The following is a special contribution to this blog by Sankar Basu, National Science Foundation (NSF) Program Director for Computing and Communication Foundations.
NSF recently announced a new program solicitation, Energy-Efficient Computing: from Devices to Architectures (E2CDA), which is a partnership with among NSF’s Computer & Information Science & Engineering (CISE) Directorate and the Engineering (ENG) Directorate with the Semiconductor Research Corporation.
Through this joint solicitation, NSF and SRC aim to support game-changing research that can set the stage for the next paradigm of computing – from mobile devices to data centers – by minimizing the energy impact of future computing systems.
The program synopsis reads as follows:
There is a consensus across the many industries touched by our ubiquitous computer infrastructure that future performance improvements across the board are now severely limited by the amount of energy it takes to manipulate, store, and critically, transport data. While the limits and tradeoffs for this performance-energy crisis vary across the full range of application platforms, they have all reached a point where evolutionary approaches to addressing this challenge are no longer adequate.
Truly disruptive breakthroughs are now required, and not just from any one segment of the entire technology stack. Due to the complexity of the challenges, revolutionary new approaches are needed at each level in the hierarchy. Furthermore, simultaneous co-optimization across all levels is essential for the creation of new, sustainable computing platforms.
These simultaneous technical and organizational challenges have never been as complex or as critically important as they are now. The urgency of solving the multi-disciplinary technical challenges will require new methods of collaboration and organization of the technical researchers.
A comprehensive and collaborative approach therefore must be undertaken to maximize the potential for successfully identifying and implementing revolutionary solutions to break through the bottleneck of energy-constrained computational performance. Programmers, system architects, circuit designers, chip processing engineers, material scientists, and computational chemists must all explore these new paths together to co-design an optimal solution path.
The NSF and the SRC recognize this need, and agreed to embark on a new collaborative research program to support compelling research that is of paramount importance to industry, academia and society at large. This partnership will specifically be supporting new research to minimize the energy impact of processing, storing, and moving data within future computing systems, and will be synergistic with other existing and future research which addresses other aspects of this overarching energy-constrained computing performance challenge.
The effort aligns with interagency initiatives and priorities, including the National Strategic Computing Initiative (NSCI) and the Nanotechnology-Inspired Grand Challenge for Future Computing. For more information, you can also see the Computing Community Consortium (CCC) white paper, Opportunities and Challenges for Next Generation Computing, that articulates some opportunities and challenges for dramatic performance improvements of both personal to national scale computing, and discusses some “out of the box” possibilities for achieving computing at this scale.
NSF looks forward to the new research that will be supported through this endeavor. The deadline for submissions is March 28, 2016. Please read the full program solicitation for more information. You can also access the slides from a recent informational webinar.
