Dense Matrix-Vector Multiplication on the CUDA Architecture.
Noriyuki FujimotoPublished in: Parallel Process. Lett. (2008)
Keyphrases
- general purpose
- sparse matrix
- real time
- eigenvalues and eigenvectors
- management system
- matrix representation
- data flow
- dot product
- rows and columns
- floating point
- singular value decomposition
- software architecture
- parallel implementation
- low rank
- arithmetic operations
- covariance matrix
- weight matrix
- feature vectors
- moving objects