Investigating the Impact of Radiation-Induced Soft Errors on the Reliability of Approximate Computing Systems
Matana Luza, L., Söderström, D., Tsiligiannis, G., Puchner, H., Cazzaniga, C., Sanchez, E., Bosio, A., & Dilillo, L. (2020). Investigating the Impact of Radiation-Induced Soft Errors on the Reliability of Approximate Computing Systems. In L. Dilillo, M. Psarakis, & T. Siddiqua (Eds.), DFT 2020 : 33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems. IEEE. Proceedings : IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems, 2020. https://doi.org/10.1109/DFT50435.2020.9250865
Published in
Proceedings : IEEE International Symposium on Defect and Fault Tolerance in VLSI SystemsDate
2020Copyright
© 2020 IEEE
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.
Publisher
IEEEParent publication ISBN
978-1-7281-9458-5Conference
IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology SystemsIs part of publication
DFT 2020 : 33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology SystemsISSN Search the Publication Forum
1550-5774Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/68030575
Metadata
Show full item recordCollections
Related funder(s)
European CommissionFunding program(s)
MSCA Innovative Training Networks (ITN)
The content of the publication reflects only the author’s view. The funder is not responsible for any use that may be made of the information it contains.
License
Except where otherwise noted, this item's license is described as In Copyright