---
OA_type: closed access
_id: '21568'
abstract:
- lang: eng
  text: 'Optical approaches to AI acceleration have gained intense interest recently
    due to the potentially breakthrough advantages of photonics: high bandwidth, low
    power consumption, and efficient data movement. We overview leading photonic AI
    platforms based on beamsplitter mesh networks, weight banks, and photoelectric
    multiplication. While the theoretical performance can be orders of magnitude beyond
    current state of the art, practical issues of chip area, input / output, and crosstalk
    paint a more nuanced near-term picture of photonic AI acceleration. Both fundamental
    and near-term limitations to energy efficiency are addressed, and bandwidth limitations
    due to temporal crosstalk are analyzed.'
article_processing_charge: No
author:
- first_name: R.
  full_name: Hamerly, R.
  last_name: Hamerly
- first_name: A.
  full_name: Sludds, A.
  last_name: Sludds
- first_name: L.
  full_name: Bernstein, L.
  last_name: Bernstein
- first_name: M.
  full_name: Prabhu, M.
  last_name: Prabhu
- first_name: Charles
  full_name: Roques-Carmes, Charles
  id: e2e68fc9-6505-11ef-a541-eb4e72cc3e82
  last_name: Roques-Carmes
- first_name: J.
  full_name: Carolan, J.
  last_name: Carolan
- first_name: Y.
  full_name: Yamamoto, Y.
  last_name: Yamamoto
- first_name: M.
  full_name: Soljacic, M.
  last_name: Soljacic
- first_name: D.
  full_name: Englund, D.
  last_name: Englund
citation:
  ama: 'Hamerly R, Sludds A, Bernstein L, et al. Towards large-scale photonic neural-network
    accelerators. In: <i>2019 IEEE International Electron Devices Meeting</i>. IEEE;
    2019. doi:<a href="https://doi.org/10.1109/iedm19573.2019.8993624">10.1109/iedm19573.2019.8993624</a>'
  apa: 'Hamerly, R., Sludds, A., Bernstein, L., Prabhu, M., Roques-Carmes, C., Carolan,
    J., … Englund, D. (2019). Towards large-scale photonic neural-network accelerators.
    In <i>2019 IEEE International Electron Devices Meeting</i>. San Francisco, CA,
    United States: IEEE. <a href="https://doi.org/10.1109/iedm19573.2019.8993624">https://doi.org/10.1109/iedm19573.2019.8993624</a>'
  chicago: Hamerly, R., A. Sludds, L. Bernstein, M. Prabhu, Charles Roques-Carmes,
    J. Carolan, Y. Yamamoto, M. Soljacic, and D. Englund. “Towards Large-Scale Photonic
    Neural-Network Accelerators.” In <i>2019 IEEE International Electron Devices Meeting</i>.
    IEEE, 2019. <a href="https://doi.org/10.1109/iedm19573.2019.8993624">https://doi.org/10.1109/iedm19573.2019.8993624</a>.
  ieee: R. Hamerly <i>et al.</i>, “Towards large-scale photonic neural-network accelerators,”
    in <i>2019 IEEE International Electron Devices Meeting</i>, San Francisco, CA,
    United States, 2019.
  ista: 'Hamerly R, Sludds A, Bernstein L, Prabhu M, Roques-Carmes C, Carolan J, Yamamoto
    Y, Soljacic M, Englund D. 2019. Towards large-scale photonic neural-network accelerators.
    2019 IEEE International Electron Devices Meeting. IEDM: International Electron
    Devices Meeting.'
  mla: Hamerly, R., et al. “Towards Large-Scale Photonic Neural-Network Accelerators.”
    <i>2019 IEEE International Electron Devices Meeting</i>, IEEE, 2019, doi:<a href="https://doi.org/10.1109/iedm19573.2019.8993624">10.1109/iedm19573.2019.8993624</a>.
  short: R. Hamerly, A. Sludds, L. Bernstein, M. Prabhu, C. Roques-Carmes, J. Carolan,
    Y. Yamamoto, M. Soljacic, D. Englund, in:, 2019 IEEE International Electron Devices
    Meeting, IEEE, 2019.
conference:
  end_date: 2019-12-11
  location: San Francisco, CA, United States
  name: 'IEDM: International Electron Devices Meeting'
  start_date: 2019-12-07
date_created: 2026-03-30T12:22:47Z
date_published: 2019-12-01T00:00:00Z
date_updated: 2026-05-05T07:39:32Z
day: '01'
doi: 10.1109/iedm19573.2019.8993624
extern: '1'
fulldoi: https://doi.org/10.1109/iedm19573.2019.8993624
language:
- iso: eng
month: '12'
oa_version: None
publication: 2019 IEEE International Electron Devices Meeting
publication_identifier:
  eisbn:
  - '9781728140322'
  eissn:
  - 2156-017X
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Towards large-scale photonic neural-network accelerators
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2019'
...