DNNVM: End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-Based CNN Accelerators.
Yu XingShuang LiangLingzhi SuiXijie JiaJiantao QiuXin LiuYushun WangYi ShanYu WangPublished in: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. (2020)
Keyphrases
- end to end
- field programmable gate array
- admission control
- cellular neural networks
- ad hoc networks
- congestion control
- general purpose
- multipath
- high bandwidth
- computing systems
- wireless ad hoc networks
- embedded systems
- transactional memory
- content delivery
- application specific
- hardware implementation
- application layer
- wireless networks