A review paper titled “Review of Magnetic Tunnel Junctions for Stochastic Computing” was published by researchers at University of Minnesota Twin Cities. Funding agencies include Semiconductor Research Corporation (SRC), CAPSL, NIST, DARPA and others.
Abstract:
“Modern computing schemes require large circuit areas and large energy consumption for neuromorphic computing applications, such as recognition, classification, and prediction. This is because these tasks require parallel processing on large datasets. Stochastic computing (SC) is a promising alternative to conventional binary computing schemes due to its low area cost, low processing power, and robustness to noise. However, the large area and energy costs for random number generation with CMOS-based circuits make SC impractical for most hardware implementations. For this reason, beyond-CMOS approaches to random number generation have been investigated in recent years. Spintronics is one of the most promising approaches due to the intrinsic stochasticity of the magnetic tunnel junction (MTJ). In this review article, we provide an overview of the literature published in recent years investigating the tunable, intrinsic stochasticity of MTJs and proposing practical methods for random number generation using spintronic hardware.”
Find the technical paper here. Published December 2022.
B. R. Zink, Y. Lv and J. -P. Wang, “Review of Magnetic Tunnel Junctions for Stochastic Computing,” in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, vol. 8, no. 2, pp. 173-184, Dec. 2022, doi: 10.1109/JXCDC.2022.3227062. Open access through Creative Commons License.
Leave a Reply