Machine Learning Accelerators in 2.5D Chiplet Platforms with Silicon Photonics
Machine Learning Accelerators in 2.5D Chiplet Platforms with Silicon Photonics
复制标题
DOI：
10.23919/date56975.2023.10137317
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Febin P. Sunny;Ebadollah Taheri;M. Nikdast;S. Pasricha
中科院分区：
文献类型：
--
作者：
Febin P. Sunny;Ebadollah Taheri;M. Nikdast;S. Pasricha
特定领域的机器学习（ML）加速器，如谷歌的张量处理单元（TPU）和苹果的神经引擎，如今在高能效的ML处理方面已超越了中央处理器（CPU）和图形处理器（GPU）。然而，由于单片处理芯片的计算密度有限以及对慢速金属互连的依赖，电子加速器的发展正面临根本限制。在本文中，我们展望了如何将光计算和通信集成到2.5D小芯片平台中，以推动一类全新的可持续且可扩展的ML硬件加速器。我们阐述了光学器件、电路和架构的跨层设计与制造，以及硬件/软件协同设计如何有助于设计高效的基于光子学的2.5D小芯片平台，以加速新兴的ML工作负载。
Domain-specific machine learning (ML) accelerators such as Google's TPU and Apple's Neural Engine now dominate CPUs and GPUs for energy-efficient ML processing. However, the evolution of electronic accelerators is facing fundamental limits due to the limited computation density of monolithic processing chips and the reliance on slow metallic interconnects. In this paper, we present a vision of how optical computation and communication can be integrated into 2.5D chiplet platforms to drive an entirely new class of sustainable and scalable ML hardware accelerators. We describe how cross-layer design and fabrication of optical devices, circuits, and architectures, and hardware/software codesign can help design efficient photonics-based 2.5D chiplet platforms to accelerate emerging ML workloads.