Argonne’s featured DOE booth speaker, Arvind Ramanathan, will present “AI-driven Adaptive Multiresolution Molecular Simulations on Heterogeneous Computing Platforms.” The talk will address how emerging hardware tailored for artificial intelligence (AI) and machine learning (ML) provides a novel means to couple AI and ML methods with traditional high performance computing (HPC) workflows involving molecular dynamics (MD) simulations. Stream-AI-MD, which applies deep learning methods to drive adaptive MD simulation campaigns, allows researchers to run ensemble MD simulations on GPU clusters, while the data from atomistic MD simulations are streamed continuously to AI/ML approaches to guide the conformational search on a wafer-scale AI accelerator.