SPINBIS: Spintronics-based Bayesian inference system with stochastic computing


Journal Article

© 1982-2012 IEEE. Bayesian inference is an effective approach for solving statistical learning problems, especially with uncertainty and incompleteness. However, Bayesian inference is a computing-intensive task whose efficiency is physically limited by the bottlenecks of conventional computing platforms. In this paper, a spintronics-based stochastic computing (SC) approach is proposed for efficient Bayesian inference. The inherent stochastic switching behaviors of spintronic devices are exploited to build a stochastic bitstream generator (SBG) for SC with hybrid CMOS/magnetic tunnel junction (MTJ) circuits design. Aiming to improve the inference efficiency, an SBG sharing strategy is leveraged to reduce the required SBG array scale by integrating a switch network between SBG array and SC logic. A device-to-architecture level framework is proposed to evaluate the performance of spintronics-based Bayesian inference system (SPINBIS). Experimental results on data fusion applications have shown that SPINBIS could improve the energy efficiency about 12 × than MTJ-based approach with 45% design area overhead and about 26 × than FPGA-based approach.

Full Text

Duke Authors

Cited Authors

  • Jia, X; Yang, J; Dai, P; Liu, R; Chen, Y; Zhao, W

Published Date

  • April 1, 2020

Published In

Volume / Issue

  • 39 / 4

Start / End Page

  • 789 - 802

Electronic International Standard Serial Number (EISSN)

  • 1937-4151

International Standard Serial Number (ISSN)

  • 0278-0070

Digital Object Identifier (DOI)

  • 10.1109/TCAD.2019.2897631

Citation Source

  • Scopus