The Hardware Cost and Computing Accuracy Trade-off in Multipliers using Imprecise 4-2 Compressors for Image Processing Applications

다국어 초록 (Multilingual Abstract)

Approximate computing has been widely used in image processing applications to significantly reduce the hardware cost of circuits; however, this induces a sacrifice in computing accuracy. The compromise between accuracy and hardware cost in approximate multipliers has not been investigated yet. To address this issue, this paper proposes a set of approximate 8×8 Dadda multipliers built by using an efficient imprecise 4-2 compressor. The compressor introduces symmetrical errors into the truth table of the exact design to reach a simpler structure. Furthermore, as an important image processing application, image multiplication is implemented with the proposed multipliers. Synthesis and simulation results show that the overall performance of the multipliers varies depending on the various assessment criteria. Utilization of the modified compressor in the multipliers results in area, delay, and power reductions of 38%-72%, 14%-33%, and 39%-77%, respectively, compared to the exact design, while maintaining acceptable computing accuracy in image multiplication. According to the results, the proposed multipliers achieve a better trade-off between energy efficacy and computing accuracy than the existing designs, which could be certified as options for exact multipliers in image processing.

참고문헌 (Reference)

1 F. Salmanpour, "Ultra-Compact Imprecise 4:2 Compressor and Multiplier Circuits for Approximate Computing in Deep Nanoscale" 2021

2 C. Chiphong, "Ultra low-voltage low-power CMOS 4-2 and 5-2compressors for fast arithmetic circuits" 51 (51): 1985-1997, 2004

3 J. Liang, "New Metrics for the Reliability of Approximate and Probabilistic Adders" 62 (62): 1760-1771, 2013

4 M. Ha, "Multipliers With Approximate 4-2 Compressors and Error Recovery Modules" 10 (10): 6-9, 2018

5 S. Angizi, "Majority-Based Spin-CMOS Primitives for Approximate Computing" 17 (17): 795-806, 2018

6 M. S. Ansari, "Low-Power Approximate Multipliers Using Encoded Partial Products and Approximate Compressors" 8 (8): 404-416, 2018

7 A. G. M. Strollo, "Low-Power Approximate Multiplier with Error Recovery using a New Approximate 4-2Compressor" 1-4, 2020

8 W. Zhou, "Image quality assessment : from error visibility to structural similarity" 13 (13): 600-612, 2004

9 W. Guo, "Fast Binary Counters and Compressors Generated by Sorting Network" 29 (29): 1220-1230, 2021

10 M. Ahmadinejad, "Energy-and Quality-Efficient Approximate Multipliers for Neural Network and Image Processing Applications" 1-1, 2021

11 N. V. Toan, "Energy-Area-Efficient Approximate Multipliers for Error-Tolerant Applications on FPGAs" 336-341, 2019

12 M. Ahmadinejad, "Energy and area efficient imprecise compressors for approximate multiplication at nanoscale" 110 : 2019

13 O. Akbari, "Dual-Quality 4 : 2 Compressors for Utilizing in Dynamic Accuracy Configurable Multipliers" 25 (25): 1352-1361, 2017

14 X. Yi, "Design of an Energy-Efficient Approximate Compressor for Error-Resilient Multiplications" 1-5, 2019

15 H. Pei, "Design of UltraLow Power Consumption Approximate 4-2Compressors Based on the Compensation Characteristic" 68 (68): 461-465, 2021

16 S. Venkatachalam, "Design of Power and Area Efficient Approximate Multipliers" 25 : 1782-1786, 2017

17 M. M. D. Savio, "Design of Higher Order Multiplier with Approximate Compressor" 1-6, 2020

18 A. Gorantla, "Design of Approximate Compressors for Multiplication" 3 : 44-, 2017

19 A. Momeni, "Design and Analysis of Approximate Compressors for Multiplication" 64 (64): 984-994, 2015

20 A. Strollo, "Comparison and Extension of Approximate 4-2Compressors for Low-Power Approximate Multipliers" 67 (67): 3021-3034, 2020

21 D. Esposito, "Approximate Multipliers Based on New Approximate Compressors" 65 (65): 4169-4182, 2018

22 H. Jiang, "Approximate Arithmetic Circuits: A Survey, Characterization, and Recent Applications" 108 (108): 2108-2135, 2020

23 F. Sabetzadeh, "A Majority-Based Imprecise Multiplier for UltraEfficient Approximate Image Multiplication" 66 (66): 4200-4208, 2019

24 N. Savithaa, "A High speed Area Efficient Compression technique of Dadda multiplier for Image Blending Application" 426-430, 2019