The NERSC-9 High Performance Computing System named after Nobel Laureate Saul Perlmutter will provide a 3-4x increase in capability for NERSC users over existing systems. Announced last month, the Cray Shasta system was designed to support both large scale simulations as well as data analysis from DOE’s experimental facilities. The system features 30PBs of an all-flash Lustre file system, the Cray Slingshot interconnect, a scalable data analysis and machine learning software stack, and a robust application readiness effort for simulation, learning and data applications. This talk will discuss the NERSC-9 architecture, software, timeline and plans to support a growing and diverse workload from DOE’s experimental facilities.
About the Speaker: Katie Antypas
Katie is the Division Deputy and Data Department Head at the National Energy Research Scientific Computing (NERSC) Center at Lawrence Berkeley National Laboratory. Katie is also the Project Director of the NERSC-9 system, NERSC’s next generation system arriving in 2020 that will support large scale simulation and data workloads. She lead the NERSC-8 Cori system project as well. Katie is PI on an ASCR Research Project, “Science Search: Automated MetaData Using Machine Learning” and is interested in how experimental science facilities can leverage HPC. Before coming to NERSC, Katie worked at the ASC Flash Center at the University of Chicago supporting the FLASH code, a highly scalable, parallel, adaptive mesh refinement astrophysics application. She has an M.S. in Computer Science from the University of Chicago and a bachelors in Physics from Wellesley College.