Soft Error Assessment Methodology
This Chapter details the adopted fault injection approaches and their fault injection modules,
used to evaluate the soft error resilience of single or multi-core systems (Sect. 4.1). In this …
used to evaluate the soft error resilience of single or multi-core systems (Sect. 4.1). In this …
[图书][B] Early soft error reliability assessment of convolutional neural networks executing on resource-constrained IoT edge devices
This book describes an extensive and consistent soft error assessment of convolutional
neural network (CNN) models from different domains through more than 14.8 million fault …
neural network (CNN) models from different domains through more than 14.8 million fault …
Early Soft Error Consistency Assessment
This Chapter presents the evaluation of the soft error assessment consistency considering
the SOFIA OVPsim-FIM wrt RTL and gem5 FIMs. This Book contribution lead to the …
the SOFIA OVPsim-FIM wrt RTL and gem5 FIMs. This Book contribution lead to the …
FireNN: Neural networks reliability evaluation on hybrid platforms
Modern neural network complexity has grown dramatically in recent years, leading to the
adoption of hardware-accelerated solutions to cope with the computational power required …
adoption of hardware-accelerated solutions to cope with the computational power required …
DeBaTE-FI: A Debugger-Based Fault Injector Infrastructure for IoT Soft Error Reliability Assessment
A Hanneman, J Gava, V Bandeira… - 2023 IEEE 9th World …, 2023 - ieeexplore.ieee.org
This work presents DeBaTE-FI as a scalable tool to aid in assessing the susceptibility of
embedded IoT systems to soft errors. DeBaTE-FI includes a method that allows precise …
embedded IoT systems to soft errors. DeBaTE-FI includes a method that allows precise …
Machine Learning Applied to Soft Error Assessment in Multicore Systems
The last chapter explores how machine learning techniques can be applied to soft error
assessment in multicore systems, especially considering the extensive fault injection …
assessment in multicore systems, especially considering the extensive fault injection …
Using machine learning techniques to evaluate multicore soft error reliability
Virtual platform frameworks have been extended to allow earlier soft error analysis of more
realistic multicore systems (ie, real software stacks and state-of-the-art ISAs). The high …
realistic multicore systems (ie, real software stacks and state-of-the-art ISAs). The high …
Pros and cons of fault injection approaches for the reliability assessment of deep neural networks
In the last years, the adoption of Artificial Neural Networks (ANNs) in safety-critical
applications has required an in-depth study of their reliability. For this reason, the research …
applications has required an in-depth study of their reliability. For this reason, the research …
Assessing convolutional neural networks reliability through statistical fault injections
Assessing the reliability of modern devices running CNN algorithms is a very difficult task.
Actually, the complexity of the state-of-the-art devices makes exhaustive Fault Injection (FI) …
Actually, the complexity of the state-of-the-art devices makes exhaustive Fault Injection (FI) …
Soft error reliability predictor based on a Deep Feedforward Neural Network
DR Falcó, A Serrano-Cases… - 2020 IEEE Latin …, 2020 - ieeexplore.ieee.org
Statistical fault injection is a widely used methodology to early evaluation of soft error
reliability of microprocessor based systems. Due to the increasing complexity of the software …
reliability of microprocessor based systems. Due to the increasing complexity of the software …