Huawei Technologies Canada Co., Ltd. 19 Allstate Parkway, Markham, Ontario, L3R 5A4, Canada.
Department of Electrical and Computer Engineering, The University of British Columbia, 2332 Main Mall, Vancouver, British Columbia, V6T 1Z4, Canada.
Sci Rep. 2023 Jan 23;13(1):1260. doi: 10.1038/s41598-023-27724-y.
We propose a photonic processing unit for high-density analog computation using intensity-modulation-based microring modulators (IM-MRMs). The output signal at the fixed resonance wavelength is directly intensity modulated by changing the extinction ratio (ER) of the IM-MRM . Thanks to the intensity-modulated approach, the proposed photonic processing unit is less sensitive to the inter-channel crosstalk. Simulation results reveal that the proposed design offers a maximum of 17-fold increase in wavelength channel density compared to its wavelength-modulated counterpart. Therefore, a photonic tensor core of size 512 [Formula: see text] 512 can be realized by current foundry lines. A convolutional neural network (CNN) simulator with 6-bit precision is built for handwritten digit recognition task using the proposed modulator. Simulation results show an overall accuracy of 96.76%, when the wavelength channel spacing suffers a 3-dB power penalty. To experimentally validate the system, 1000 dot product operations are carried out with a 4-bit signed system on a co-packaged photonic chip, where optical and electrical I/Os are realized using photonic and electrical wire bonding techniques. Study of the measurement results show a mean squared error (MSE) of 3.09[Formula: see text]10[Formula: see text] for dot product calculations. The proposed IM-MRM, therefore, renders the crosstalk issue tractable and provides a solution for the development of large-scale optical information processing systems with multiple wavelengths.
我们提出了一种使用基于强度调制的微环调制器(IM-MRM)的高密度模拟计算光子处理单元。通过改变 IM-MRM 的消光比(ER),可以直接对固定谐振波长的输出信号进行强度调制。由于采用了强度调制方法,所提出的光子处理单元对信道间串扰的敏感度较低。仿真结果表明,与波长调制相比,所提出的设计在波长信道密度方面最大可提高 17 倍。因此,可以使用当前的代工厂线实现大小为 512[Formula: see text]512 的光子张量核。使用所提出的调制器构建了具有 6 位精度的卷积神经网络(CNN)模拟器,用于手写数字识别任务。当波长信道间隔遭受 3dB 功率损耗时,仿真结果显示整体准确性为 96.76%。为了实验验证系统,在共封装的光子芯片上进行了 1000 次点积运算,其中使用光子和电气引线键合技术实现了光学和电气 I/O。对点积计算结果的研究表明,均方误差(MSE)为 3.09[Formula: see text]10[Formula: see text]。因此,所提出的 IM-MRM 解决了串扰问题,并为开发具有多个波长的大规模光学信息处理系统提供了一种解决方案。