Compression and load balancing for efficient sparse matrix-vector product on multicore processors and graphics processing units.
José Ignacio AliagaHartwig AnztThomas GrützmacherEnrique S. Quintana-OrtíAndrés E. TomásPublished in: Concurr. Comput. Pract. Exp. (2022)
Keyphrases
- load balancing
- sparse matrix
- floating point
- parallel architectures
- fault tolerance
- multicore processors
- distributed systems
- graphics processing units
- peer to peer
- mobile agents
- fault tolerant
- grid computing
- computing power
- random projections
- general purpose
- real time
- parallel processing
- parallel computing
- computing systems
- efficient implementation
- highly parallel
- information systems