Data Driven Optimizations for MTJ based Stochastic Computing

TL;DR

This paper proposes an energy-efficient, data-sensitive MTJ-based stochastic number generator for stochastic computing, demonstrating significant energy savings in multiplication operations compared to baseline designs.

Contribution

It introduces a novel, energy-efficient MTJ-based SNG tailored for stochastic computing, emphasizing data sensitivity and practical benefits.

Findings

Significant energy savings in multiplication circuits

Effective data-sensitive design for MTJ-based SNGs

Potential for improved stochastic computing efficiency

Abstract

Stochastic computing, a form of computation with probabilities, presents an alternative to conventional arithmetic units. Magnetic Tunnel Junctions (MTJs), which exhibit probabilistic switching, have been explored as Stochastic Number Generators (SNGs). We provide a perspective of the energy requirements of such an application and design an energy-efficient and data-sensitive MTJ-based SNG. We discuss its benefits when used for stochastic computations, illustrating with the help of a multiplier circuit, in terms of energy savings when compared to computing with the baseline MTJ-SNG.