journal article·2022-04-01Open access

Emerging devices and packaging strategies for electronic-photonic AI accelerators: opinion

Nicola Peserico, Thomas Ferreira de Lima, Paul Prucnal, Volker J. Sorger

Optical Materials Express· Volume 12· Issue 4

Abstract

The field of mimicking the structure of the brain on a chip is experiencing interest driven by the demand for machine intelligent applications. However, the power consumption and available performance of machine-learning (ML) accelerating hardware still leave much desire for improvement. In this letter, we share viewpoints, challenges, and prospects of electronic-photonic neural network (NN) accelerators. Combining electronics with photonics offers synergistic co-design strategies for high-performance AI Application-specific integrated circuits (ASICs) and systems. Taking advantages of photonic signal processing capabilities and combining them with electronic logic control and data storage is an emerging prospect. However, the optical component library leaves much to be desired and is challenged by the enormous size of photonic devices. Within this context, we will review the emerging electro-optic materials, functional devices, and systems packaging strategies that, when realized, provide significant performance gains and fuel the ongoing AI revolution, leading to a stand-alone photonics-inside AI ASIC ‘black-box’ for streamlined plug-and-play board integration in future AI processors.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Neural Networks and Reservoir Computing · Photonic and Optical Devices · Optical Network Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

George Washington University

NEC Laboratories America Inc

Princeton University

References (21)

Show source-provided references
1. Shastri · Nat. Photonics · 2021 · 15 · 10210.1038/s41566-020-00754-y ↗
2. Miscuglio · Appl. Phys. Rev. · 2020 · 7 · 03140410.1063/5.0001942 ↗
3. Tait · Opt. Express · 2018 · 26 · 2642210.1364/OE.26.026422 ↗
4. Tait · J. Lightwave Technol. · 2014 · 32 · 402910.1109/JLT.2014.2345652 ↗
5. Shen · Nat. Photonics · 2017 · 11 · 44110.1038/nphoton.2017.93 ↗
6. Chrostowski · 2015
7. Soref · IEEE J. Quantum Electron. · 1987 · 23 · 12310.1109/JQE.1987.1073206 ↗
8. Multi-level nonvolatile photonic memories using broadband transparent phase change materials
9. Ferreira de Lima · IEEE J. Sel. Top. Quantum Electron. · 2019 · 26 · 110.1109/JSTQE.2019.2931252 ↗
10. Amin · Optica · 2020 · 7 · 33310.1364/OPTICA.389437 ↗
11. Xu · ACS Photonics · 2019 · 6 · 55310.1021/acsphotonics.8b01628 ↗
12. Li · Optica · 2019 · 6 · 110.1364/OPTICA.6.000001 ↗
13. Zhang · Photonics Res. · 2020 · 8 · 117110.1364/PRJ.393513 ↗
14. Green · Opt. Express · 2007 · 15 · 1710610.1364/OE.15.017106 ↗
15. Amin · Sci. Rep. · 2021 · 11 · 128710.1038/s41598-020-80381-3 ↗
16. Amin · APL Photonics · 2021 · 6 · 12080110.1063/5.0062830 ↗
17. Vermeulen · Proc. IEEE · 2018 · 106 · 227010.1109/JPROC.2018.2865725 ↗
18. Lindenmann · Opt. Express · 2012 · 20 · 1766710.1364/OE.20.017667 ↗
19. Thiessen · J. Lightwave Technol. · 2020 · 38 · 300010.1109/JLT.2020.2978413 ↗
20. Liang · Opt. Fiber Technol. · 2018 · 44 · 4310.1016/j.yofte.2017.12.005 ↗
21. Margalit · Appl. Phys. Lett. · 2021 · 118 · 22050110.1063/5.0050117 ↗