Cognitive simulation (CogSim) is an important and emerging workflow for HPC scientific exploration and scientific machine learning (SciML). This presentation will discuss recent tests with hybrid workflows that intertwine data-driven, learning models with traditional scientific simulation.  These workflows include complex physical simulation with a surrogate model “inside” the computational loop.

The major driver behind Machine Learning going mainstream is the exponential growth of chip performance through Moore’s law over the last four decades. However, when it comes to ML for the future, Moore’s law is not enough. Mere scaling through going to a lower node is not sufficient to keep pace with the ever-increasing complexity of ML workloads for both training and inference. Add energy efficiency to the mix and we need a dramatically new class of hardware – silicon optimized for specific domains.