Welcome to Lightning, the next-generation photonic computing system invented here at MIT!
Lightning is a reconfigurable photonic-electronic smartNIC that serves real-time deep neural network inference requests at 100 Gbps. Lightning uses a novel datapath that feeds traffic from the NIC into the photonic domain without creating digital packet processing and data movement bottlenecks. Lightning achieves this by employing a reconfigurable count-action abstraction, which keeps track of the computation Directed Acyclic Graph (DAG) of each inference packet. Our count-action abstraction decouples the compute control plane from the data plane by counting the number of operations in each task of the DAG and triggers the execution of the next tasks as soon as the previous task is finished, without interrupting the flow of the data.
To know more about this project:
- Read our full technical paper at the ACM SIGCOMM 2023: https://dl.acm.org/doi/10.1145/3603269.3604821
- Join our Slack channel: #project-lightning
- Try out our open source code: https://github.com/hipersys-team/lightning
What's New?
- [2023-09-23] Distributed photonic computing paper accepted at ACM HotNets 2023!
- [2023-09-11] MIT news covers Lightning: https://news.mit.edu/2023/system-combines-light-electrons-unlock-faster-...
- [2023-09-05] Sign up for an open-source Lightning Dev Kit here: https://forms.gle/hMXgTdb8XoE5gYV69
- [2023-08-18] Lightning software and hardware design is publicly available at: https://github.com/hipersys-team/lightning
- [2023-07-10] Lightning demo is accepted at ACM SIGCOMM 2023! We will move our experimental setup from MIT to New York City for a live demo.
- [2023-05-18] Lightning main paper is accepted at ACM SIGCOMM 2023! Congratulations to the team!
Technical publications
[1] Lightning: A Reconfigurable Photonic-Electronic SmartNIC for Fast and Energy-Efficient Inference
Zhizhen Zhong, Mingran Yang, Jay Lang, Christian Williams, Liam Kronman, Alexander Sludds, Homa Esfahanizadeh, Dirk Englund, Manya Ghobadi
ACM SIGCOMM 2023
Paper | Artifact | Demo | Slides | Video
[2] On-Fiber Photonic Computing
Zhizhen Zhong*, Mingran Yang*, Manya Ghobadi (co-first author)
ACM HotNets 2023
[3] Delocalized Photonic Deep Learning on the Internet's Edge
Alexander Sludds, Saumil Bandyopadhyay, Zaijun Chen, Zhizhen Zhong, Jared Cochrane, Liane Bernstein, Darius Bunandar, P. Ben Dixon, Scott Hamilton, Matthew Streshinsky, Ari Novack, Tom Baehr-Jones, Michael Hochberg, Manya Ghobadi, Ryan Hamerly, Dirk Englund
Science, Vol. 378 (6617) 2022
[4] IOI: In-Network Optical Inference
Zhizhen Zhong, Weiyang Wang, Manya Ghobadi, Alexander Sludds, Ryan Hamerly, Liane Bernstein, Dirk Englund
ACM SIGCOMM 2021 Workshop on Optical Systems (OptSys 2021)