Design of low-cost approximate multipliers based on probability-driven inexact compressors

Yi Guo, Heming Sun, Ping Lei, Shinji Kimura

Research output: Contribution to journalArticle

Abstract

Approximate computing has emerged as a promising approach for error-tolerant applications to improve hardware performance at the cost of some loss of accuracy. Multiplication is a key arithmetic operation in these applications. In this paper, we propose a low-cost approximate multiplier design by employing new probability-driven inexact compressors. This compressor design is introduced to reduce the height of partial product matrix into two rows, based on the probability distribution of the sum result of partial products. To compensate the accuracy loss of the multiplier, a grouped error recovery scheme is proposed and achieves different levels of accuracy. In terms of mean relative error distance (MRED), the accuracy losses of the proposed multipliers are from 1.07% to 7.86%. Compared with the Wallace multiplier using 40nm process, the most accurate variant of the proposed multipliers can reduce power by 59.75% and area by 42.47%. The critical path delay reduction is larger than 12.78%. The proposed multiplier design has a better accuracy-performance tradeoff than other designs with comparable accuracy. In addition, the efficiency of the proposed multiplier design is assessed in an image processing application.

Original languageEnglish
Pages (from-to)1781-1791
Number of pages11
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE102A
Issue number12
DOIs
Publication statusPublished - 2019

Keywords

  • Approximate computing
  • Error recovery
  • Inexact compressor
  • Multiplier

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Design of low-cost approximate multipliers based on probability-driven inexact compressors'. Together they form a unique fingerprint.

  • Cite this