npj 2D Materials and Applications ( IF 9.7 ) Pub Date : 2021-05-14 , DOI: 10.1038/s41699-021-00236-x Batyrbek Alimkhanuly , Joon Sohn , Ik-Joon Chang , Seunghyun Lee
Recent studies on neural network quantization have demonstrated a beneficial compromise between accuracy, computation rate, and architecture size. Implementing a 3D Vertical RRAM (VRRAM) array accompanied by device scaling may further improve such networks’ density and energy consumption. Individual device design, optimized interconnects, and careful material selection are key factors determining the overall computation performance. In this work, the impact of replacing conventional devices with microfabricated, graphene-based VRRAM is investigated for circuit and algorithmic levels. By exploiting a sub-nm thin 2D material, the VRRAM array demonstrates an improved read/write margins and read inaccuracy level for the weighted-sum procedure. Moreover, energy consumption is significantly reduced in array programming operations. Finally, an XNOR logic-inspired architecture designed to integrate 1-bit ternary precision synaptic weights into graphene-based VRRAM is introduced. Simulations on VRRAM with metal and graphene word-planes demonstrate 83.5 and 94.1% recognition accuracy, respectively, denoting the importance of material innovation in neuromorphic computing.
中文翻译:
基于三元精度的基于石墨烯的3D XNOR-VRRAM用于神经形态计算
最近关于神经网络量化的研究表明,在准确性,计算速率和体系结构大小之间存在有益的折衷。实现3D垂直RRAM(VRRAM)阵列并伴随设备缩放可进一步改善此类网络的密度和能耗。单独的设备设计,优化的互连以及精心的材料选择是决定整体计算性能的关键因素。在这项工作中,针对电路和算法级别,研究了用基于石墨烯的微型制造的VRRAM替代传统设备的影响。通过利用亚纳米级的薄2D材料,VRRAM阵列展示了加权和过程的改进的读/写裕度和读取不准确度。此外,在阵列编程操作中,能耗大大降低。最后,引入了XNOR逻辑启发的体系结构,该体系结构旨在将1位三元精度突触权重集成到基于石墨烯的VRRAM中。在具有金属和石墨烯字平面的VRRAM上进行的仿真分别显示了83.5%和94.1%的识别精度,这表明材料创新在神经形态计算中的重要性。