by Han, Hyuck, Jung, Hyungsoo, Kim, JaiWug, Lee, Jongpil, Yu, Youngjin, Kim, ShinGyu and Yeom, HeonY.
Reference:
SHIELD: A Fault-Tolerant MPI for an Infiniband Cluster (Han, Hyuck, Jung, Hyungsoo, Kim, JaiWug, Lee, Jongpil, Yu, Youngjin, Kim, ShinGyu and Yeom, HeonY.), Chapter in High Performance Computing and Communications (Gerndt, Michael, Kranzlmüller, Dieter, eds.), Springer Berlin Heidelberg, volume 4208, 2006.
Bibtex Entry:
@incollection{han2006shield,
year={2006},
isbn={978-3-540-39368-9},
booktitle={High Performance Computing and Communications},
volume={4208},
series={Lecture Notes in Computer Science},
editor={Gerndt, Michael and Kranzlmüller, Dieter},
doi={10.1007/11847366_90},
title={SHIELD: A Fault-Tolerant MPI for an Infiniband Cluster},
url={http://dx.doi.org/10.1007/11847366_90},
publisher={Springer Berlin Heidelberg},
keywords={Checkpoint; Consistent recovery; Fault-tolerance; MPI; Infiniband},
author={Han, Hyuck and Jung, Hyungsoo and Kim, JaiWug and Lee, Jongpil and Yu, Youngjin and Kim, ShinGyu and Yeom, HeonY.},
pages={874-883},
language={English}
}