Conventional von Neumann architecture faces many challenges in dealing with data-intensive artificial intelligence tasks efficiently due to huge amounts of data movement between physically separated data computing and...Conventional von Neumann architecture faces many challenges in dealing with data-intensive artificial intelligence tasks efficiently due to huge amounts of data movement between physically separated data computing and storage units.Novel computing-in-memory(CIM)ar-chitecture implements data processing and storage in the same place,and thus can be much more energy-efficient than state-of-the-art von Neumann architecture.Compared with their counterparts,resis-tive random-access memory(RRAM)-based CIM systems could consume much less power and area when processing the same amount of data.In this paper,we first introduce the principles and challenges re-lated to RRAM-based CIM systems.Then,recent works on the circuit and macro levels of RRAM-CIM systems will be reviewed to highlight the trends and challenges in this field.展开更多
基金supported by the China key research and develop-ment program(2019YFB2205403).
文摘Conventional von Neumann architecture faces many challenges in dealing with data-intensive artificial intelligence tasks efficiently due to huge amounts of data movement between physically separated data computing and storage units.Novel computing-in-memory(CIM)ar-chitecture implements data processing and storage in the same place,and thus can be much more energy-efficient than state-of-the-art von Neumann architecture.Compared with their counterparts,resis-tive random-access memory(RRAM)-based CIM systems could consume much less power and area when processing the same amount of data.In this paper,we first introduce the principles and challenges re-lated to RRAM-based CIM systems.Then,recent works on the circuit and macro levels of RRAM-CIM systems will be reviewed to highlight the trends and challenges in this field.
