BSC: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML

TL;DR

This paper introduces BSC, a novel block-based stochastic computing architecture for TinyML that improves accuracy and reduces power consumption by leveraging high data parallelism and optimized arithmetic units.

Contribution

The paper proposes a new BSC architecture with block division, optimized arithmetic units, and a global optimization scheme for better latency-power trade-offs in TinyML.

Findings

BSC achieves over 10% higher accuracy on ML tasks.

BSC reduces power consumption by over 6 times.

Experimental results demonstrate improved performance over existing designs.

Abstract

Along with the progress of AI democratization, machine learning (ML) has been successfully applied to edge applications, such as smart phones and automated driving. Nowadays, more applications require ML on tiny devices with extremely limited resources, like implantable cardioverter defibrillator (ICD), which is known as TinyML. Unlike ML on the edge, TinyML with a limited energy supply has higher demands on low-power execution. Stochastic computing (SC) using bitstreams for data representation is promising for TinyML since it can perform the fundamental ML operations using simple logical gates, instead of the complicated binary adder and multiplier. However, SC commonly suffers from low accuracy for ML tasks due to low data precision and inaccuracy of arithmetic units. Increasing the length of the bitstream in the existing works can mitigate the precision issue but incur higher latency. In this work, we propose a novel SC architecture, namely Block-based Stochastic Computing (BSC). BSC divides inputs into blocks, such that the latency can be reduced by exploiting high data parallelism. Moreover, optimized arithmetic units and output revision (OUR) scheme are proposed to improve accuracy. On top of it, a global optimization approach is devised to determine the number of blocks, which can make a better latency-power trade-off. Experimental results show that BSC can outperform the existing designs in achieving over 10% higher accuracy on ML tasks and over 6 times power reduction.