Systolic-CNN: An OpenCL-defined Scalable Run-time-flexible FPGA Accelerator Architecture for Accelerating Convolutional Neural Network Inference in Cloud/Edge Computing.
Akshay DuaYixing LiFengbo RenPublished in: CoRR (2020)
Keyphrases
- convolutional neural network
- field programmable gate array
- systolic array
- face detection
- hardware implementation
- hardware architecture
- hardware design
- parallel architecture
- fpga implementation
- software implementation
- xilinx virtex
- cloud computing
- pipelined architecture
- embedded systems
- highly flexible
- real time
- compute intensive
- reconfigurable hardware
- parallel computing
- neural network
- low cost
- dedicated hardware
- inference engine
- data flow
- lightweight
- parallel implementation
- computing platform
- fpga technology
- high speed
- hardware architectures
- hardware software
- low power
- image processing algorithms
- computer vision
- object detection
- scalable distributed
- edge detection
- detection method
- map reduce
- parallel programming
- parallel algorithm