Isomorphic, Sparse MPI-like Collective Communication Operations for Parallel Stencil Computations.
Jesper Larsson TräffFelix Donatus LübbeAntoine RougierSascha HunoldPublished in: EuroMPI (2015)
Keyphrases
- shared memory
- parallel implementation
- message passing interface
- distributed memory
- matrix multiplication
- parallel computing
- parallelization strategy
- parallel programming
- parallel computation
- message passing
- parallel algorithm
- massively parallel
- multithreading
- ibm sp
- parallel computers
- processing units
- parallel processing
- sparse data
- high performance computing
- general purpose
- communication systems
- packet switched
- high dimensional
- computer architecture
- communication protocol
- parallel architecture
- parallel architectures
- processing elements
- communication networks
- interconnection networks
- sparse coding
- computer networks
- sparse representation
- information exchange
- concurrent processes
- data acquisition
- mobile devices