@article {icl:490, title = {Algorithmic Based Fault Tolerance Applied to High Performance Computing}, journal = {Journal of Parallel and Distributed Computing}, volume = {69}, year = {2009}, month = {2009-00}, pages = {410-416}, author = {Jack Dongarra and George Bosilca and Remi Delmas and Julien Langou} } @techreport {icl:426, title = {Algorithmic Based Fault Tolerance Applied to High Performance Computing}, journal = {University of Tennessee Computer Science Technical Report, UT-CS-08-620 (also LAPACK Working Note 205)}, year = {2008}, month = {2008-01}, author = {George Bosilca and Remi Delmas and Jack Dongarra and Julien Langou} }