Abstract
Stochastic computing (SC) is an approximate computing technique that has been considered in recent years as an alternative to conventional binary encoding and is compatible with CMOS technology. Stochastic circuits have the advantages of low power, small area, and high fault tolerance. However, highly accurate computation often takes a lot of time because of the fluctuations in random numbers and the requirement for decorrelation between random bitstreams. In this work, mean circuits are proposed to exploit the correlation between the random bitstreams for an arbitrary number of inputs. With the proposed mean circuit, high-accuracy and low-cost mean filtering designs are implemented. Experimental results indicate that the implementations of mean filtering show 10% and 93% reductions in area and power, compared with multiplexer-based designs.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.