Two Efficient Approximate Unsigned Multipliers by Developing New Configuration for Approximate 4:2 Compressors

Ladan Sayadi, Somayeh Timarchi, Akbar Sheikh-Akbari

Research output: Contribution to journalArticlepeer-review


Approximate computing is a promising approach for reducing power consumption and design complexity in applications that accuracy is not a crucial factor. Approximate multipliers are commonly used in error-tolerant applications. This paper presents three approximate 4:2 compressors and two approximate multiplier designs, aiming at reducing the area and power consumption, while maintaining acceptable accuracy. The paper seeks to develop approximate compressors that align positive and negative approximations for input patterns that have the same probability. Additionally, the proposed compressors are utilized to construct approximate multipliers for different columns of partial products based on the input probabilities of the two compressors in adjacent columns. The proposed approximate multipliers are synthesized using the 28nm technology. Compared to the exact multiplier, the first proposed multiplier improves power $\times $ delay and area $\times $ power by 91% and 86%, respectively, while the second proposed multiplier improves the two parameters by 90% and 84%, respectively. The performance of the proposed approximate methods was assessed and compared with the existing methods for image multiplication, sharpening, smoothing and edge detection. Also, the performance of the proposed multipliers in the hardware implementation of the neural network was investigated, and the simulation results indicate that the proposed multipliers have appropriate accuracy in these applications.
Original languageEnglish
Article number10042128
Pages (from-to)1649-1659
Number of pages11
JournalIEEE Transactions on Circuits and Systems I: Regular Papers
Issue number4
Publication statusPublished - 1 Apr 2023


  • Compressors
  • Adders
  • Power demand
  • Neural networks
  • Approximate computing
  • Smoothing methods
  • Probability


Dive into the research topics of 'Two Efficient Approximate Unsigned Multipliers by Developing New Configuration for Approximate 4:2 Compressors'. Together they form a unique fingerprint.

Cite this