As deep neural networks require tremendous amount of computation and memory, analog computing with emerging memory devices is a promising alternative to digital computing for edge devices. However, because of the increasing simulation time for analog computing system, it has not been explored. To overcome this issue, analytically approximated simulators are developed, but these models are inaccurate and narrow down the options for peripheral circuits for multiply-accumulate operation (MAC). In this sense, we propose a methodology, SEMULATOR (SiMULATOR by Emulating the analog computing block) which uses a deep neural network to emulate the behavior of crossbar-based analog computing system. With the proposed neural architecture, we experimentally and theoretically shows that it emulates a MAC unit for neural computation. In addition, the simulation time is incomparably reduced when it compared to the circuit simulators such as SPICE.
翻译:由于深神经网络需要大量的计算和内存,使用新兴记忆装置进行模拟计算是边缘设备数字计算的一个很有希望的替代方法。 但是,由于模拟计算系统的模拟时间不断增加,还没有对此进行探讨。为了克服这一问题,开发了分析性近似模拟器,但这些模型是不准确的,缩小了用于乘积操作的外围电路选项。 从这个意义上讲,我们提出了一个方法:SEMULATOR(SiMULATOR,通过模拟计算块),它利用深神经网络来模仿跨边模拟计算系统的行为。我们用拟议的神经结构实验和理论上显示,它模仿了神经计算的一个MAC单元。此外,与SPICE等电路模拟器相比,模拟时间的缩短是无法比较的。