cuConv: CUDA implementation of convolution for CNN inference.
Marc JordàPedro Valero-LaraAntonio J. PeñaPublished in: Clust. Comput. (2022)
Keyphrases
- parallel implementation
- general purpose
- graphics processors
- efficient implementation
- image processing
- bayesian networks
- compute unified device architecture
- database
- inference process
- implementation issues
- implementation details
- parallel computing
- shared memory
- cloud computing
- case study
- knowledge base
- information systems