Developing a High Performance Software Library with MPI and CUDA for Matrix Computations.
Bogdan OanceaTudorel AndreiPublished in: CoRR (2015)
Keyphrases
- parallel implementation
- general purpose
- software systems
- parallel computing
- source code
- parallel algorithm
- parallel computers
- distributed memory
- parallel computation
- linear algebra
- software development
- shared memory
- software tools
- design and implementation issues
- scientific computing
- parallel programming
- message passing
- computer systems
- software design
- information systems
- efficient implementation
- test cases
- user interface