Skip to main content
Video s3
    Details
    Presenter(s)
    Daniel García-Lesta Headshot
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Country
    Author(s)
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Display Name
    Paula López
    Affiliation
    Affiliation
    Universidade de Santiago de Compostela
    Abstract

    This paper addresses a mixed-mode CMOS circuit for Hyperdimensional Computing (HDC). HDC is based on the use of binary vectors with thousands dimensions to represent data in a holistic way. During the last years HDC has shown to be a powerful approach to solve classification problems. The proposed circuit architecture in this paper is made up of an array of 128x64 (8192) processing units (PUs) with 1-bit ALU, local memory and connectivity to their 4 nearest neighbors to run the basic operations of HDC, i.e, binding, bundling and permutation. The architecture also includes a module to calculate Hamming distance to address classification. Postlayout simulations of the complete system working on various basic operations are shown.

    Slides
    • HDC8192: A General Purpose Mixed-Signal CMOS Architecture for Massively Parallel Hyperdimensional Computing (application/pdf)