Hardware/Software Co-Design of an Automatically Generated Analog NN.
International Conference / Workshop on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS)(2021)
摘要
This paper presents a partial automated workflow for a hard-ware and software co-design used to generate analog convolutional neural networks. The developed workflow provides an automated generation of the schematic and layout of analog neural networks itself as well as the verification of the created circuit with an automated simulation setup. The designed application-specific integrated circuit (ASIC) has an energy consumption of 450 nJ (235 nJ for the frontend and 215 nJ for the neural network) and needs 369 ps (362 ps for the front-end and 7 ps for the neural network) per inference.
更多查看译文
关键词
Neuromorphic computing, Analog computing, Hardware and software co-design, Workflow, Integrated circuits, Analog synthesis
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