Investigating the Impact of Radiation-Induced Soft Errors on the Reliability of Approximate Computing Systems

Year of publication

2020

Authors

Matana Luza, Lucas; Söderström, Daniel; Tsiligiannis, Georgios; Puchner, Helmut; Cazzaniga, Carlo; Sanchez, Ernesto; Bosio, Alberto; Dilillo, Luigi

Abstract

Approximate Computing (AxC) is a well-known paradigm able to reduce the computational and power overheads of a multitude of applications, at the cost of a decreased accuracy. Convolutional Neural Networks (CNNs) have proven to be particularly suited for AxC because of their inherent resilience to errors. However, the implementation of AxC techniques may affect the intrinsic resilience of the application to errors induced by Single Events in a harsh environment. This work introduces an experimental study of the impact of neutron irradiation on approximate computing techniques applied on the data representation of a CNN.

Organizations and authors

University of Jyväskylä

Söderström Daniel

Publication type

Publication format

Article

Parent publication type

Conference

Article type

Audience

Scientific

Peer-reviewed

Non Peer-Reviewed

MINEDU's publication type classification code

B3 Article in conference proceedings (non-peer-reviewed)

Publication channel information

Open access

Open access in the publisher’s service

Self-archived

Yes

Other information

Fields of science

Physical sciences; Electronic, automation and communications engineering, electronics

Keywords

[object Object],[object Object],[object Object]

Publication country

United States

Internationality of the publisher

International

Language

English

International co-publication

Yes

Co-publication with a company

Yes

DOI

10.1109/DFT50435.2020.9250865

The publication is included in the Ministry of Education and Culture’s Publication data collection

Yes