A new paper has been accepted in IEEE Transaction on Circuits and Systems II: https://ieeexplore.ieee.org/abstract/document/9729892
Tony Liu, Amirali Amirsoleimani, Jianxiong Xu, Fabien Alibart, Yann Beilliard, Serge Ecoffey, Dominique Drouin, and Roman Genov, “CODEX: Stochastic Encoding Method to Relax Resistive Crossbar Accelerator Design Requirements“, IEEE TCAS2, 2022.
In this work, a stochastic input encoding scheme (CODEX) is presented that aims to relax the analog-to-digital converter (ADC) design requirements in memristor crossbar systems. CODEX reduces the ADC input range by encoding the input bits using Bernoulli statistics so that the bit-line current distribution becomes a narrow Gaussian. By reducing ADC input range, CODEX can be used to reduce ADC power and area or increase ADC resolution to reduce the number of epochs required for in-situ training. Besides input data encoding, CODEX includes probability thresholding for sparse input data as well as a random re-sampling method for dealing with ADC overflow.