Publication date: 15th April 2025
Artificial intelligence (AI) is pushing the limits of digital computing to such an extent that, if current trends were to continue, global energy consumption from computation alone would surpass all other forms of energy in the next two decades. One promising approach to reduce energy consumption and to increase computational speed to meet growing demands is in-memory analog computing. However, analog computing necessitates a fundamental rethinking of computation at the material level, where information is stored as continuously variable physical observables. This shift introduces difficulties related to the accuracy, dynamic range, and reliability of analog devices — issues that have hindered the development of existing memory technology for use in analog computers. Here, we address these issues in the context of memory which stores information as resistance. Our approach utilizes an electrochemical cell to tune the bulk defect concentration within a metal oxide film, with integrated control over thermal, chemical and electrical degrees of freedom. The resulting electro-thermo-chemical random-access memory (ETCRAM) exhibits a dynamic range of more than six decades of analog tunable resistance with thousands of available states, deterministic write operations with high accuracy, and programming speeds as fast as 15 ns.