用于UNet架构片上学习的畴壁与磁性隧道结混合结构
Domain wall and Magnetic Tunnel Junction Hybrid for on-chip Learning in UNet architecture
AI总结：
本研究提出基于畴壁MTJ与非稳定铁磁体MTJ的UNet硬件实现方案，通过混合仿真验证，在CamVid数据集上实现83.71%分割准确率，同时大幅降低片上学习能耗。
摘要：
我们提出了基于自旋电子器件的UNet硬件实现方案，用于图像分割任务。我们的方法包括为UNet架构的卷积层、反卷积层、整流激活函数（ReLU）和最大池化层设计硬件。我们利用畴壁MTJ（磁性隧道结）的突触行为设计了网络的卷积层和反卷积层，还利用自旋霍尔效应驱动的正交电流注入MTJ构建了网络的ReLU和最大池化功能。为了在UNet设计中整合自旋输运、磁化动力学和CMOS元件的多样物理特性，我们采用了一种混合仿真设置，将微磁仿真、非平衡格林函数、SPICE仿真与网络实现耦合在一起。我们在CamVid数据集上评估了所提出的UNet设计，在测试数据上取得了83.71%的分割准确率，与软件实现的性能相当，且在150个epoch的片上训练中能耗为821mJ。我们进一步证明，与基于稳定铁磁体（Δ=45）的ReLU和最大池化功能相比，使用非稳定铁磁体（Δ=4.58）的网络能耗需求提升了近一个数量级（10倍），同时保持了相近的准确率。这种由畴壁MTJ和基于非稳定FM（铁磁体）的MTJ组成的混合架构，训练期间的片上能耗为85.79mJ，测试能耗为1.55μJ。
英文摘要：
We present spintronic devices based hardware implementation of UNet for segmentation tasks. Our approach involves designing hardware for convolution, deconvolution, rectified activation function (ReLU), and max pooling layers of the UNet architecture. We designed the convolution and deconvolution layers of the network using the synaptic behavior of the domain wall MTJ. We also construct the ReLU and max pooling functions of the network utilizing the spin hall driven orthogonal current injected MTJ. To incorporate the diverse physics of spin-transport, magnetization dynamics, and CMOS elements in our UNet design, we employ a hybrid simulation setup that couples micromagnetic simulation, non-equilibrium Green's function, SPICE simulation along with network implementation. We evaluate our UNet design on the CamVid dataset and achieve segmentation accuracies of 83.71$\%$ on test data, on par with the software implementation with 821mJ of energy consumption for on-chip training over 150 epochs. We further demonstrate nearly one order $(10\times)$ improvement in the energy requirement of the network using unstable ferromagnet ($Δ$=4.58) over the stable ferromagnet ($Δ$=45) based ReLU and max pooling functions while maintaining the similar accuracy. The hybrid architecture comprising domain wall MTJ and unstable FM-based MTJ leads to an on-chip energy consumption of 85.79mJ during training, with a testing energy cost of 1.55 $μJ$.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
