Local rollback for resilient MPI applications with application-level checkpointing and message logging.
Nuria LosadaGeorge BosilcaAurélien BouteillerPatricia GonzálezMaría J. MartínPublished in: Future Gener. Comput. Syst. (2019)
Keyphrases
- application level
- low overhead
- main memory databases
- shared memory
- operating system
- parallel algorithm
- quality of service
- network management
- parallel implementation
- message passing
- main memory
- overlay network
- bottle neck
- concurrency control
- load balancing
- high reliability
- network services
- virtual machine
- fault tolerance
- distributed databases
- log records
- parallel computing
- message passing interface
- peer to peer
- b tree
- high performance computing
- computer systems
- real time