Thermodynamic Computing System for AI Applications
This work addresses the problem of accelerating AI applications, especially generative and probabilistic AI, for researchers and engineers by proposing a physics-based hardware solution, though it is incremental as it builds on existing thermodynamic computing concepts.
The authors tackled the need for novel computing hardware to accelerate AI by developing the first continuous-variable thermodynamic computer, called the stochastic processing unit (SPU), which demonstrated Gaussian sampling and matrix inversion on hardware with 8 unit cells.
Recent breakthroughs in artificial intelligence (AI) algorithms have highlighted the need for novel computing hardware in order to truly unlock the potential for AI. Physics-based hardware, such as thermodynamic computing, has the potential to provide a fast, low-power means to accelerate AI primitives, especially generative AI and probabilistic AI. In this work, we present the first continuous-variable thermodynamic computer, which we call the stochastic processing unit (SPU). Our SPU is composed of RLC circuits, as unit cells, on a printed circuit board, with 8 unit cells that are all-to-all coupled via switched capacitances. It can be used for either sampling or linear algebra primitives, and we demonstrate Gaussian sampling and matrix inversion on our hardware. The latter represents the first thermodynamic linear algebra experiment. We also illustrate the applicability of the SPU to uncertainty quantification for neural network classification. We envision that this hardware, when scaled up in size, will have significant impact on accelerating various probabilistic AI applications.