With the explosion of data and processing required to turn that data into useful information, there is an unprecedented need for energy efficient computation. In the last decade, the rate at which data was generated outpaced improvements in compute efficiency, leading to high energy consumption. For perspective, data centers consume 200 TWh+ each year which exceeds the total energy consumption of some entire countries. Expanded use of the Internet, smart phones, and more sophisticated computation is causing all of those numbers to escalate. Making computation more energy-efficient would reduce computation cost, energy consumption, and enable batteries to run longer or be smaller for mobile computing. 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 would save money, reduce energy use, and permit batteries that provide power in mobile devices to run longer and/or be smaller.
Materials are the building blocks of the compute hardware stack. Starting at the smallest scale, there are switching elements that comprise logic and/or memory. These elements are put together at the package level with passives, thermal management solutions, and interconnects to form the integrated chip. As materials touch every one of these components, the goal of this Symposium is to focus on the materials challenges and opportunities that will accelerate solutions for energy efficient computation. There is already a substantial body of knowledge in this field spanning multiple approaches. The Symposium Co- Organizers have decided to focus specifically on the important areas described below.