Voltage-driven Building Block for Hardware Belief Networks

Abstract

Probabilistic spin logic (PSL), based on networks of binary stochastic neurons (or p-bits), has been shown to provide a viable framework for many functionalities including Ising computing, Bayesian inference, invertible Boolean logic and image recognition. This paper presents a hardware building block for the PSL architecture, consisting of an embedded MTJ and a capacitive voltage adder of the type used in neuMOS. We use SPICE simulations to show how identical copies of these building blocks (or weighted p-bits) can be interconnected with wires to design and solve a small instance of the NP-complete Subset Sum Problem fully in hardware.

References in corpus (3)

• Stochastic p-bits for Invertible Logic
• Intrinsic optimization using stochastic nanomagnets
• A building block for hardware belief networks

Cited by in corpus (12)

• p-Bits for Probabilistic Spin Logic
• A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms
• Hardware-aware $insitu$ Boltzmann machine learning using stochastic magnetic tunnel junctions
• Energy-efficient stochastic computing with superparamagnetic tunnel junctions
• Implementing Bayesian Networks with Embedded Stochastic MRAM
• Low Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons
• Double Free-Layer Magnetic Tunnel Junctions for Probabilistic Bits
• Correlated fluctuations in spin orbit torque-coupled perpendicular nanomagnets
• Probabilistic Circuits for Autonomous Learning: A simulation study
• A Deep Dive into the Computational Fidelity of High Variability Low Energy Barrier Magnet Technology for Accelerating Optimization and Bayesian Problems
• Hardware implementation of Bayesian network building blocks with stochastic spintronic devices
• Combining Learned Representations for Combinatorial Optimization