Wu Guangjian, Zhang Xumeng, Feng Guangdi, Wang Jingli, Zhou Keji, Zeng Jinhua, Dong Danian, Zhu Fangduo, Yang Chenkai, Zhao Xiaoming, Gong Danni, Zhang Mengru, Tian Bobo, Duan Chungang, Liu Qi, Wang Jianlu, Chu Junhao, Liu Ming
State Key Laboratory of Integrated Chips and Systems, Frontier Institute of Chip and System, Fudan University, Shanghai, China.
Shanghai Qi Zhi Institute, Xuhui District, Shanghai, China.
Nat Mater. 2023 Dec;22(12):1499-1506. doi: 10.1038/s41563-023-01676-0. Epub 2023 Sep 28.
Recently, the increasing demand for data-centric applications is driving the elimination of image sensing, memory and computing unit interface, thus promising for latency- and energy-strict applications. Although dedicated electronic hardware has inspired the development of in-memory computing and in-sensor computing, folding the entire signal chain into one device remains challenging. Here an in-memory sensing and computing architecture is demonstrated using ferroelectric-defined reconfigurable two-dimensional photodiode arrays. High-level cognitive computing is realized based on the multiplications of light power and photoresponsivity through the photocurrent generation process and Kirchhoff's law. The weight is stored and programmed locally by the ferroelectric domains, enabling 51 (>5 bit) distinguishable weight states with linear, symmetric and reversible manipulation characteristics. Image recognition can be performed without any external memory and computing units. The three-in-one paradigm, integrating high-level computing, weight memorization and high-performance sensing, paves the way for a computing architecture with low energy consumption, low latency and reduced hardware overhead.
最近，对以数据为中心的应用的需求不断增加，推动了图像传感、内存和计算单元接口的淘汰，因此有望用于对延迟和能量要求严格的应用。尽管专用电子硬件推动了内存计算和传感器内计算的发展，但将整个信号链集成到一个设备中仍然具有挑战性。在此，使用铁电定义的可重构二维光电二极管阵列展示了一种内存传感和计算架构。基于通过光电流产生过程和基尔霍夫定律对光功率和光响应度的乘法运算，实现了高级认知计算。权重由铁电畴在本地存储和编程，实现了51（>5比特）个可区分的权重状态，具有线性、对称和可逆的操作特性。无需任何外部内存和计算单元即可执行图像识别。这种将高级计算、权重存储和高性能传感集成在一起的三合一范式，为低能耗、低延迟和减少硬件开销的计算架构铺平了道路。
