Batched Kronecker product for 2-D matrices and 3-D arrays on NVIDIA GPUs
Chetan JhuraniPublished in: CoRR (2013)
Keyphrases
- kronecker product
- graphics processing units
- graphics hardware
- gpu implementation
- graphics processors
- general purpose
- parallel processing
- cpu implementation
- times faster
- parallel programming
- real time
- massively parallel
- parallel implementation
- computing systems
- parallel algorithm
- compute unified device architecture
- parallel computing
- floating point
- processing speed
- feature tracking
- dimensionality reduction