Non-Boolean Computer Architectures

MOTIVATION
Most information processing is Boolean.  This paradigm has obviously and deservedly persisted due to Moore's Law scaling.  However, it widely expected that Moore's Law will face hard limits due to issues such as device-to-device variation associated with further miniaturization, power density requirements, etc.  

An alternative approach is to process information in a non-Boolean fashion.  Nature suggests that this is obviously a successful approach.  The human brain works well at 30 W — and is capable of delivering the equivalent of 3e6 MIPS / W for certain applications. By comparison, a Dell Pentium 4 might operate at 200W and delivers just 5 MIPS / W [1].  Additionally, a commodity cellular nonlinear network (CNN)-based image processor with an area of 1.4 cm2 and a power budget of just 4.5 W can match the performance of the IBM cellular supercomputer — which has an area of ~7 m2 and a power budget of 491 kW [2]. While non-Boolean systems may not map well to general purpose processing, they are capable of solving problems that are expected to be commonplace in future information processing workloads (pattern matching, etc.)  As such, investment in non-Boolean hardware both for standalone functionality and for hardware accelerators seems promising.  

[1] Ralph Cavin, “Computation vis-à-vis Physics”, [2] Analogical and Neural Computing Lab, Budapest

Project Specifics

• This work will identify wave-like non-Boolean computational primitives based on the spatial-temporal characteristics of such processor networks, and inspiration will be gained from known wave behavior in physics and applications derived from these. In addition, nanoelectronic systems will be explored where such wave-type excitations might find a natural implementation. This research will identify, on the physical level, computational building blocks based on nanoelectronic structures with spatial-temporal wave-like dynamics, and on the computer science level, ways to perform computation with such non-Boolean primitives. This interdisciplinary research, which spans the whole range from nanostructures to new paradigms for computing, will require a team with expertise that spans the whole range from physics to computer science. 

• This work will lay the groundwork for a radically different approach to information processing, which is based on physics-inspired and brain-like wave behavior in large-scale arrays of nanoelectronic processing elements. Specifically, our research will identify computational building blocks of future computing systems, along with the inherent state variables, where each computational task directly maps onto the underlying physical structure. This project will also identify which information-processing tasks will find their natural implementation in such architectures.

Students

• Robert Perricone — G0raduate student
• Craig Cahillane — Undergraduate student

Support

• National Science Foundation via “NEB: Physics-Inspired Non-Boolean Computation based on Spatial- Temporal Excitations,” $1,998,370.