@inproceedings {icl:679, title = {A Checkpoint-on-Failure Protocol for Algorithm-Based Recovery in Standard MPI}, journal = {18th International European Conference on Parallel and Distributed Computing (Euro-Par 2012) (Best Paper Award)}, year = {2012}, month = {2012-08}, publisher = {Springer-Verlag}, address = {Rhodes, Greece}, author = {Wesley Bland and Peng Du and Aurelien Bouteiller and Thomas Herault and George Bosilca and Jack Dongarra}, editor = {Christos Kaklamanis and Theodore Papatheodorou and Paul Spirakis} }