A GPU Architecture Aware Fine-Grain Pruning Technique for Deep Neural Networks.
Kyusik ChoiHoeseok YangPublished in: Euro-Par (2021)
Keyphrases
- fine grain
- coarse grain
- neural network
- parallel computation
- real time
- parallel algorithm
- distributed memory
- multithreading
- reconfigurable hardware
- management system
- associative memory
- parallel architecture
- parallel processing
- parallel implementation
- parallel computing
- software architecture
- pairwise
- parallel computers
- database systems