Efficient Implementation of Convolution and Winograd on ASMP Embedded Multicore Vector Processor.
Nicolas LeclaireStéphane ManciniClaude DelnondedieuJean-Paul HenriquesPublished in: SiPS (2020)
Keyphrases
- efficient implementation
- highly parallel
- graphics processing units
- cell processor
- memory management
- parallel architectures
- multicore processors
- high end
- hardware implementation
- embedded processors
- active set
- embedded systems
- efficient processing
- feature vectors
- computer systems
- high speed
- single chip
- dynamic random access memory
- image processing
- parallel programming
- computer architecture
- parallel processing
- vector space
- operating system
- computation intensive
- shared memory multiprocessor
- face recognition