Storage 2020: A Vision for the Future of HPC Storage
Glenn K. Lockwood, Damien Hazen, Quincey Koziol, Richard Shane Canon, Katie Antypas, J. Balewski, Nicholas Balthaser, W. Bhimji, J Botts, Jeff Broughton, Tina Butler, Gregory Butler, Ravi Cheema, Christopher S. Daley, Tina Declerck, L. Gerhardt, Wayne Hurlbert, Kristy Kallback-Rose, Stephen Leak, Jason Lee · 2017
The explosive growth in data over the next five years that will accompany exascale simulations and new experimental detectors will enable new data-driven science across virtually every domain. At the same time, new nonvolatile storage technologies will enter the market in volume and upend long-held principles used to design the storage hierarchy. The disruption that these forces will bring to bear on high-performance computing (HPC) will also create significant opportunities to innovate and accelerate scientific discovery. To ensure that NERSC fully capitalizes on these opportunities, we have developed a comprehensive vision for the future of storage in HPC and identified short- and long-term strategic goals to effectively realize this vision. This report presents the results of this effort and offers a blueprint for designing a storage infrastructure for supporting HPC through 2025 and beyond.