A system hierarchy for brain-inspired computing

• Published in: Nature (London) 2020-10, Vol.586 (7829), p.378-384
• Main Authors: Zhang, Youhui, Qu, Peng, Ji, Yu, Zhang, Weihao, Gao, Guangrong, Wang, Guanrui, Song, Sen, Li, Guoqi, Chen, Wenguang, Zheng, Weimin, Chen, Feng, Pei, Jing, Zhao, Rong, Zhao, Mingguo, Shi, Luping
• Format: Article
• Language: English
• Subjects: 639/166/987; 639/766/259; Algorithms; Brain; Completeness; Computation; Computer programs; Computers; Design; Hardware; Hierarchical organization (Computers); Humanities and Social Sciences; Intelligence; Machine learning; multidisciplinary; Neural networks; Productivity; Programming languages; Science; Science (multidisciplinary); Software
• ISSN: 0028-0836; 1476-4687
• DOI: 10.1038/s41586-020-2782-y

Neuromorphic computing draws inspiration from the brain to provide computing technology and architecture with the potential to drive the next wave of computer engineering 1 – 13 . Such brain-inspired computing also provides a promising platform for the development of artificial general intelligence 14 , 15 . However, unlike conventional computing systems, which have a well established computer hierarchy built around the concept of Turing completeness and the von Neumann architecture 16 – 18 , there is currently no generalized system hierarchy or understanding of completeness for brain-inspired computing. This affects the compatibility between software and hardware, impairing the programming flexibility and development productivity of brain-inspired computing. Here we propose ‘neuromorphic completeness’, which relaxes the requirement for hardware completeness, and a corresponding system hierarchy, which consists of a Turing-complete software-abstraction model and a versatile abstract neuromorphic architecture. Using this hierarchy, various programs can be described as uniform representations and transformed into the equivalent executable on any neuromorphic complete hardware—that is, it ensures programming-language portability, hardware completeness and compilation feasibility. We implement toolchain software to support the execution of different types of program on various typical hardware platforms, demonstrating the advantage of our system hierarchy, including a new system-design dimension introduced by the neuromorphic completeness. We expect that our study will enable efficient and compatible progress in all aspects of brain-inspired computing systems, facilitating the development of various applications, including artificial general intelligence. The concept of neuromorphic completeness and a system hierarchy for neuromorphic computing are presented, which could improve programming-language portability, hardware completeness and compilation feasibility of brain-inspired computing systems