Data Centers At Meta: Heterogeneous Integration Driven By AI/ML And Network Applications
Ravi Agarwal
-
EPS
IEEE Members: Free
Non-members: FreeLength: 00:31:15
Abstract: This talk focuses on heterogeneous integration for Artificial Intelligence, Machine Learning and network applications at Meta Infrastructure, and discusses implications for packaging and system-level considerations. The talk also shares some of the advanced packaging (chiplet) initiatives in which Meta is participating to develop an open ecosystem.
Bio: Ravi Agarwal is a technical sourcing manager at the Facebook Infrastructure group. In this role, he is responsible for driving advanced packaging architectures and foundry for both networking and AI/ML compute applications to meet Facebook’s future workloads. He is driving Chiplet Business Workstream in Open Domain-Specific Architecture (ODSA) Sub-Project within the Open Compute Project (OCP), working with ecosystem partners to enable a Chiplet marketplace. Prior to Facebook, he spent 12+ years at Intel Corporation and Amkor Technologies, where he held several leadership positions. In his last role at Intel, he was Chief of Staff to Intel Global Supply Chain Corp. Vice President.
Ravi received PhD dual major in Materials Science & Engineering and Polymer Science from North Carolina State University and MBA from University of California Berkeley. Ravi has 17+ years of High Tech industry experience in the areas of advanced packaging, supply chain strategy, product management, and business operations. He has co-authored more than 20 journal and conference publications, and holds 6 U.S. Patents.