The Optical Networking and Communication
Conference & Exhibition

Moscone Center,
San Francisco, California, USA

CANCELLED - Panel III: Optical Interconnect and Computing for Scaling Machine Learning Systems


-
Expo Theater I

Panel Description:

Until recently, the architectures and systems for executing Machine Learning (ML) workloads were based on traditional optical interconnects used for datacenter networking or high-performance computing. With the rapid rise in ML workloads and the fact that ML network architectures/protocols and computation requirements are different from traditional datacenter architectures and compute, leading cloud operators, component/system vendors, and a number of startups are exploring optical technologies for more efficient and scalable ML systems. These fall into two categories: (a) Making higher performance (bandwidth, latency) optical interconnects while improving power, cost, and density and (b) Exploring optics for computation, by leveraging the unique characteristics of ML systems for both axes.  

This panel will introduce the views of several industry leaders in this area, followed by discussion among panelists and the floor. 

Speakers:

Mitchell Nahmias, CTO and Co-Founder, Luminous Computing, USA

 

Addressing the Bottlenecks of Artificial Intelligence with Photonic Computing
In this panel, we describe how photonic computing can lead to staggering improvements in the efficiency of artificial intelligence algorithms by addressing its two main bottlenecks: data movement and performing matrix multiplications. I outline the ingredients that make this possible, covering advances in photonic large-scale manufacturing, and compare photonics with both digital and analog electronics.

 

Robert (Ted) Weverka, Senior Optical Physicist and IP Lead, Fathom Computing, USA
Scalable Interconnects for Neural Networks

Rent’s rule expresses a power law for the number of interconnects crossing a boundary enclosing a number of logic gates in a portion of a system.  Systems that scale to large size have natural limits to the power law that can be realized, given by the geometry of the interconnects.  Rent exponents greater than 0.5 require multilayer interconnects and serializer-deserializers, with the number of layers and bandwidth multipliers growing with system size.

High Rent exponents are suggested by the geometry of human and animal brains where the gray matter at the surface is largely connected by white matter throughout the volume.  Achieving this kind of connectivity which scales to ever larger system sizes at finite connection bandwidth requires interconnects that utilize surface normal communication, rather than die edge connections.  We explore systems that utilize optoelectronics on silicon to achieve this scaling.


Biographies:

Mitchell Nahmias, CTO and Co-Founder, Luminous Computing, USA

Dr. Mitchell Nahmias is the Chief Technology Officer and Co-Founder of Luminous Computing - a moonshot photonic computing company backed by Bill Gates developing a 1000x improvement over state-of-the-art AI chips. During his Ph. D. at Princeton, he helped create the field of Neuromorphic Photonics. Mitch has 60+ publications and 1000+ citations to his name, and was a National Science Foundation Fellow.

 

 

Robert (Ted) Weverka, Senior Optical Physicist and IP Lead, Fathom Computing, USA

 

Ted Weverka started work in systems and devices for optical computing in the early 80’s, developing adaptive neural networks and radar signal processing systems. These analog systems grew to utilize volume holographic adaptive weights for large-scale high-speed systems. Ted founded Network Photonics, developing WDM digital communication systems for metro area optical networks.  He is currently developing a pioneering optoelectronic computer for artificial neural networks at Fathom Computing. Ted is a member of the graduate faculty at the University of Colorado, Boulder and on the editorial board of Fiber and Integrated Optics.

Sponsored by: