DescriptionIn the next few years, exascale computing systems will become available to the scientific community. They will require new levels of parallelization, new models of memory and storage, and a variety of node architectures for processors and accelerators. They will also provide simulation capabilities with unprecedented scale and complexity across many fields of science, helping to answer fundamental science questions in cosmology, astrophysics, and nuclear science; understand and address issues in climate change, the environment and seismic safety; and aid in the design of advanced materials, manufacturing, energy systems, and pharmaceuticals. These systems may also offer exascale data analysis capabilities, allowing genomics, images, and sensor data to be processed, analyzed, and modeled using comparisons with simulations, deep learning algorithms or other machine learning methods. In this talk, I will present some of the exciting science opportunities, the need for advanced in algorithms and mathematics to advance along with the system performance, and how the variety of workloads will stress the different aspects of exascale hardware and software systems.