanamoorthy S, Moghaddam HA, Liu Z, Park T, Kim NS (2014) Energy-efficientapproximate multiplication for digital signal processing andclassification applications. IEEE Trans Verylarge Scale Integr (VLSI) Syst 23(6):1180–1184

    Article  Google Scholar 

  6. 6.

    Ansari MS, Cockburn BF, Han J (2019) A hardware-efficient logarithmic multiplier with improved accuracy. In: 2019 design, automation & test in europe conference & exhibition (DATE). IEEE, pp 928–931

  7. 7.

    Lu S-L (2004) Speeding up processing with approximation circuits. Computer 37(3):67–73

    Article  Google Scholar 

  8. 8.

    Zhu N, Goh WL, Wang G, Yeo K S (2010) Enhanced low-power high-speed adder for error-tolerant application. In: 2010 international soc design conference. IEEE, pp 323–327

  9. 9.

    Zhu N, Goh WL, Zhang W, Yeo KS, Kong ZH (2009) Design of low-power high-speed truncation-error-tolerant adder and its application in digital signal processing. IEEE Trans Very Large Scale Integr (VLSI) Syst 18(8):1225–1229

    Google Scholar 

  10. 10.

    Patel S, Garg B, Mahajan A, Rai S (2019) Area-delay efficient and low-power carry skip adder for high performance computing systems. In: IEEE international symposium on smart electronic systems (iSES) (Formerly iNiS). IEEE, pp 295–298

  11. 11.

    Garg B, Bisht Y (2019) A novel high performance reverse carry propagate adder for energy efficient multimedia applications. In IEEE international symposium on smart electronic systems (iSES) (Formerly iNiS). IEEE, pp 291–294

  12. 12.

    Garg B, Patel SK (2021) Reconfigurable carry look-ahead adder trading accuracy for energy efficiency. J Sign Process Syst 93:99–111. https://doi.org/10.1007/s11265-020-01542-1

    Article  Google Scholar 

  13. 13.

    Kulkarni P, Gupta P, Ercegovac M, (2011) Trading accuracy for power with an underdesigned multiplier architecture. In: 2011 24th internatioal conference on VLSI design. IEEE, pp 346–351

  14. 14.

    Garg B, Sharma G (2017) Acm: An energy-efficient accuracy configurable multiplier for error-resilient applications. J Elect Testing 33(4):479–489

    Article  Google Scholar 

  15. 15.

    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 Press, pp 418–425

  16. 16.

    Zendegani R, Kamal M, Bahadori M, Afzali-Kusha A, Pedram M (2016) Roba multiplier: a rounding-based approximate multiplier for high-speed yet energy-efficient digital signal processing. IEEE Trans Very Large Scale Integr (VLSI) Syst 25(2):393–401

    Article  Google Scholar 

  17. 17.

    Ebrahimi Z, Ullah S, Kumar A (2020) Leap: leading-one detection-based softcore approximate multipliers with tunable accuracy. In: 2020 25th Asia and South Pacific design automation conference (ASP-DAC). IEEE, pp. 605–610

  18. 18.

    Ansari MS, Mrazek V, Cockburn BF, Sekanina L, Vasicek Z, Han J (2020) Improving the accuracy and hardware efficiency of neural networks using approximate multipliers. IEEE Trans Very Large Scale Integ VLSI) Syst 28(2):317–328. https://doi.org/10.1109/TVLSI.2019.2940943

    Article  Google Scholar 

  19. 19.

    Garg B, Patel SK, Dutt S (2020) LoBA: a leading one bit based imprecise multiplier for efficient image processing. J Electron Test 36:429–437. https://doi.org/10.1007/s10836-020-05883-4

    Article  Google Scholar 

  20. 20.

    Garg B, Goteti V C, Sharma G (2016) A low-cost energy efficient image scaling processor for multimedia applications. In: VLSI Design and Test (VDAT), 2016 20th international symposium on. IEEE, pp 1–6

  21. 21.

    Garg B, Sharma G (2016) A quality-aware energy-scalable gaussian smoothing filter for image processing applications. Microprocess Microsyst 45:1–9

    Article  Google Scholar 

  22. 22.

    Harley RM et al (2009) The pocket handbook of image processing algorithms in C. Prentice-Hall, New Jersey

    Google Scholar 

Download references

Author information

Affiliations

  1. Thapar Institute of Engineering and Technology, Patiala, India

    Piyush Satti, Pratibha Agrawal & Bharat Garg

Authors
  1. Piyush Satti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pratibha Agrawal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bharat Garg
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bharat Garg.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Satti, P., Agrawal, P. & Garg, B. LORAx: A High-speed Energy-efficient Lower-Order Rounding-based Approximate Multiplier. Natl. Acad. Sci. Lett. (2021). https://doi.org/10.1007/s40009-020-01036-5

Download citation

Keywords

  • Arithmetic design
  • Approximate architecture
  • High-speed
  • Energy-efficient design
  • Multipliers
  • Image processing