Brückerhoff-Plückelmann Frank, Feldmann Johannes, Gehring Helge, Zhou Wen, Wright C David, Bhaskaran Harish, Pernice Wolfram
University of Münster, Heisenberg Str. 11, Muenster 48155, Germany.
Department of Materials , University of Oxford, Parks Road, Oxford OX1 3PH, Oxfordshire, UK.
Nanophotonics. 2022 Feb 11;11(17):4063-4072. doi: 10.1515/nanoph-2021-0752. eCollection 2022 Sep.
The integration of artificial intelligence (AI) systems in the daily life greatly increases the amount of data generated and processed. In addition to the large computational power required, the hardware needs to be compact and energy efficient. One promising approach to fulfill those requirements is phase-change material based photonic neuromorphic computing that enables in-memory computation and a high degree of parallelization. In the following, we present an optimized layout of a photonic tensor core (PTC) which is designed to perform real valued matrix vector multiplications and operates at telecommunication wavelengths. We deploy the well-studied phase-change material GeSbTe (GST) as an optical attenuator to perform single positive valued multiplications. In order to generalize the multiplication to arbitrary real factors, we develop a novel symmetric multiplication unit which directly includes a reference-computation branch. The variable GST attenuator enables a modulation depth of 5 dB over a wavelength range of 100 nm with a wavelength dependency below 0.8 dB. The passive photonic circuit itself ensures equal coupling to the main-computation and reference-computation branch over the complete wavelength range. For the first time, we integrate wavelength multiplexers (MUX) together with a photonic crossbar array on-chip, paving the way towards fully integrated systems. The MUX are crucial for the PTC since they enable multiple computational channels in a single photonic crossbar array. We minimize the crosstalk between the channels by designing Bragg scattering based MUX. By cascading, we achieve an extinction ratio larger than 61 dB while the insertion loss is below 1 dB.
人工智能（AI）系统融入日常生活极大地增加了所生成和处理的数据量。除了需要强大的计算能力外，硬件还需紧凑且节能。一种满足这些要求的有前景的方法是基于相变材料的光子神经形态计算，它能够实现内存内计算和高度并行化。在此，我们展示了一种光子张量核（PTC）的优化布局，该布局旨在执行实值矩阵向量乘法，并在电信波长下运行。我们采用经过充分研究的相变材料锗锑碲（GST）作为光衰减器来执行单正值乘法。为了将乘法推广到任意实因数，我们开发了一种新颖的对称乘法单元，该单元直接包含一个参考计算分支。可变GST衰减器在100nm波长范围内实现了5dB的调制深度，波长依赖性低于0.8dB。无源光子电路本身可确保在整个波长范围内与主计算分支和参考计算分支实现均匀耦合。我们首次将波长复用器（MUX）与光子交叉开关阵列集成在芯片上，为实现完全集成系统铺平了道路。MUX对于PTC至关重要，因为它们能在单个光子交叉开关阵列中实现多个计算通道。我们通过设计基于布拉格散射的MUX来最小化通道间的串扰。通过级联，我们实现了大于61dB的消光比，而插入损耗低于1dB。
