GGrantIndex
← Search

SHF: NeTS: Medium: Collaborative Research: The Power of Less Wiring: Wireless NoC-enabled Voltage-Frequency Islands (VFIs) for Energy-Efficient Multicore Platforms

$172,019FY2015CSENSF

Washington State University, Pullman WA

Investigators

Abstract

Parallel processing via massively integrated multicore systems can offer unprecedented levels of performance for many real applications, e.g., networking, e-commerce, scientific computing, entertainment, etc. However, the design of such multicore platforms is dominated by the power and thermal constraints that need to be addressed in order to make them practical. Indeed, the increasing power and thermal dissipation represents a major concern due to its impact on performance, temperature, reliability, scalability, and environmental impact. Consequently, this project targets an interdisciplinary research-based curriculum for power and thermally efficient multi-core system design meant to raise awareness and increase the number of students attracted to this area of engineering. Towards this end, this project also aims at involving underrepresented groups in research through REU and IGERT projects via catalyzing the creation of more sustainable environments. In terms of technical aspects of the research, this project defines an integrated theory-implementation-evaluation framework, which aims at developing new algorithms, architectures, and tool-sets to design and evaluate sustainable multicore systems while provisioning the system resources for the necessary power/performance/thermal trade-offs. The research objectives target the development of a new communication network consisting of both traditional wires and emerging on-chip wireless links suitable to support voltage and frequency scaling, new algorithms for distributed resource management and hierarchical control under multi-kernel operating systems, and unified power-performance models for extended range dynamic voltage and frequency scaling with validation of power/performance trade-offs.

View original record on NSF Award Search →