@inproceedings {icl:153, title = {Fault Tolerant Communication Library and Applications for High Performance Computing}, journal = {Los Alamos Computer Science Institute (LACSI) Symposium 2003 (presented)}, year = {2003}, month = {2003-10}, address = {Santa Fe, NM}, keywords = {ftmpi, lacsi}, author = {Graham Fagg and Edgar Gabriel and Zizhong Chen and Thara Angskun and George Bosilca and Antonin Bukovsky and Jack Dongarra} } @inproceedings {icl:144, title = {A Fault-Tolerant Communication Library for Grid Environments}, journal = {17th Annual ACM International Conference on Supercomputing (ICS{\textquoteright}03) International Workshop on Grid Computing and e-Science}, year = {2003}, month = {2003-06}, address = {San Francisco}, keywords = {ftmpi, lacsi}, author = {Edgar Gabriel and Graham Fagg and Antonin Bukovsky and Thara Angskun and Jack Dongarra} } @inproceedings {icl:203, title = {Fault Tolerant MPI for the HARNESS Meta-Computing System}, journal = {Proceedings of International Conference of Computational Science - ICCS 2001, Lecture Notes in Computer Science}, volume = {2073}, year = {2001}, month = {2001-00}, pages = {355-366}, publisher = {Springer Verlag}, address = {Berlin}, keywords = {ftmpi, harness}, doi = {10.1007/3-540-45545-0_44}, author = {Graham Fagg and Antonin Bukovsky and Jack Dongarra}, editor = {Benjoe A. Juliano and R. Renner and K. Tan} } @article {icl:86, title = {HARNESS and Fault Tolerant MPI}, journal = {Parallel Computing}, volume = {27}, number = {11}, year = {2001}, month = {2001-01}, pages = {1479-1496}, author = {Graham Fagg and Antonin Bukovsky and Jack Dongarra} }