Conference proceeding
Investigating the Impact of High-Level Software Design on Low-Level Hardware Fault Resilience
2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S), pp.163-167
06/2023
DOI: 10.1109/DSN-S58398.2023.00044
Abstract
Silent Data Corruptions (SDCs) have become an insurmountable issue that threatens the system reliability. General strategies for protecting programs from SDCs, such as dual modular redundancy, incur intolerable overheads. Another strategy is Algorithm-Based Fault Tolerance which is highly bounded to the specific algorithm and hard to generalize. In this study, we find different implementations of the same algorithm may lead to very different SDC probabilities. We conduct a characterization study to quantify the differences and investigate the root causes. The insights we derive could help and guide the developers in software engineering domain to design programs that is naturally resilient.
Details
- Title: Subtitle
- Investigating the Impact of High-Level Software Design on Low-Level Hardware Fault Resilience
- Creators
- Bohan Zhang - University of IowaLishan Yang - George Mason UniversityGuanpeng Li - University of IowaHui Xu - Fudan University
- Resource Type
- Conference proceeding
- Publication Details
- 2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S), pp.163-167
- Publisher
- IEEE
- DOI
- 10.1109/DSN-S58398.2023.00044
- eISSN
- 2833-292X
- Language
- English
- Date published
- 06/2023
- Academic Unit
- Computer Science
- Record Identifier
- 9984459654702771
Metrics
7 Record Views