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: FCCM (2020)
Keyphrases
- convolutional neural network
- field programmable gate array
- hardware implementation
- systolic array
- face detection
- hardware architecture
- hardware design
- fpga technology
- parallel architecture
- xilinx virtex
- lightweight
- software implementation
- real time
- dedicated hardware
- fpga implementation
- cloud computing
- shared memory
- data flow
- computing platform
- highly flexible
- reconfigurable hardware
- compute intensive
- neural network
- parallel algorithm
- parallel computing
- scalable distributed
- pipelined architecture
- parallel implementation
- low cost
- edge detection
- high speed
- inference engine
- signal processing
- embedded systems
- object detection
- fpga device
- hardware architectures
- face recognition
- data management
- image processing algorithms
- pairwise
- object recognition
- bayesian networks
- feature selection