论文标题
基于MRAM的模拟Sigmoid函数用于内存计算
MRAM-based Analog Sigmoid Function for In-memory Computing
论文作者
论文摘要
我们提出了先验激活函数的模拟实现，该功能利用了两个自旋轨道磁盘磁盘磁盘随机访问存储器（SOT-MRAM）设备和一个CMOS逆变器。与最先进的模拟和数字实现相比，拟议的模拟神经元电路消耗的功率减少了1.8-27倍，占地2.5-4931x。此外，无需任何中间信号转换单元就可以轻松地将开发的神经元与回忆横梁整合在一起。结构级别的分析表明，使用我们的SOT-MRAM神经元以及基于SOT-MRAM的横杆的完全动物内存计算（IMC）电路可以分别降低1.1倍，12x和13.3倍以上的功率，延迟，延迟和能量，与与类似的Memristive Neuristive Neuristive Neuristive Neuristive Neuransbars和Dighate bysristive Neuristive Neuristive Neuristive neeuristive neeuristive neyuristive neyuristive neebars和Digital bars相比。最后，通过跨层分析，我们提供了一个指南，介绍了神经元中的设备级参数如何影响MNIST分类的多层感知器（MLP）的准确性。
We propose an analog implementation of the transcendental activation function leveraging two spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices and a CMOS inverter. The proposed analog neuron circuit consumes 1.8-27x less power, and occupies 2.5-4931x smaller area, compared to the state-of-the-art analog and digital implementations. Moreover, the developed neuron can be readily integrated with memristive crossbars without requiring any intermediate signal conversion units. The architecture-level analyses show that a fully-analog in-memory computing (IMC) circuit that use our SOT-MRAM neuron along with an SOT-MRAM based crossbar can achieve more than 1.1x, 12x, and 13.3x reduction in power, latency, and energy, respectively, compared to a mixed-signal implementation with analog memristive crossbars and digital neurons. Finally, through cross-layer analyses, we provide a guide on how varying the device-level parameters in our neuron can affect the accuracy of multilayer perceptron (MLP) for MNIST classification.
