Low Precision Floating Point Arithmetic for High Performance FPGA-based CNN Acceleration.
Chen WuMingyu WangXinyuan ChuKun WangLei HePublished in: FPGA (2020)
Keyphrases
- floating point arithmetic
- floating point
- cellular neural networks
- application specific
- instruction set
- convolutional neural network
- hardware implementation
- high efficiency
- signal processing
- data model
- database
- fixed point
- dynamical systems
- graphics processing units
- field programmable gate array
- fine grained
- image processing