Papers
Topics
Authors
Recent
2000 character limit reached

Invited: Neuromorphic architectures based on augmented silicon photonics platforms (2407.06240v1)

Published 7 Jul 2024 in cs.ET, eess.SP, and physics.optics

Abstract: In this work, we discuss our vision for neuromorphic accelerators based on integrated photonics within the framework of the Horizon Europe NEUROPULS project. Augmented integrated photonic architectures that leverage phase-change and III-V materials for optical computing will be presented. A CMOS-compatible platform will be discussed that integrates these materials to fabricate photonic neuromorphic architectures, along with a gem5-based simulation platform to model accelerator operation once it is interfaced with a RISC-V processor. This simulation platform enables accurate system-level accelerator modeling and benchmarking in terms of key metrics such as speed, energy consumption, and footprint.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. B. A. Bell and I. A. Walmsley. 2021. Further Compactifying Linear Optical Unitaries. APL Photonics 6, 7 (July 2021), 070804. https://doi.org/10.1063/5.0053421
  2. The Gem5 Simulator. SIGARCH Comput. Archit. News 39, 2 (aug 2011), 1–7. https://doi.org/10.1145/2024716.2024718
  3. An Overview on Edge Computing Research. IEEE Access 8 (2020), 85714–85728. https://doi.org/10.1109/ACCESS.2020.2991734
  4. gem5-MARVEL: Microarchitecture-Level Resilience Analysis of Heterogeneous SoC Architectures. In IEEE International Symposium on High-Performance Computer Architecture (HPCA 2024). 543–559. https://doi.org/10.1109/HPCA57654.2024.00047
  5. Optimal design for universal multiport interferometers. Optica 3, 12 (Dec. 2016), 1460. https://doi.org/10.1364/OPTICA.3.001460
  6. Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook. Proc. IEEE 109, 5 (May 2021), 911–934. https://doi.org/10.1109/JPROC.2021.3067593 Conference Name: Proceedings of the IEEE.
  7. Ge–Sb–S–Se–Te amorphous chalcogenide thin films towards on-chip nonlinear photonic devices. Sci Rep 10, 1 (July 2020), 11894. https://doi.org/10.1038/s41598-020-67377-9
  8. Parallel convolutional processing using an integrated photonic tensor core. Nature 589, 7840 (Jan. 2021), 52–58. https://doi.org/10.1038/s41586-020-03070-1
  9. All-optical spiking neurosynaptic networks with self-learning capabilities. Nature 569, 7755 (May 2019), 208–214. https://doi.org/10.1038/s41586-019-1157-8
  10. Optimal Design of Error-Tolerant Reprogrammable Multiport Interferometers. Optics Letters 45, 9 (May 2020), 2632–2635. https://doi.org/10.1364/OL.385433
  11. Bottom-Up and Top-Down Approaches for the Design of Neuromorphic Processing Systems: Tradeoffs and Synergies Between Natural and Artificial Intelligence. Proc. IEEE 111, 6 (June 2023), 623–652. https://doi.org/10.1109/JPROC.2023.3273520
  12. Neuromorphic spintronics. Nat Electron 3, 7 (July 2020), 360–370. https://doi.org/10.1038/s41928-019-0360-9 Publisher: Nature Publishing Group.
  13. The SpiNNaker 2 Processing Element Architecture for Hybrid Digital Neuromorphic Computing. http://arxiv.org/abs/2103.08392
  14. Artificial Synapse with Mnemonic Functionality using GSST-based Photonic Integrated Memory. ([n. d.]), 8.
  15. NEUROPULS: NEUROmorphic energy-efficient secure accelerators based on Phase change materials aUgmented siLicon photonicS. 2023 IEEE European Test Symposium (ETS). https://doi.org/10.1109/ETS56758.2023.10173974
  16. Open-Access Silicon Photonics: Current Status and Emerging Initiatives. Proc. IEEE 106, 12 (Dec. 2018), 2313–2330. https://doi.org/10.1109/JPROC.2018.2878686 Conference Name: Proceedings of the IEEE.
  17. gem5-SALAM: A System Architecture for LLVM-based Accelerator Modeling. In 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 471–482. https://doi.org/10.1109/MICRO50266.2020.00047
  18. Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications. Proc. IEEE 109, 3 (March 2021), 247–278. https://doi.org/10.1109/JPROC.2021.3060483
  19. Mahadev Satyanarayanan. 2017. The Emergence of Edge Computing. Computer 50, 1 (Jan. 2017), 30–39. https://doi.org/10.1109/MC.2017.9
  20. Photonics for Artificial Intelligence and Neuromorphic Computing. Nature Photonics 15, 2 (Feb. 2021), 102–114. https://doi.org/10.1038/s41566-020-00754-y
  21. Electro-optical switching at 1550 nm using a two-state GeSe phase-change layer. Opt. Express, OE 23, 2 (Jan. 2015), 1536–1546. https://doi.org/10.1364/OE.23.001536 Publisher: Optica Publishing Group.
  22. Silicon Photonic Modulator Neuron. Phys. Rev. Appl. 11, 6 (June 2019), 064043. https://doi.org/10.1103/PhysRevApplied.11.064043 Publisher: American Physical Society.
  23. In-memory photonic dot-product engine with electrically programmable weight banks. Nat Commun 14, 1 (May 2023), 2887. https://doi.org/10.1038/s41467-023-38473-x

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up