Researchers Accurately Simulate 100 Million Atoms With Machine Learning

Harvard researchers have developed a deep equivariant neural network that is capable of simulating 44 million atoms with quantum fidelity. This is achieved through a combination of innovative model architecture, massive parallelization, and models and implementations optimized for efficient GPU utilization. The Allegro architecture bridges the accuracy speed tradeoff of atomistic simulations and enables description of dynamics in structures of unprecedented complexity. To illustrate the scalability of Allegro, they perform nanoseconds-long stable simulations of protein dynamics and scale up to a 44-million atom structure of a complete, all-atom, explicitly solvated HIV capsid on the Perlmutter supercomputer. This is the first scalable, transferable machine-learning potential with state-of-the-art equivariant deep-learning accuracy.