CAPSL
Probabilistic Spin Logic for Low-Energy Boolean and Non-Boolean Computing

Joerg Appenzeller, Purdue University

Among many proposed new device concepts and architectural designs, there is increasing interest in a fundamentally different form of brain-like logic based on probabilistic inference that is far more effective and energy efficient in dealing with the problems of search and recognition posed by the ever-increasing amounts and demands of "big data." The Boltzmann Machine (BM) proposed by Ackley, Hinton, and Sejnowski is a type of parallel constraint satisfaction network capable of learning the underlying constraints that characterize a domain through examples from the domain. Herein we propose a stochastic nanomagnet based hardware unit, which we call a "p-bit", as a primitive BM computing element. Our unique p-bit, simply consisting of an input and a low energy barrier (low kBT) nanomagnet, has binary states and adopts these states as a probabilistic function of its input states and their weights. This elegant, simple hardware form of a random number generator is the key element to distinguish our proposal from other hardware implementations of BMs and will be the focus of the center’s study on Probabilistic Spin Logic Devices (PSL).

CAPSL Metrics

  1. Current

    7 Research Tasks
    4 Universities
    14 Students
    7 Faculty Researchers
    5 Liaison Personnel
  2. This Year

    7 Task Starts
    10 Research Publications
Updated: 19-Jun-2018, 12:05 a.m. ET

4819 Emperor Blvd, Suite 300 Durham, NC 27703 Voice: (919) 941-9400 Fax: (919) 941-9450

Important Information for the SRC website. This site uses cookies to store information on your computer. By continuing to use our site, you consent to our cookies. If you are not happy with the use of these cookies, please review our Cookie Policy to learn how they can be disabled. By disabling cookies, some features of the site will not work.