What, exactly, is thermodynamic computing? (Yes, we know everything obeys thermodynamic laws.) A trio of researchers from Microsoft, UC San Diego, and Georgia Tech have written an interesting viewpoint in the June issue of Communications of ACM – “A Vision to Compute like Nature: Thermodynamically.”
Arguing that traditional computing is approaching hard limits for many familiar reasons, Todd Hylton (UCSD), Thomas Conte (Georgia Tech), and Mark Hill (Microsoft) sketch out this idea that it may be possible to harness thermodynamic computing to solve many currently difficult problem sets and to do so with lower power and better performance.
“Animals, plants, bacteria, and proteins solve problems by spontaneously finding energy-efficient configurations that enable them to thrive in complex, resource-constrained environments. For example, proteins fold naturally into a low-energy state in response to their environment,” write the researchers. “In fact, all matter evolves toward low-energy configurations in accord with the Laws of Thermodynamics. For near-equilibrium systems these ideas are well known and have been used extensively in the analysis of computational efficiency and in machine learning techniques,” write the researchers in their paper.
There’s a nice, summary description of the TC notion on a Computing Community Consortium (CCC) blog this week:
What if we designed computing systems to solve problems through a similar process? The writers “envision a thermodynamic computing system (TCS) as a combination of a conventional computing system and novel TC hardware. The conventional computer is a “host” through which users can access the TC and define a problem for the TC to solve. The TC, on the other hand, is an open thermodynamic system directly connected to real-world input potentials (for example, voltages), which drive the adaptation of its internal organization via the transport of charge through it to relieve those potentials.”
In the ACM Viewpoint, the researchers say, “[W]e advocate a new, physically grounded, computational paradigm centered on thermodynamics and an emerging understanding of using thermodynamics to solve problems that we call “Thermodynamic Computing” or TC. Like quantum computers, TCs are distinguished by their ability to employ the underlying physics of the computing substrate to accomplish a task.” (See the figure below from the paper)
The recent Viewpoint is actually the fruit of a 2019 thermodynamic computing workshop sponsored by CCC and organized by the ACM Viewpoint authors. In many ways, their idea sounds somewhat similar to adiabatic quantum computing (e.g. D-Wave Systems) but without the need to maintain quantum state coherence during computation.
“Among existing computing systems, TC is perhaps most similar to neuromorphic computing, except that it replaces rule-driven adaptation and neuro-biological emulation with thermo-physical evolution,” is how the researchers describe TC.
The broad idea – to let a system seek thermodynamic equilibrium to compute – isn’t new and has been steadily advancing, as they note in their paper:
“The idea of using the physics of self-organizing electronic or ionic devices to solve computational problems has shown dramatic progress in recent years. For example, networks of oscillators built from devices exhibiting metal-insulator transitions have been shown to solve computational problems in the NP-hard class. Memristive devices have internal state dynamics driven by complex electronic, ionic, and thermodynamic considerations, which, when integrated into networks, result in large-scale complex dynamics that can be employed in applications such as reservoir computing. Other systems of memristive devices have been shown to implement computational models such as Hopfield networks and to build neural networks capable of unsupervised learning.
“Today we see opportunity to couple these recent experimental results with the new theories of non-equilibrium systems through both existing (for example, Boltzmann Machines) and newer (for example, Thermodynamic Neural Network) model systems.”
The researchers say thermodynamic computing approaches are “particularly well-suited for searching complex energy landscapes that leverage both rapid device fluctuations and the ability to search a large space in parallel, and addressing NP-complete combinatorial optimization problems or sampling many-variable probability distributions.”
They suggest a three-prong TC development roadmap:
- Using classical computing to model and simulate potential TC advances and, conversely, focusing the lens of TC back on classical systems in order to improve them.
- Developing nearer-term hybrid computer systems with both classical and thermodynamically-augmented components—for example, thermodynamic “bits,” “neurons,” “synapses,” “gates,” and “noise generators”—and evolving these systems toward greater TC exploitation.
- Creating systems using complex thermodynamics networks wherein a classical computing system provides an interface to and scaffolding for mesoscale assemblies of interacting, self-organizing components exhibiting complex dynamics and multiscale, continuously evolving structure, either at room temperature or—if quantum effects are key—at very low temperature (milliKelvin).
“At least initially, we expect that TC will enable new computing opportunities rather than replace Classical Computing at what Classical Computing does well (enough), following the disruption path articulated by Christensen. These new opportunities will likely enable orders of magnitude more energy efficiency and the ability to self-organize across scales as an intrinsic part of their operation. These may include self-organizing neuromorphic systems and the simulation of complex physical or biological domains, but the history of technology shows that compelling new applications often emerge after the technology is available.”
The viewpoint is fascinating and best read directly.
Link to ACM Thermodynamic Computing Viewpoint: https://cacm.acm.org/magazines/2021/6/252841-a-vision-to-compute-like-nature/fulltext