Scalable HPC platform and memory expansion techniques using Die-to-Die and LPDDR subsystems

With advanced packaging and interface solutions, it is possible to connect multiple CPU clusters (near or far) and share external memory resources among them. We will review some of the IPs required to build such a platform and recommend applications that can benefit from it.

This webinar will be useful to designers, architects, and application engineers to understand the solution required to scale high-performance compute (HPC) nodes.

Speakers

Ketan Mehta Sr. Director, Product/Application Marketing, Interface IPKetan Mehta
Sr. Director, Product/Application Marketing, Interface IP

As the Sr. Director of Interface IP at OpenFive, Ketan Mehta is responsible for HBM Memory, Interlaken, Ethernet, Die-to-Die links, and other high-speed interfaces. With over 25 years of experience in engineering, product planning, and marketing, Ketan has a rich background in IP connectivity solutions for various applications including high-performance computing (HPC), AI, networking, data center, and storage. He received his M.S. degree in electrical engineering from The University of Texas at San Antonio, and his MBA from San Jose State University.