Generating optimal CUDA sparse matrix-vector product implementations for evolving GPU hardware.
Ahmed H. El ZeinAlistair P. RendellPublished in: Concurr. Comput. Pract. Exp. (2012)
Keyphrases
- sparse matrix
- graphics processors
- graphics hardware
- real time
- gpu implementation
- parallel implementation
- parallel computation
- dynamic programming
- gpu accelerated
- general purpose
- graphics processing units
- parallel computing
- random projections
- rows and columns
- parallel algorithm
- optimal solution
- massively parallel
- parallel processing
- multi objective