RANC: A Residue Arithmetic Nanophotonic Computer
Abstract
Due to the end of Moore’s law and Dennard scaling, feature reduction and higher speed of clocking are seizing to be the source for higher computer performance. Therefore, it is of paramount interest to explore alternative technologies and architectures for this post Moore’s law era of computing. The goal of our proposed effort is to develop an integrated photonics computing systems (from device to architectures) based on the residue number system (RNS) to achieve orders of magnitude improvements in computational speed per watt over the current state of the art. Residue arithmetic is of particular interest as it can represent a large number as a set of smaller numbers, which can be processed individually in parallel. Furthermore, RNS and nanophotonics have a natural affinity where most operations can be achieved as spatial routing using electrically controlled directional coupler (‘switches’), thereby giving rise to an innovative processing in network (PIN) paradigm. Our project will explore a path for attojoule per bit efficient and fast electro optic switching devices, and use them to develop optical compute engines based on residue arithmetic leading to multi purpose nanophotonic computing. Our team’s vertical approach leverages its synergistic proven record in heterogeneous integrated photonics and light matter enhancement techniques with novel circuit and electro optic hybrid, computer architecture and high performance architectures for enabling synergistic device to architecture co design. The resulting novel compute engines feature reduced complexity and processing in network (PIN) computing schemes, which minimizes overheads. Preliminary investigations indicate figure of merits (Speed-Energy Footprint) estimates that surpass electronic counterparts by orders of magnitude. The group has the experience and facilities for fabrication, modeling, hardware design, FPGA prototyping, and extensive simulations.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Jan 14, 2022
- Source ID
- FA95501910277
Entities
People
- Tarek El Ghazawi
Organizations
- Air Force Office of Scientific Research
- George Washington University
- United States Air Force