Optimizing tensor contraction expressions for hybrid CPU-GPU execution.
Wenjing MaSriram KrishnamoorthyOreste VillaKarol KowalskiGagan AgrawalPublished in: Clust. Comput. (2013)
Keyphrases
- gpu implementation
- graphics processing units
- graphics processors
- multithreading
- high order
- real time
- parallel computing
- heterogeneous computing
- execution model
- higher order
- facial expressions
- parallel implementation
- diffusion tensor
- natural language
- data flow
- massively parallel
- belief change
- personal computer
- parallel processing
- dimensionality reduction
- gpu accelerated