skip to: onlinetools | mainnavigation | content | footer

 

Scalable System Software - Resilience R&D

It is widely accepted that future extreme-scale parallel computing systems will require alternative methods to enable applications to maintain current levels of uninterrupted execution. As the component count of future systems continues to grow, the likelihood of a failure impacting an application grows as well. Researchers in the Scalable System Software department are exploring strategies to increase the resilience and reliability of future extreme-scale systems.

Recent Resilience Publications

Site contact: rbbrigh@sandia.gov