Photonic tensor cores (PTCs) are essential building blocks for optical artificial intelligence (AI) accelerators based on programmable photonic integrated circuits. Most PTC designs today are manually constructed, with low design efficiency and unsatisfying solution quality. This makes it challenging to meet various hardware specifications and keep up with rapidly evolving AI applications. Prior work has explored gradient-based methods to learn a good PTC structure differentiably. However, it suffers from slow training speed and optimization difficulty when handling multiple non-differentiable objectives and constraints. Therefore, in this work, we propose a more flexible and efficient zero-shot multi-objective evolutionary topology search framework ADEPT-Z that explores Pareto-optimal PTC designs with advanced devices in a larger search space. Multiple objectives can be co-optimized while honoring complicated hardware constraints. With only <3 hours of search, we can obtain tens of diverse Pareto-optimal solutions, 100x faster than the prior gradient-based method, outperforming prior manual designs with 2x higher accuracy weighted area-energy efficiency. The code of ADEPT-Z is available at https://github.com/ScopeX-ASU/ADEPT-Z.

翻译：光子张量核（PTC）是基于可编程光子集成电路的光学人工智能（AI）加速器的核心构建模块。目前大多数PTC设计均为人工构建，设计效率低且解决方案质量欠佳，难以满足多样化的硬件规格要求并跟上快速演进的人工智能应用步伐。先前研究探索了基于梯度的方法以可微分方式学习优良的PTC结构，但该方法在处理多个不可微分目标与约束时存在训练速度缓慢和优化困难的缺陷。为此，本研究提出一种更灵活高效的零样本多目标进化拓扑搜索框架ADEPT-Z，该框架可在更大搜索空间中利用先进器件探索帕累托最优的PTC设计。该框架能够同时优化多个目标，并严格满足复杂的硬件约束条件。仅需不足3小时的搜索即可获得数十个多样化的帕累托最优解，其搜索速度较先前基于梯度的方法提升100倍，并以2倍精度加权面积能效优势超越现有手工设计。ADEPT-Z的代码已发布于https://github.com/ScopeX-ASU/ADEPT-Z。