FT-BLAS: a high performance BLAS implementation with online fault tolerance.
Yujia ZhaiElisabeth GiemQuan FanKai ZhaoJinyang LiuZizhong ChenPublished in: ICS (2021)
Keyphrases
- fault tolerance
- highly optimized
- fault tolerant
- scientific computing
- high performance computing
- linear algebra
- distributed systems
- response time
- load balancing
- distributed computing
- special purpose
- general purpose
- high availability
- replicated databases
- group communication
- high scalability
- fault management
- mobile agents
- peer to peer
- data replication
- clustering algorithm
- database replication
- component failures
- computer architecture
- computing environments
- digital libraries