DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems（2019）
关键词
Hardware,Optimization,Layout,Field programmable gate arrays,Throughput,Computer architecture,Deep learning,Compiler,convolutional neural network (CNN),field-programmable gate array (FPGA),fusion,optimizations
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要