Image
Stanford EE

Lightwave Fabrics: At-Scale Optical Circuit Switching for Datacenter and Machine Learning Systems

Summary
Dr. Kevin Yasumura (Google Platforms Optics Team)
Skilling Auditorium; Zoom
Mar
5
Date(s)
Content

Zoom ID: 97763044901

Password: 427136


 

ABSTRACT: We describe our experience developing what we believe to be the world’s first large-scale production deployments of lightwave fabrics used for both datacenter networking and machine-learning applications.  Optical circuit switches and optical transceivers developed in-house have produced a lightwave fabric that is reconfigurable, low latency, rate agnostic, and highly available.  These fabrics have provided substantial benefits for long-lived traffic patterns in tightly-coupled machine learning clusters.  We also report results for a large-scale ML superpod with 4096 tensor processing unit chips that has more than one exaflop of computing power.

Bio: Kevin Yasumura is a Principal Engineer/Director in Google’s Platforms Optics Team. At Google he is the Technical Lead for MEMS and optical switching development.  His optical switches are used worldwide for both datacenter networking and machine-learning applications and are critical to Google’s entire business model.  He has over 25 years of experience developing MEMS-based products and systems.  Before joining Google, he was a founding member and Manager of Micro-machining Development at Iolon Corporation where they developed MEMS tunable lasers, tunable filters, and optical switches.  He was also Senior Director of Product Development at Formfactor where he led the development of MEMS-based integrated circuit test solutions.  He holds a bachelor’s degree in physics from U.C. Berkeley and an M.S. and Ph.D. in applied physics from Stanford University.