Faculty of Information Technology, BUT

Publication Details

Evolutionary Approach to Approximate Digital Circuits Design

VAŠÍČEK Zdeněk and SEKANINA Lukáš. Evolutionary Approach to Approximate Digital Circuits Design. IEEE Transactions on Evolutionary Computation, vol. 19, no. 3, pp. 432-444. ISSN 1089-778X.
Czech title
Evoluční přístup k návrhu aproximačních číslicových obvodů
Type
journal article
Language
english
Authors
URL
Keywords
Approximate computing, Cartesian genetic programming, digital circuits, population seeding
Abstract

In approximate computing, the requirement of perfect functional behavior can be relaxed because some applications are inherently error resilient. Approximate circuits, which fall into the approximate computing paradigm, are designed in such a way that they do not fully implement the logic behavior given by the specification and hence their accuracy can be exchanged for lower area, delay or power consumption.  In order to automate the design process, we propose to evolve approximate digital circuits which show a minimal error for a supplied amount of resources. The design process which is based on Cartesian Genetic Programming (CGP) can be repeated many times in order to obtain various tradeoffs between the accuracy and area. A heuristic seeding mechanism is introduced to CGP which allows for  improving not only the quality of evolved circuits, but also reducing the time of evolution. The efficiency of the proposed method is evaluated for the gate as well as the functional level evolution. In particular, approximate multipliers and median circuits which show very good parameters in comparison with other available implementations were constructed by means of the proposed method. 
Published
2015
Pages
432-444
Journal
IEEE Transactions on Evolutionary Computation, vol. 19, no. 3, ISSN 1089-778X
Publisher
IEEE Computational Intelligence Society
DOI
BibTeX
@ARTICLE{FITPUB10406,
   author = "Zden\v{e}k Va\v{s}\'{i}\v{c}ek and Luk\'{a}\v{s} Sekanina",
   title = "Evolutionary Approach to Approximate Digital Circuits Design",
   pages = "432--444",
   journal = "IEEE Transactions on Evolutionary Computation",
   volume = 19,
   number = 3,
   year = 2015,
   ISSN = "1089-778X",
   doi = "10.1109/TEVC.2014.2336175",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10406"
}
Files
Back to top