CS Distinguished Colloquium - Ramana Kompella and John Marshall, Cisco

Event time: 
Friday, October 9, 2020 - 4:00pm
Location: 
Zoom Presentation See map
Event description: 

CS Distinguished Colloquium

Ramana Kompella, Cisco
John Marshall, Cisco

Zoom link: https://yale.zoom.us/j/92748598082

Host: Robert Soule

Ramana Kompella, Cisco
Title: Research topics of interest in emerging tech areas for Cisco

Abstract:

In the past few months, Cisco Research has started focusing on several emerging technology areas of interest to Cisco. In this talk, I will be talking a bit about  what these areas are of research interest are, how we are leveraging and engaging with universities for tech and societal impact.

Bio:

Dr. Ramana Kompella is currently the Head of Research in the Emerging Technology and Incubation group at Cisco. His previous experience includes co-founding successful startups, and providing engineering leadership to build world class products currently in use in several hundreds of customers’ data centers. Prior to his industry roles, he was a tenured faculty at Purdue in Computer Science Department, where he conducted research on systems and networking areas, with multi-million dollar grants from NSF and other industry sources. He co-advised several PhD and Masters students, and has co-authored 70+ publications in top networking and systems conferences such as SIGCOMM. He was the recipient of several awards including the prestigious NSF CAREER award.

John Marshall, Cisco
Title: Exploring the Potential of Edge Computing

Abstract:

With the growth of end-points, 5G mobility, and volumes of data used for analytics, edge computing brings computation closer to where data is generated that allows machine learning algorithms to provide faster response times and improved efficiency.  Local processing can also offer autonomous operation improving availability and greater network utilization.

The benefits are clear; however, the definition of the edge will continue to evolve to support the processing needs of the Internet of Things (IoT).  Architectural trade-offs need to be considered which enables efficient distributed processing to occur between IoT devices, local edge servers, and cloud computing resources.  The datacenter’s physical operating environment isn’t able to be easily extended in terms of power delivery, cooling needs, or even physical space.  Simply using smaller compute units, CPUs & GPUs, is not sufficient.

Tomorrow’s edge computing environment needs to support vastly improved power efficiency over a range of physical operating environments while enabling a common software-defined framework for operational agility.  Applications will likely adapt to enable edge-compute to augment IoT processing while maintaining data privacy & security.

Bio:

John Marshall is a Distinguished Engineer at Cisco Systems.  His interest in network innovation includes programmable data planes, network processor architecture, and high-performance packet classification.  His current focus is on the development of a next-generation Data Processing Unit (DPU) for edge computing.  John has held numerous silicon architectural and design roles at Cisco involving the application advanced memory technologies.

Before joining Cisco, he worked for IBM as a senior designer in disciplines that include network processors, switch fabrics, and vector processing.  John holds over 25 patents in processor and system design.  He also has several publications in the areas of computer architecture & networking.