Integrating metadata tools with the data services archive to provide Web-based management of large-scale scientific simulation data

Abstract

A metadata tool system and a data service system are undergoing development and integration, at Sandia National Laboratories, to provide Web-based access to high-performance computing clusters and its associated simulation data. These clusters host a set of scalable post-processing applications for very large data manipulation, and the examination of results generated by high-fidelity simulations in support of the design to analysis process for ensuring safety and reliability of the nation's nuclear weapons stockpile. The primary subject of this work is the integration of metadata tools with a data service archiving capability, resulting in a service-oriented and Web-based architecture, which provides end users the ability from their desktops to manage and understand simulation results for very large, complex problems.