CPU-GPU Layer-Switched Low Latency CNN Inference.
Ehsan AghapourDolly SapraAndy D. PimentelAnuj PathaniaPublished in: DSD (2022)
Keyphrases
- low latency
- real time
- graphics processing units
- gpu implementation
- graphics processors
- high bandwidth
- high speed
- high throughput
- highly efficient
- massive scale
- virtual machine
- stream processing
- general purpose
- continuous query processing
- database
- parallel computing
- parallel processing
- data acquisition
- information systems
- databases
- data sets