Skip to main content
Video s3
    Details
    Presenter(s)
    Kamyar Givaki Headshot
    Display Name
    Kamyar Givaki
    Affiliation
    Affiliation
    University of Tehran
    Country
    Author(s)
    Display Name
    Kamyar Givaki
    Affiliation
    Affiliation
    University of Tehran
    Display Name
    Reza Hojabr
    Affiliation
    Affiliation
    University of Tehran
    Affiliation
    Affiliation
    Chosun University
    Display Name
    Ahmad Khonsari
    Affiliation
    Affiliation
    University of Tehran
    Display Name
    Saeid Gorgin
    Affiliation
    Affiliation
    Chosun University
    Display Name
    Dara Rahmati
    Affiliation
    Affiliation
    Shahid Beheshti University
    Display Name
    M. Hassan Najafi
    Affiliation
    Affiliation
    University of Louisiana at Lafayette
    Abstract

    Stochastic Computing (SC) is a re-emerging computing paradigm with a great potential to surpass conventional binary implementations in term of hardware cost. The inaccuracy of computations is an important challenge with conventional SC designs. Recently, some deterministic approaches to SC were proposed. These methods are able to produce completely accurate results. However, they take a long processing time to produce exact results which directly translates to very high energy consumption. This work proposes a design methodology based on the Residue Number System (RNS) to mitigate the long processing time of the deterministic methods of SC. Leveraging RNS, the length of bit-streams decreases exponentially as high bitwidth operands are replaced with low bit-width residues. Compared to the state-of-the-art deterministic methods, the proposed approach delivers more than 2400× and 3200× reduction in processing time and energy consumption, respectively, for 8-bit multiplication operation.

    Slides
    • High Performance Deterministic Stochastic Computing Using Residue Number System (application/pdf)