4.6 Article

On the Safe Deployment of Matrix Multiplication in Massively Parallel Safety-Related Systems

Related references

Note: Only part of the references are listed.
Article Computer Science, Hardware & Architecture

Making Convolutions Resilient Via Algorithm-Based Error Detection Techniques

Siva Kumar Sastry Hari et al.

Summary: This article focuses on algorithmically verifying convolutions in CNNs and proposes variations of algorithm-based error detection (ABED) techniques. The results show that ABED can efficiently detect transient hardware errors that may corrupt the output, with low runtime overhead.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2022)

Article Computer Science, Hardware & Architecture

Towards functional safety compliance of matrix-matrix multiplication for machine learning-based autonomous systems

Javier Fernandez et al.

Summary: This paper discusses the safety measures taken when using machine learning libraries on multi-core processors in autonomous systems to ensure system reliability and safety during operation. Recommended programming practices, including error avoidance and the use of checksum mechanisms to control runtime errors, are applied, and the impact of these measures on performance as well as the achieved diagnostic coverage are evaluated.

JOURNAL OF SYSTEMS ARCHITECTURE (2021)

Proceedings Paper Computer Science, Hardware & Architecture

Combining Architectural Simulation and Software Fault Injection for a Fast and Accurate CNNs Reliability Evaluation on GPUs

Josie E. Rodriguez Condia et al.

Summary: This study combines the accuracy of microarchitectural simulation with the speed of software fault injection to evaluate the reliability of CNNs executed in GPUs. By injecting faults on critical and user-hidden modules in GPUs and propagating the effects to CNNs using software injection, the study focuses on analyzing the impact of faults on hidden modules on the overall CNN execution.

2021 IEEE 39TH VLSI TEST SYMPOSIUM (VTS) (2021)

Article Computer Science, Information Systems

A Selective Mitigation Technique of Soft Errors for DNN Models Used in Healthcare Applications: DenseNet201 Case Study

Khalid Adam et al.

Summary: The paper introduces a selective mitigation technique to improve the reliability of DNN models in healthcare systems, demonstrating effectiveness through in-depth analysis and protection of sensitive portions to reduce error rates.

IEEE ACCESS (2021)

Article Computer Science, Theory & Methods

Multi-core Devices for Safety-critical Systems: A Survey

Jon Perez Cerrolaza et al.

ACM COMPUTING SURVEYS (2020)

Article Computer Science, Hardware & Architecture

GMAI: Understanding and Exploiting the Internals of GPU Resource Allocation in Critical Systems

Alejandro J. Calderon et al.

ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS (2020)

Proceedings Paper Computer Science, Hardware & Architecture

Dissecting the CUDA scheduling hierarchy: a Performance and Predictability Perspective

Ignacio Sanudo Olmedo et al.

2020 IEEE REAL-TIME AND EMBEDDED TECHNOLOGY AND APPLICATIONS SYMPOSIUM (RTAS 2020) (2020)

Proceedings Paper Automation & Control Systems

Evaluating Convolutional Neural Networks Reliability depending on their Data Representation

Annachiara Ruospo et al.

2020 23RD EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD 2020) (2020)

Article Engineering, Electrical & Electronic

Deep Collaborative Attention Network for Hyperspectral Image Classification by Combining 2-D CNN and 3-D CNN

Hao Guo et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2020)

Article Computer Science, Information Systems

A Survey of Deep Learning-Based Object Detection

Licheng Jiao et al.

IEEE ACCESS (2019)

Article Engineering, Mechanical

Designing a multi-scroll chaotic system by operating Logistic map with fractal process

Nabil Ben Slimane et al.

NONLINEAR DYNAMICS (2017)

Article Computer Science, Hardware & Architecture

The Effectiveness of Checksums for Embedded Control Networks

Theresa C. Maxino et al.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2009)

Article Computer Science, Hardware & Architecture

Software-based self-testing of embedded processors

N Kranitis et al.

IEEE TRANSACTIONS ON COMPUTERS (2005)