Producing Ultra-High Performing and Energy-Efficient Electronics
ECE Assistant Professor Yanzhi Wang, in collaboration with Massoud Pedram from the University of Southern California, was awarded a $500K NSF grant for “Advanced Circuits, Architectures and Design Automation Technologies for Energy-efficient Single Flux Quantum Logic.”
Abstract Source: NSF
The critical dependence of the world economy on energy-efficient operations in computing are now almost universally recognized. To this end, advances in ‘beyond-CMOS’ device technologies and corresponding logic families are now seen as a key step towards achieving the next major leap in high-performance computing. The challenges and opportunities described in this research provide directions for developing many aspects of a very promising ‘beyond-CMOS’ technology, which can result in extremely high-performance, yet energy-efficient, computing systems, and thereby ensure sustainability of the information-technology ecosystem. SuperConductive Electronics (SCE) based on the Josephson junction (JJ) Single Flux Quantum (SFQ) logic cells have evolved into a within-reach ‘beyond-CMOS’ technology, with switching speeds in the hundreds of GHz and energy dissipation of 10^-19 or less Joules per transition. The project will enhance business and societal opportunities by producing ultra-high performance and energy-efficient electronics for a wide range of computing fabrics, and in the process will also contribute to enhancing the technological capabilities of the US by providing education and research opportunities to undergraduate, graduate, and underrepresented students by including them in the planned research.
This research aims to achieve major strides in the development of advanced circuits, architectures and design-automation technologies in support of large-scale superconductive SFQ digital electronics to meet the needs of future energy-efficient, high-performance exa-scale computing systems. Research on design automation will enable large-scale SCE systems integration. Targeting both DC-powered energy-efficient Rapid SFQ and AC-powered Adiabatic Quantum-Flux-Parametron circuit families, this research aims to solve four key problems associated with the design automation and optimization of SFQ logic circuits, namely: minimization of SFQ circuit retiming to the number of buffers for operating frequency improvement and/or clock-phase consistency; path-balancing technology mapping for sequential SFQ circuits with loops; timing-driven global placement using unique features of SFQ logic families and a powerful mathematical optimization tool; and circuit partitioning to enable effective current recycling.
This award reflects NSF’s statutory mission and has been deemed worthy of support through evaluation using the Foundation’s intellectual merit and broader impacts review criteria.