@techreport {822, title = {Design for a Soft Error Resilient Dynamic Task-based Runtime}, journal = {ICL Technical Report}, number = {ICL-UT-14-04}, year = {2014}, month = {2014-11}, publisher = {University of Tennessee}, abstract = {Abstract{\textemdash}As the scale of modern computing systems grows, failures will happen more frequently. On the way to Exascale a generic, low-overhead, resilient extension becomes a desired aptitude of any programming paradigm. In this paper we explore three additions to a dynamic task-based runtime to build a generic framework providing soft error resilience to task-based programming paradigms. The first recovers the application by re-executing the minimum required sub-DAG, the second takes critical checkpoints of the data flowing between tasks to minimize the necessary re-execution, while the last one takes advantage of algorithmic properties to recover the data without re-execution. These mechanisms have been implemented in the PaRSEC task-based runtime framework. Experimental results validate our approach and quantify the overhead introduced by such mechanisms.}, author = {Chongxiao Cao and Thomas Herault and George Bosilca and Jack Dongarra} }