Memristive Crossbar Arrays for Storage and Computing Applications

The emergence of memristors with potential applications in data storage and artificial intelligence has attracted wide attentions. Memristors are assembled crossbar arrays bits encoded by the resistance individual cells. Despite proposed high density excellent scalability, sneak-path current causing cross interference impedes their practical applications. Therefore, developing novel architectures to mitigate improve efficiency, reliability, stability may benefit next-generation storage-class memory (SCM). Moreover, conventional digital computers face von-Neumann bottleneck slowdown transistors’ scaling, imposing a big challenge hardware intelligence. Memristive features colocation processing units, as well superior making it promising candidate for accelerating machine learning neuromorphic computing. Herein, first, architecture is introduced. Then, storage, origin reviewed techniques this issue from angle materials circuits discussed. Computing wise, memristive crossbars both computing surveyed, focusing on structure unit cells, network topology, types. Finally, perspective future engineering