Efficient OpenMP parallelization to a complex MPI parallel magnetohydrodynamics code.
Hongyang ZhouGábor TóthPublished in: J. Parallel Distributed Comput. (2020)
Keyphrases
- shared memory
- parallel execution
- message passing interface
- distributed memory
- parallel architectures
- parallel programming
- coarse grained
- parallel computing
- message passing
- parallel algorithm
- address space
- parallel processing
- high performance computing
- low overhead
- parallel implementation
- parallel machines
- massively parallel
- multi processor
- parallel computation
- computationally expensive
- multi core systems
- computationally intensive
- parallel computers
- complex data
- complex systems
- parallel architecture
- single processor
- multi core processors
- real world
- high level
- multiprocessor systems
- computationally efficient
- general purpose
- cost model
- efficient implementation
- fine grained
- parallelization strategy