Hybrid MPI and CUDA Parallelization for CFD Applications on Multi-GPU HPC Clusters.
Jianqi LaiHang YuZhengyu TianHua LiPublished in: Sci. Program. (2020)
Keyphrases
- parallel implementation
- message passing interface
- parallel computing
- high performance computing
- shared memory
- compute unified device architecture
- parallel programming
- parallel computation
- parallel implementations
- parallel algorithm
- graphics processing units
- clustering algorithm
- distributed memory
- massively parallel
- gpu implementation
- parallel execution
- parallel tree search
- graphic processing unit
- computing systems
- parallel computers
- parallel processing
- self organizing maps
- scientific computing
- hierarchical clustering
- general purpose
- cpu implementation
- message passing
- cluster analysis
- computer systems
- coarse grained
- data points
- gpu accelerated
- real time