MPI-CUDA parallel linear solvers for block-tridiagonal matrices in the context of SLEPc's eigensolvers.
Alejandro Lamas DaviñaJosé E. RománPublished in: Parallel Comput. (2018)
Keyphrases
- parallel implementation
- parallel programming
- parallel algorithm
- shared memory
- parallel computing
- message passing interface
- linear systems
- parallel computation
- general purpose
- coefficient matrix
- massively parallel
- parallelization strategy
- contextual information
- parallel processing
- distributed memory
- parallel computers
- sat solvers
- high performance computing
- motion estimation
- real time
- message passing
- closed form
- compute unified device architecture
- symmetric matrices