Verifying quantitative reliability for programs that execute on unreliable hardware
Michael Carbin, Saša Misailovíc, Martin Rinard · 2013
Emerging high-performance architectures are anticipated to contain unreliable components that may exhibit soft errors, which silently corrupt the results of computations. Full detection and masking of soft errors is challenging, expensive, and, for some applications, unnecessary. For example, approximate computing applications (such as multimedia processing, machine learning, and big data analytics) can often naturally tolerate soft errors.
Cited by 222 works. doi:10.1145/2509136.2509546 Open-access PDF
Authors
References
- Guarded commands, nondeterminacy and formal derivation of programs
- Designing programs that check their work
- Modeling the effect of technology trends on the soft error rate of combinational logic
- Razor: a low-power pipeline based on circuit-level timing speculation
- Self-testing/correcting with applications to numerical problems
- Neural Acceleration for General-Purpose Approximate Programs
- Translation validation
- Enhancing server availability and security through failure-oblivious computing
- SWIFT: Software Implemented Fault Tolerance
- Semantics of probabilistic programs