2020 OCP Virtual Summit

There is increasing variety in hyperscale workloads, and in the types of computation and acceleration engines to address them. These engines need to operate on large scales of data and do so quickly, leading to unprecedented engineering and planning challenges in hyperscale datacenters. One efficient way to address this complexity is to disaggregate the various subsystems in the server and distribute them in the data center. The concept is known but has been difficult to execute in the past. But we may finally be ready to take this on. Our panel has extensive experience in architecting and deploying hyperscale infrastructure and are subject matter experts in servers, storage and networking, so we will cover the key issues in disaggregating data centers and how to address them.