Algorithm Level Timing Speculation for Convolutional Neural Network Accelerators - Archive ouverte HAL Access content directly
Reports (Technical Report) Year : 2018

Algorithm Level Timing Speculation for Convolutional Neural Network Accelerators

Spéculation temporelle algorithmique pour accélérateurs de réseaux de neuro

(1) , (1) , (1)
1

Abstract

In this paper, we propose a technique for improving the efficiency of hardware accelerators based on timing speculation (overclocking) and fault tolerance. We augment the accelerator with a lightweight error detection mechanism to protect against timing errors, enabling aggressive timing speculation. We demonstrate the validity of our approach for the convolution layers in Convolutional Neural Networks (CNN). We present an implementation of a fault-tolerant CNN accelerator combined with the lightweight error detection for convolution layers. The error detection mechanism we have developed works at the algorithm level, based on algebraic properties of the computation, allowing the full implementation to be realized using High-Level Synthesis tools. We use a set of Zybo boards to experimentally demonstrate that overclocking boosts the frequency by 17-36% with low chances of error, and that the infrequent errors can be detected with a negligible overhead (only 1000 LUTs).
Fichier principal
Vignette du fichier
RT-0500.pdf (490.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01811231 , version 1 (08-06-2018)

Identifiers

  • HAL Id : hal-01811231 , version 1

Cite

Thibaut Marty, Tomofumi Yuki, Steven Derrien. Algorithm Level Timing Speculation for Convolutional Neural Network Accelerators. [Technical Report] RT-0500, Univ Rennes, Inria, CNRS, IRISA, France. 2018, pp.1-17. ⟨hal-01811231⟩
614 View
284 Download

Share

Gmail Facebook Twitter LinkedIn More