@inproceedings{villamayor2017fault, title={A Fault Tolerance Manager with Distributed Coordinated Checkpoints for Automatic Recovery}, author={Villamayor, Jorge and Rexachs, Dolores and Luque, Emilio}, booktitle={H2017 Int. Conf. on High Performance Computing \& Simulation (HPCS-17)}, pages={452--459}, year={July, 2017}, organization={IEEE} }