arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.20331physics.optics
收藏

超越每核TOPS的光子逻辑张量计算

Photonic logic tensor computing beyond TOPS per core

Wenkai Zhang, Bo Wu, Wentao Gu, Hailong Zhou, Weida Hu, Ting He, Liao Chen, Wenchan Dong, Dongmei Huang, Yang Zhao, Wei Wang, Naidi Cui, Qiansheng Wang, Xi Xiao… 展开作者

Wenkai Zhang, Bo Wu, Wentao Gu, Hailong Zhou, Weida Hu, Ting He, Liao Chen, Wenchan Dong, Dongmei Huang, Yang Zhao, Wei Wang, Naidi Cui, Qiansheng Wang, Xi Xiao, Jianji Dong, Xinliang Zhang

AI总结:

首次提出光子逻辑张量计算架构并制备光子通用逻辑张量核(PULTC),通过微环调制器非线性映射与马赫-曾德尔干涉仪网格配置实现超越TOPS的大规模并行通用逻辑计算。

摘要:

对计算资源需求的激增引发了人们对具有更高速度和更大计算容量的光子计算的浓厚兴趣。由于布尔逻辑在现代数字计算系统中的基础性作用,光子逻辑门至关重要。然而,由于光学元件中微弱且固定的非线性,大多数光子逻辑方案难以展现出大规模并行处理和灵活重构的能力。在此,我们首次提出了一种光子逻辑张量计算架构,并制备了并行逻辑计算容量超越TOPS的光子通用逻辑张量核(PULTC)。PULTC中设计了十个波长通道和四个空间通道,其中每个通道的逻辑计算速度可达50 Gbit/s。经过微环调制器的非线性映射,可以通过配置马赫-曾德尔干涉仪网格来实现任意逻辑操作。我们的工作为具有高并行能力的通用光子逻辑计算提供了一条创新途径,并推动了光子逻辑计算的实际应用。

英文摘要:

The soaring demand for computing resources has spurred great interest in photonic computing with higher speed and larger computing capacity. Photonic logic gates are of crucial importance due to the fundamental role of Boolean logic in modern digital computing systems. However, most photonic logic schemes struggle to exhibit the capability of massively parallel processing and flexible reconfiguration, owing to weak and fixed nonlinearity in optical elements. Here, we propose a photonic logic tensor computing architecture for the first time and fabricate the photonic universal logic tensor core (PULTC) with a parallel logic computing capacity beyond TOPS. Ten wavelength channels and four spatial channels are designed in PULTC, where the logic computing speed in each channel can reach 50 Gbit/s. After the nonlinear mapping of microring modulators, arbitrary logic operations can be achieved by configuring the Mach-Zehnder interferometer mesh. Our work offers an innovative route for photonic universal logic computing with high-parallel capability and propels the practical applications of photonic logic computing.

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。

↑