The Extensible Terascale Facility (ETF) is the next stage in the evolution of NSF large-scale cyberinfrastructure for enabling high-end computational research. The ETF enables researchers to address the most challenging computational problems by utilizing the integrated resources, data collections, instruments and visualization capabilities of nine resource partners. On October 1, 2004, the ETF concluded a three-year construction effort to create this distributed environment called the TeraGrid (TG) and we are now entering the production operations phase.
The TeraGrid resource partners inclue: the University of Chicago/Argonne National Laboratory, the San Diego Supercomputer Center at UCSD, the Texas Advanced Computing Center at UT-Austin, the National Center for Supercomputing Applications at UIUC, Indiana University, Purdue University, Oak Ridge National Laboratory, and the Pittsburgh Supercomputing Center.
A separate proposal was submitted to NSF on October 19, 2004 for the TeraGrid Grid Infrastructure Group (GIG). Under the direction of Charlie Catlett at UC/ANL, in general, the GIG will be responsible for coordination of development activities for the TeraGrid with subcontracts to the partner sites. The resource partners (RP) will each have independent cooperative agreements with NSF, but will work closely with the GIG to implement the vision of the TeraGrid.
This proposal outlines the plan at NCSA to participate as a resource partner in the TeraGrid team to provide the expanding user community with ongoing access to this computational science facility. This proposal covers the period November 1, 2004 through October 31, 2009.
To fulfill NCSA's mission of enabling new scientific discoveries, NCSA brings its extensive experience and world-class leadership in supporting engineering and science research and education in a 24x7 production environment to the TeraGrid (TG). Our goals as a TG Resource Provider (RP) are to a) support applications development and tuning to enable users to develop highly effective grid applications, b) offer production-quality computational, data, and visualization services to support advanced science needs, c) respond rapidly to issues raised by users, administrators, or other TeraGrid sites, and d) support the services, software, policies, and milestones of the TG Grid Integration Group (GIG). The result of these efforts will be a stable, robust, secure, grid-enabled high-performance computing and storage environment that supports the development and execution of grid applications, science gateways, and capability applications. In fulfilling these goals, NCSA will leverage expertise and effort from other activities, including the NCSA/SDSC CyberInfrastrcture Partnership, to address the needs of the TG user communities to the greatest extent possible. The success of TG depends on the integration of the unique and collective strengths and capabilities of the individual sites and the GIG. NCSA's strengths are in the areas of application performance engineering, advanced grid applications support, software integration, packaging and support, distributed operations and procedures, large-scale parallel file systems and data-exchange and analysis tools, I/O and network performance analysis, security, and large-scale compute resources integrated with storage and visualization. Our hardware and software resources are backed by a knowledgeable and experienced staff well versed in working with high-end users. The integration of site-specific production services into the common TG user environment will make it possible for applications teams and user communities to increase their productivity by minimizing the effort required to access multiple or different resources while maximizing the quality and availability of those resources. This will enable current users to expand the scope and range of their scientific research, provide an easy-to-use, highly productive environment for new users and communities, and create a cyberinfrastructure that will be the basis for new scientific programs. NCSA's success within the TG will be measured by the degree to which its TG resources are effectively used to solve important scientific problems such as those being investigated by leading edge researchers.
This proposal outlines NCSA's plan to participate as a resource provider on the TG team. We will provide to the expanding TG user community ongoing access to the growing NCSA-managed TG computational science facility. The TG RP grant will be used almost entirely to fund highly experienced NCSA personnel to support this facility and to serve the needs of TG users in coordination with NCSA's Core NSF support. Appendix A contains common text that links the nine TG RP proposals and the TG GIG proposal.
Through this RP, we will empower research communities to do their science and Engineering research by seamless use of NCSA's TG and Core resources in the context of the larger TG effort. This includes support for distributed computation, data-centric science, on-demand computing, and connection to a broad range of emerging cyberinfrastructure-based capabilities funded from a variety of sources. Working together with scientists, engineers, and other RP sites, NCSA will help enable new research that would otherwise be much more difficult, or simply impossible, to carry out.
NCSA will build, improve, and make available a set of high-end resources in support of the national research community. The results of this effort will lead to a hardware, software, and networking environment that can be extended to other facilities. It will also provide valuable information to others building grids that may include high-end facilities. Finally, NCSA's experienced staff will have a substantial positive impact on the quality of the TG environment and on the ability of users to work effectively in that environment.
