6533b85cfe1ef96bd12bca86

RESEARCH PRODUCT

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

Alberto BosioLuigi DililloDaniel SoderstromErnesto SanchezLucas Matana LuzaGeorgios TsiligiannisHelmut PuchnerCarlo Cazzaniga

subject

Approximate computingComputer scienceReliability (computer networking)Radiation effectsRadiation induced02 engineering and technologyneuroverkotExternal Data Representation01 natural sciencesConvolutional neural networkSoftwareHardware020204 information systems0103 physical sciences0202 electrical engineering electronic engineering information engineering[SPI.NANO]Engineering Sciences [physics]/Micro and nanotechnologies/MicroelectronicsResilience (network)mikroprosessoritNeutronsResilience010308 nuclear & particles physicsbusiness.industryReliabilityApproximate computingPower (physics)[SPI.TRON]Engineering Sciences [physics]/ElectronicsComputer engineeringsäteilyfysiikka[INFO.INFO-ES]Computer Science [cs]/Embedded SystemsbusinessSoftware

description

International audience; 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.

yearjournalcountryeditionlanguage
2020-10-19
10.1109/dft50435.2020.9250865https://hal-lirmm.ccsd.cnrs.fr/lirmm-03025736/document