Thermodynamic computing offers a potential route to energy-efficient computation. Unlike digital or quantum computing, which must at considerable energetic cost overpower or suppress the effects of thermal noise, thermodynamic computing is designed to use thermal noise as a source of energy. Physical devices whose states evolve under Langevin dynamics (overdamped or underdamped) can be engineered to perform computations as they relax toward thermal equilibrium. Because these computations are carried out by the natural dynamics of the system, such devices can in principle operate with very low energy overhead, approaching fundamental thermodynamic limits. A key challenge for thermodynamic computing is to identify algorithms that reproduce the algebraic and machine-learning operations done digitally, while making efficient use of thermodynamic hardware. The Foundry Theory facility is developing methods to train thermodynamic computers in order to perform the broad range of tasks addressed by modern machine learning.
Was this page useful?
Send
