Tutorial EL21—Research Approaches for Energy Efficient Computing

Instructors: Sasikanth Maniputrani, Kepler Compute; Kaustav Banerjee, University of California, Santa Barbara; Asif Khan, Georgia Institute of Technology; Daniel Gall, Rensselaer Polytechnic Institute; Zhihong Chen, Purdue University; Madhavan Swaminathan, Penn State University

There has been a collective effort among academia, industry, and government to explore multi-faceted approaches for advancing low energy computing.  Making computation more energy-efficient saves money, reduces energy use, and herald the advent of entire systems built into high-performance, compact form factors.
 
New materials make possible compute hardware stack elements needed for this revolution.  Starting at the smallest scale, there are switching elements that comprise logic and/or memory.  These elements are integrated into systems-on-chip (SoC) and subsequently assembled into systems-in-package (SiP). Advanced passive components and thermal management solutions are all seamlessly stitched together with fast, low-energy connections to achieve unprecedented power and performance in the smallest area. 
 
This tutorial will focus on research in different components of the compute stack:
 
·   Charge-based energy efficient devices
·         Non-charge based energy efficient devices
·         Future low-energy memory solutions
·         Low energy interconnects
·         Higher efficiency thermal management
·         Heterogeneous integration, and potentially
·         Neuromorphic computing (with materials thrust)

Tutorial Schedule