Solid State Technology and Devices Seminar: A Framework for Information Processing: Computing Beyond Moore’s Law

Seminar: Solid State Technology and Devices: EE: CS: Data Science | October 18 | 1-2 p.m. | Cory Hall, The Hogan Room, 521

 Sadasivan Shankar, Ph.D, Associate in Applied Physics, Harvard Paulson School of Engineering and Applied Sciences, Cambridge, MA

 Electrical Engineering and Computer Sciences (EECS)

The computer revolution, rolling past its fifty-year march as one of the most significant advancements of human civilization, has been enabled by a confluence of breakthroughs in science and engineering. This revolution known by the moniker Moore’s Law has evidently slowed leading to the question of how computing of the future will evolve. With this as the backdrop, we present the rationale for and describe an adaptable and scalable framework (“Co-design Version 3.0”), which can be used to configure, and “personalize” computing driven by the specific needs of applications. We will examine 6 different scaling paradigms that are driving this need for a change in thinking: combinatorial nature of scientific problems, multiscale nature of systems, algorithms, complexity of applications, Moore’s law, and economics of scaling.

To realize this vision in a cost-effective way, this should be done in a scalable manner to help in wider dispersion of the benefits of computing rather than to niche scientific communities. We think that both research and development in natural, computational, and mathematical sciences along with centers of computational and physical sciences need to be formally engaged. In addition, the co-design should also address manufacturing of complex materials and devices. As part of this talk, we will also briefly illustrate a new class that we have developed in which students are taught hands-on about using extreme computing to address real applications. With a focus on real applications, we anticipate co-design will shift the way computing is evaluated and enable many possibilities in applying computing to solve societal problems.

 CA, dadevera@berkeley.edu, 510-642-3214