NoLoSS: Enabling Exascale Science through Node Local Storage Systems
External storage systems, such as parallel file systems, provide a number of important capabilities to today's high-performance computing systems: holding checkpoints that allow applications to tolerate failures, temporarily storing data for subsequent analysis, and preserving science results. However, scaling the external storage model to provide the necessary I/O bandwidth and capacity strains power, cooling, and cost budgets. The development of inexpensive, nonvolatile memory technologies such as flash memory and phase-change memory make it feasible to include solid-state, persistent memory inside future extreme-scale systems.
The goal of the NoLoSS project is to conduct a detailed assessment of the potential roles and benefits of in-system storage in extreme-scale computational science, so that scientists can build more effective future systems for scientific discovery.