Special Session: Approximation and Fault Resiliency of DNN Accelerators

Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in many scenarios, including safety-critical applications such as autonomous driving. In this context, besides energy efficiency and performance, reliability plays a crucial role since a system failure can jeopardize...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE 41st VLSI Test Symposium (VTS) pp. 1 - 10
Main Authors Ahmadilivani, Mohammad Hasan, Barbareschi, Mario, Barone, Salvatore, Bosio, Alberto, Daneshtalab, Masoud, Torca, Salvatore Della, Gavarini, Gabriele, Jenihhin, Maksim, Raik, Jaan, Ruospo, Annachiara, Sanchez, Ernesto, Taheri, Mahdi
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.04.2023
Subjects
approximate computing
Circuit faults
Deep learning
deep neural networks
fault emulation
Hardware
Integrated circuit modeling
Neural networks
Performance evaluation
reliability
resiliency assessment
Very large scale integration
Online AccessGet full text

Cover

More Information
Summary:Deep Learning, and in particular, Deep Neural Network (DNN) is nowadays widely used in many scenarios, including safety-critical applications such as autonomous driving. In this context, besides energy efficiency and performance, reliability plays a crucial role since a system failure can jeopardize human life. As with any other device, the reliability of hardware architectures running DNNs has to be evaluated, usually through costly fault injection campaigns. This paper explores approximation and fault resiliency of DNN accelerators. We propose to use approximate (AxC) arithmetic circuits to agilely emulate errors in hardware without performing fault injection on the DNN. To allow fast evaluation of AxC DNN, we developed an efficient GPU-based simulation framework. Further, we propose a fine-grain analysis of fault resiliency by examining fault propagation and masking in networks.
ISSN:2375-1053
DOI:10.1109/VTS56346.2023.10140043