DOE OSTI · code-45238
Fenix, A Fault Tolerant Programming Framework for MPI Applications
Abstract
Fenix provides APIs to allow the users to add fault tolerance capability to MPI-based parallel programs in a transparent manner. Fenix-enabled programs can run through process failures during program execution using a pool of spare processes accommodated by Fenix.
Keep this discovery
Explore connections, maps & timelines
Gamel, Marc, Teranihi, Keita, Valenzuela, Eric, Heroux, Michael, Parashar, Manish, Whitlock, Matthew. 2016-09-27. Fenix, A Fault Tolerant Programming Framework for MPI Applications. https://doi.org/10.11578/dc.20201001.7
Cite the original work for its findings. Save a collection to share your selection of sources.