The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop:SuperCheck-SC21: Second International Symposium on Checkpointing for Supercomputing
Authors: Deborah Bard (Lawrence Berkeley National Laboratory (LBNL))
Abstract: Computing has been an important part of the scientists toolkit for decades, but the increasing volume and complexity of scientific datasets is transforming the way we think about the use of computing for experimental science. DOE supercomputing facilities have begun to expand services and provide new capabilities in support of experiment workflows via powerful computing, storage and networking systems. Experiment teams increasingly look to HPC centers for realtime data analysis to monitor, steer and analyse a running experiment. In this talk I will introduce how supercomputing at NERSC is being leveraged in experimental science to change the way we collect and analyze data in fields as diverse as particle physics, cosmology, materials science and structural biology. Through case studies and real-life challenges, I will describe the science requirements that are driving our work, and how this translates into technical innovations with a particular focus on scheduling and policy decisions.