Robustness and scalability of p-bits implemented with low energy barrier nanomagnets

TL;DR

This paper demonstrates that p-bits implemented with low energy barrier nanomagnets are robust against device-to-device geometric variations, maintaining their programmability and scalability for probabilistic computing tasks.

Contribution

The study shows that geometric device variations do not significantly impair the ability to program p-bits, supporting their scalability in large systems.

Findings

Programming probability is unaffected by device variations.

Increasing spin polarization enhances robustness.

Probabilistic computing with LBMs is scalable and error-tolerant.

Abstract

Probabilistic (p-) bits implemented with low energy barrier nanomagnets (LBMs) have recently gained attention because they can be leveraged to perform some computational tasks very efficiently. Although more error-resilient than Boolean computing, p-bit based computing employing LBMs is, however, not completely immune to defects and device-to-device variations. In some tasks (e.g. binary stochastic neurons for machine learning and p-bits for population coding), extended defects, such as variation of the LBM thickness over a significant fraction of the surface, can impair functionality. In this paper, we have examined if unavoidable geometric device-to-device variations can have a significant effect on one of the most critical requirements for probabilistic computing, namely the ability to "program" probability with an external agent, such as a spin-polarized current injected into the LBM. We found that the programming ability is fortunately not lost due to reasonable device-to-device variations. The little variation in the probability versus current characteristic that reasonable device variability causes can be suppressed further by increasing the spin polarization of the current. This shows that probabilistic computing with LBMs is robust against small geometric variations, and hence will be "scalable" to a large number of p-bits.