Zeroth and higher-order logic with content addressable memories

Technical digest - International Electron Devices Meeting/Technical digest, pp. 1–4

Abstract

Content Addressable Memories (CAMs) are attracting interest as in-memory computational primitives, thanks to the massively parallel search operation. Multiple flavors of CAMs have been realized with nanoscale memory technology, pushing their performance towards low power and latency. In this work, we demonstrate how to use CAMs for asserting and solving zeroth order and higher-order logic, in the form of Boolean satisfiability (SAT) and satisfiability modulo theories (SMT), respectively. We demonstrate a ~6.5× lower area and ~4× lower energy per search compared with state-of-the-art in-memory optimization problem solvers, such as Hopfield Neural Network (HNN), with up to 175× faster time-to-solution for problems with 150 variables.

Authors 10

1. Giacomo Pedretti

   Hewlett-Packard (United States)

   Affiliation as printed

   Artificial Intelligence Research Lab (AIRL),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Artificial Intelligence Research Lab (AIRL), Milpitas, CA, USA

2. Fabian Böhm

   Hewlett-Packard (United States)

   Affiliation as printed

   Large Scale Integrated Photonics (LSIP),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Large Scale Integrated Photonics (LSIP), Milpitas, CA, USA

3. Mohammad Hizzani Aachen Peter Grünberg Institut (PGI-14) and

   RWTH Aachen University

   Affiliation as printed

   Peter Grünberg Institut (PGI-14) and RWTH Aachen University,Germany

4. Sergey Serebryakov

   Hewlett-Packard (United States)

   Affiliation as printed

   Artificial Intelligence Research Lab (AIRL),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Artificial Intelligence Research Lab (AIRL), Milpitas, CA, USA

5. Dmitri B. Strukov

   University of California, Santa Barbara

   Affiliation as printed

   UC Santa Barbara,Santa Barbara,CA,USA

   UC Santa Barbara, Santa Barbara, CA, USA

6. John Paul Strachan Aachen Peter Grünberg Institut (PGI-14) and

   RWTH Aachen University

   Affiliation as printed

   Peter Grünberg Institut (PGI-14) and RWTH Aachen University,Germany

7. Jim Ignowski

   Hewlett-Packard (United States)

   Affiliation as printed

   Artificial Intelligence Research Lab (AIRL),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Artificial Intelligence Research Lab (AIRL), Milpitas, CA, USA

8. Thomas Van Vaerenbergh

   Hewlett-Packard (United States)

   Affiliation as printed

   Large Scale Integrated Photonics (LSIP),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Large Scale Integrated Photonics (LSIP), Milpitas, CA, USA

9. Raymond G. Beausoleil

   Hewlett-Packard (United States)

   Affiliation as printed

   Large Scale Integrated Photonics (LSIP),Hewlett Packard Labs,Milpitas,CA,USA

   Hewlett Packard Labs, Large Scale Integrated Photonics (LSIP), Milpitas, CA, USA

10. Masoud Mohseni

    Hewlett-Packard (United States)

    Affiliation as printed

    Large Scale Integrated Photonics (LSIP),Hewlett Packard Labs,Milpitas,CA,USA

    Hewlett Packard Labs, Large Scale Integrated Photonics (LSIP), Milpitas, CA, USA