AI-Guided Codesign Framework for Novel Material and Device Design applied to MTJ-based True Random Number Generators
This work addresses the time-consuming process of designing novel materials and devices for energy-efficient computing, specifically for true random number generators, but it appears incremental as it applies existing AI methods to a specific domain.
The paper tackled the design of magnetic tunnel junction devices for true random number generation by using reinforcement learning and evolutionary optimization to vary device and material properties, resulting in candidate devices that generated stochastic samples for desired probability distributions while minimizing energy usage.
Novel devices and novel computing paradigms are key for energy efficient, performant future computing systems. However, designing devices for new applications is often time consuming and tedious. Here, we investigate the design and optimization of spin orbit torque and spin transfer torque magnetic tunnel junction models as the probabilistic devices for true random number generation. We leverage reinforcement learning and evolutionary optimization to vary key device and material properties of the various device models for stochastic operation. Our AI guided codesign methods generated different candidate devices capable of generating stochastic samples for a desired probability distribution, while also minimizing energy usage for the devices.