Nature Communications · 2024 · 75 citations · 53 references
EngineeringComputer EngineeringComputer ScienceField-programmable Gate ArraysMachine LearningMicroelectronicsDevice ModelingMetal-oxide-semiconductor Field-effect TransistorsMonte Carlo MethodsMonte Carlo SimulationPower OptimizationRandom Number GenerationBoltzmann MachinesComplementary Metal-oxide-semiconductor DevicesDeep Boltzmann MachinesField-programmable Gate Arrays (Fpgas)Magnetic Tunneling JunctionsMetal-oxide-semiconductor Field-effect Transistor ModelingProbabilistic CircuitsPrototyping With Field-programmable Gate Arrays
Abstract Extending Moore’s law by augmenting complementary-metal-oxide semiconductor (CMOS) transistors with emerging nanotechnologies (X) has become increasingly important. One important class of problems involve sampling-based Monte Carlo algorithms used in probabilistic machine learning, optimization, and quantum simulation. Here, we combine stochastic magnetic tunnel junction (sMTJ)-based probabilistic bits (p-bits) with Field Programmable Gate Arrays (FPGA) to create an energy-efficient CMOS + X (X = sMTJ) prototype. This setup shows how asynchronously driven CMOS circuits controlled by sMTJs can perform probabilistic inference and learning by leveraging the algorithmic update-order-invariance of Gibbs sampling. We show how the stochasticity of sMTJs can augment low-quality random number generators (RNG). Detailed transistor-level comparisons reveal that sMTJ-based p-bits can replace up to 10,000 CMOS transistors while dissipating two orders of magnitude less energy. Integrated versions of our approach can advance probabilistic computing involving deep Boltzmann machines and other energy-based learning algorithms with extremely high throughput and energy efficiency.
53
On Information and Sufficiency
S. Kullback, R. A. Leibler · The Annals of Mathematical Statistics · 1951 · 20K citations · Full text
An Introduction to MCMC for Machine Learning
Christophe Andrieu, Nando de Freitas, Arnaud Doucet et al. · Machine Learning · 2003 · 2.4K citations · Full text
ASAP7: A 7-nm finFET predictive process design kit
Lawrence T. Clark, Vinay Vashishtha, L. Shifren et al. · Microelectronics Journal · 2016 · 736 citations · Full text