학술논문

CODEX: Stochastic Encoding Method to Relax Resistive Crossbar Accelerator Design Requirements
Document Type
Periodical
Source
IEEE Transactions on Circuits and Systems II: Express Briefs IEEE Trans. Circuits Syst. II Circuits and Systems II: Express Briefs, IEEE Transactions on. 69(8):3356-3360 Aug, 2022
Subject
Components, Circuits, Devices and Systems
Memristors
Encoding
Virtual machine monitors
Voltage
Training
Matrices
Current distribution
Memristor
analog-to-digital converter
vector-matrix multiplication
inference
deep neural network
Language
ISSN
1549-7747
1558-3791
Abstract
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. CODEX is evaluated on CIFAR-10 dataset image classification and reconstruction, sentiment classification, and audio classification. The results show an averaged 68.5% reduction in ADC power, 35.5% reduction in ADC area, and 25.8% reduction in training epochs required for in-situ training when applied to the state-of-the-art ISAAC and PUMA accelerators.