A Parallel Bitstream Generator for Stochastic Computing

TL;DR

This paper introduces a parallel bitstream generator for stochastic computing that significantly reduces hardware area and energy consumption, enhancing the practicality of SC in neural networks and image processing.

Contribution

A novel parallel bitstream generator design that operates with a single clock, drastically reducing hardware area and energy use compared to traditional methods.

Findings

2.5x reduction in hardware area

712x decrease in energy consumption

Effective for neural networks and image processing applications

Abstract

Stochastic computing (SC) presents high error tolerance and low hardware cost, and has great potential in applications such as neural networks and image processing. However, the bitstream generator, which converts a binary number to bitstreams, occupies a large area and energy consumption, thus weakening the superiority of SC. In this paper, we propose a novel technique for generating bitstreams in parallel, which needs only one clock for conversion and significantly reduces the hardware cost. Synthesis results demonstrate that the proposed parallel bitstream generator improves 2.5x area and 712x energy consumption.