Keynote Address: New Horizons in Modeling and Simulation in Julia

Presenters: Viral Shah (Julia Computing, CEO and Co-Founder), Chris Rackauckas (Julia Computing, Director of Modeling and Simulation and Christopher Laughman (Mitsubishi Electric Research Laboratories, Principal Member Research Staff)

Abstract: As modeling has become more ubiquitous, our models keep growing. The time to build models, verify their behavior, and simulate them is increasing exponentially as we seek more precise predictions. How will our tools change to accommodate the future? Julia’s language design has led to new opportunities. The combination of multiple dispatch, staged compilation, and Julia’s composable libraries have made it possible to build a next generation symbolic-numeric framework. Julia’s abstract interpretation framework enables capabilities such as automatic differentiation, automatic surrogate generation, symbolic tracing, uncertainty propagation, and automatic parallelism. These features have allowed us to build various applications in pharmaceuticals, aerospace, energy, materials, circuits, and much more – demonstrating performance and productivity that are many orders of magnitude better.