Correlation Manipulating Circuits for Stochastic Computing

TL;DR

This paper introduces novel circuits for managing correlation in stochastic computing, improving accuracy and energy efficiency in SC operations and applications like image processing.

Contribution

It presents new correlation manipulating circuits and demonstrates their advantages over existing techniques in accuracy and energy efficiency.

Findings

Circuits are more accurate than existing methods.

Energy efficiency is improved by up to 3x.

Energy consumption in image processing is reduced by up to 24%.

Abstract

Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or uncorrelated for SC arithmetic to produce accurate results. As a result, a key challenge for designing SC accelerators is manipulating the impact of correlation across SC operations. This paper presents and evaluates a set of novel correlation manipulating circuits to manage correlation in SC computation: a synchronizer, desynchronizer, and decorrelator. We then use these circuits to propose improved SC maximum, minimum, and saturating adder designs. Compared to existing correlation manipulation techniques, our circuits are more accurate and up to 3x more energy efficient. In the context of an image processing pipeline, these circuits can reduce the total energy consumption by up to 24%.