Abstract
With the decline and eventual end of historical rates of lithographic scaling, we arrive at a crossroad where synergistic and holistic decisions are required to preserve performance over power scaling in digital computing. Numerous technologies are emerging with this exact aim, from devices (transistors), memories, 3D integration, specialization, photonics, and others. This vast range of technologies with the same goal creates a grand challenge at the architectural and system levels of not only properly evaluating each technology at such a high level but also creating a strategy to pave a path forward for digital computing by making the best use out of all technology options. In this talk, I will provide the architect's view with an overview of some promising emerging technologies, how they interact with each other, as well as discuss how to create methodologies to efficiently explore the vast design space that all these new options create.
Biography
Dr. George Michelogiannakis is a research scientist in the computer architecture group (CAG) in the computational research division (CRD). He has extensive work on networking (both off- and on-chip) and computer architecture. His latest work focuses on the post Moore's law era looking into specialization, emerging devices (transistors), memories, photonics, and 3D integration. He is also currently working on optics and architecture for HPC and datacenter networks.