A minimally intrusive low-memory approach to resilience for existing transient solvers (Q1736916)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: A minimally intrusive low-memory approach to resilience for existing transient solvers |
scientific article; zbMATH DE number 7042457
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A minimally intrusive low-memory approach to resilience for existing transient solvers |
scientific article; zbMATH DE number 7042457 |
Statements
A minimally intrusive low-memory approach to resilience for existing transient solvers (English)
0 references
26 March 2019
0 references
A novel, minimally intrusive approach to adding fault tolerance to existing complex scientific simulation codes is introduced. The approach in this paper combines the proposed user-level failure mitigation extensions to the Message-Passing Interface (MPI), with the concepts of message-logging and remote inmemory checkpointing. A prototype implementation is applied to Nektar++.
0 references
exascale
0 references
fault tolerance
0 references
message-logging
0 references
MPI
0 references
transient solvers
0 references
parallel computing
0 references
0 references
0 references
0 references
0.80142975
0 references
0.7981602
0 references
0.79085934
0 references
0.7880986
0 references
0.7866721
0 references
0.78395665
0 references
0.7828996
0 references
0.7803269
0 references
