A fault tolerant self-scheduling scheme for parallel loops on shared memory systems.
Yizhuo WangAlexandru NicolauRosario CammarotaAlexander V. VeidenbaumPublished in: HiPC (2012)
Keyphrases
- shared memory
- fault tolerant
- distributed systems
- message passing
- fault tolerance
- parallel machines
- distributed memory
- interconnection networks
- parallel algorithm
- heterogeneous platforms
- parallel computing
- parallel architecture
- safety critical
- multi processor
- parallel programming
- parallel architectures
- load balancing
- parallel computers
- address space
- multi core systems
- read and write operations
- parallel execution
- parallel computation
- operating system
- massively parallel
- shared memory multiprocessors
- data parallelism
- compute unified device architecture
- higher order
- graphic processing unit
- bayesian networks