@inproceedings {979, title = {Failure Detection and Propagation in HPC Systems}, journal = { Proceedings of the The International Conference for High Performance Computing, Networking, Storage and Analysis (SC{\textquoteright}16)}, year = {2016}, month = {2016-11}, pages = {27:1-27:11}, publisher = {IEEE Press}, address = {Salt Lake City, Utah}, keywords = {failure detection, fault-tolerance, MPI}, isbn = {978-1-4673-8815-3}, url = {http://dl.acm.org/citation.cfm?id=3014904.3014941}, author = {George Bosilca and Aurelien Bouteiller and Amina Guermouche and Thomas Herault and Yves Robert and Pierre Sens and Jack Dongarra} }