This award supports the continuation and evolution of NSF project 1053575 - XSEDE: eXtreme Science and Engineering Discovery Environment. The goal of XSEDE is to accelerate open scientific discovery by enhancing the productivity and capability of researchers, engineers, and scholars, and by broadening their participation in science and engineering. It does so by making advanced computational resources easier to use, integrating existing resources into new, powerful services and building the community of users and providers. XSEDE is a virtual organization that provisions complex distributed infrastructure, support services, and technical expertise. A prominent opportunity for XSEDE is the growing, diverse collection of advanced computing, high-end visualization, data analysis, and other resources and services available to researchers, engineers, and scholars; these resources have the potential to help understand and solve the most important and challenging problems facing the nation and world. The challenge for XSEDE, as a virtual organization, is to organize these disparate resources, creating integrated services and a coordinated environment that serves the end user needs. The challenge also includes fostering awareness of, and training for, full utilization of the capabilities offered by XSEDE and its associated resources, as well as catalyzing workforce developments. All these tasks need to be accomplished in light of evolving user requirements, resources, and NSF strategies.
The XSEDE 2 project will be executed by the principal investigator (PI) and staff of the National Center for Supercomputing Applications (NCSA) at the University of Illinois at Urbana-Champaign and by the co-PIs and staff of the partner organizations at the Pittsburgh Supercomputing Center (PSC, Carnegie Mellon University and University of Pittsburgh), San Diego Supercomputing Center (SDSC, University of California San Diego), and Texas Advanced Computing Center (TACC, University of Texas at Austin), as well as 15 other partner organizations.
For the next five years, in pursuit of its overall goals of enhancing user productivity and broadening participation of the CDS&E community, XSEDE 2 will provide an adaptive and streamlined framework that anticipates the opportunities afforded by advances in technology, responds to users' abilities to make effective use of new capabilities, and enables the current and next generation in using these technologies to advance their fields. The three strategic goals remain unchanged from the original XSEDE project:
* To deepen and extend use of the ecosystem of national cyberinfrastructure (CI) by both existing computational researchers and new communities of scientists and students where the use of computation and large-scale data is transforming their respective fields; * To advance the national CI ecosystem by creating an open and evolving infrastructure, and by Â enhancing the array of technical expertise and support services offered; and * To sustain the national CI ecosystem by maintaining a secure, reliable and efficient infrastructure.
XSEDE 2 will reorganize into five goal-driven focus areas that will provide a more agile and responsive program designed to accelerate progress toward the strategic goals:
* The Resource Allocation Service (RAS), led by the National Center for Atmospheric Research (NCAR) and four other partners, will continue to manage the process of receiving, evaluating and awarding proposals for computational resources. In doing so, it will fulfill XSEDE 2's crucial role of neutral arbiter in allocating resources from the service-provider ecosystem to the research community. RAS will also identify new opportunities for allocation innovations by increased transparency, open reporting of user trends, and adapting the allocation process to new technologies. * The revised XSEDE Community Infrastructure (XCI) service, led by Cornell University and six other partners, will identify, evaluate, test, and make available new software capabilities. Governance is in place to ensure that these activities are driven by the needs of both users and providers of cyberinfrastructure. * Community Engagement & Enrichment (CEE), led by the University of Texas and 12 other partners, will build on the XSEDE tradition of outstanding user services, and engage a new generation of diverse computational researchers. In addition to education, training, and outreach activities, CEE will connect to campus HPC communities, to help researchers access both local and national resources. * The Extended Collaborative Support Service (ECSS), led by the San Diego Supercomputer Center, the Pittsburgh Supercomputing Center and eight other partners, will maximize the effectiveness of HPC resources through its large staff of computational experts who will directly participate in research teams, providing advanced assistance to science projects. * Finally, XSEDE Operations, led by the University of Tennessee and five other partners, will maintain and evolve an integrated HPC capability of national scale. Operations provides a "one-stop-shop" experience for users across the XSEDE-coordinated HPC ecosystem.
While continuity in providing these services is essential for the large and further-growing user community, XSEDE 2 will also respond to the evolving needs and opportunities of science and technology. To this end, XSEDE 2 will develop novel ways to connect to and collaborate with other national, regional and campus cyberinfrastructure organizations. The project will continue to innovate the use of "e-science portals" (also known as Science Gateways). Science gateways provide interfaces and services that are customized to a domain science and have an increasing role with facilities and research centers, collaborating on large research undertakings (e.g., Advanced LIGO, Polar Geospatial Center). This approach facilitates broad community access to advanced compute and data resources. Science gateways are now serving more than 50% of the user community. XSEDE 2 will also incorporate new methods to serve users interested in cloud computing resources and big-data projects. Furthermore, by analyzing trends in usage and technology, the renewal project will be even better positioned to respond to the evolving needs of its stakeholders and to emerging opportunities in new compute and data resources.