Analyzing the Reliability of Alternative Convolution Implementations for Deep Learning Applications
- Resource Type
- Conference
- Authors
- Bolchini, Cristiana; Cassano, Luca; Miele, Antonio; Nazzari, Alessandro; Passarello, Dario
- Source
- 2023 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT) Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT), 2023 IEEE International Symposium on. :1-6 Oct, 2023
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
General Topics for Engineers
Deep learning
Fault tolerance
Graphical models
Convolution
Fault tolerant systems
Single event upsets
Graphics processing units
Convolutional Neural Networks
Deep Learning
Error Simulation
Fault Injection
Reliability Analysis
- Language
- ISSN
- 2765-933X
Convolution represents the core of Deep Learning (DL) applications, enabling the automatic extraction of features from raw input data. Several implementations of the convolution have been proposed. The impact of these different implementations on the performance of DL applications has been studied. However, no specific reliability-related analysis has been carried out. In this paper, we apply the CLASSES cross-layer reliability analysis methodology for an in-depth study aimed at: i) analyzing and characterizing the effects of Single Event Upsets occurring in Graphics Processing Units while executing the convolution operators; and ii) identifying whether a convolution implementation is more robust than others. The outcomes can then be exploited to tailor better hardening schemes for DL applications to improve reliability and reduce overhead.