CFP: http://www.nsf.gov/publications/pub_summ.jsp?ods_key=nsf08571
Deadline for preliminary proposals: 11/4/2008 (only for Integrating Services category)
Deadline for full proposals: 11/14/2008 for HPC Remote Visualization and Data Analysis, 6/15/2009 for Integrating Services
Award amounts: 3-6 projects from $32,000,000 total
–
Over the past three years, the TeraGrid has revolutionized the way in which members of the academic science and engineering community use leading-edge digital resources in their research. As a recent external assessment of the TeraGrid noted, “The TeraGrid is among the best grids in the world with respect to providing resources to a broad and inclusive audience. The TeraGrid is: enabling leading edge science and engineering, providing access to world class heterogeneous resources for a large and diverse community of researchers and educators, [and] leading in innovative approaches to exploiting cyber-infrastructure.”
By pioneering the implementation of techniques to virtualize access to heterogeneous, geographically dispersed high-end computing, data management, and visualization resources, the TeraGrid enables researchers to move beyond working in batch mode on a single supercomputer by giving them the opportunity to select the right advanced digital resource for each research project they are working on and for each stage of each project.
Combining a considerable depth of user support and advanced consulting with a range of access modes that includes interactive, batch mode, by advance reservation, dedicated access, and web-based access, the TeraGrid has made advanced digital resources more usable by researchers and educators. Through a program of online and in-person training, education and outreach opportunities, the TeraGrid has lowered the barriers to the use of high-end digital resources. One result is that the TeraGrid has become vital infrastructure for many researchers across a broad array of research areas.
The scientific impacts of the TeraGrid resources have been felt in astronomy, astrophysics, atmospheric science, biochemistry, chemistry, civil engineering, computer science, condensed matter physics, earth science, materials research, mechanical engineering, nanotechnology, ocean science, particle physics, plasma physics, relativity, and the social, behavioral and economic sciences. In the twelve months ending March, 2007, over one quarter of a billion dollars worth of funded research was supported by the TeraGrid’s infrastructure.
The evolution of the TeraGrid has so far included a “construction phase,” (Phase I) embodied in the Distributed Terascale Facility and TeraGrid Extensions Program, and an initial operational phase (Phase II), formally referred to as the Extensible Terascale Facility. The TeraGrid is a collaborative activity in which a number of individual resource providers provide advanced digital resources and services within an integrating framework. Individual institutions may phase in and out as resource partners on time scales of a few years but the ensemble of services has a longer lifetime and provides a reliable infrastructure for research and education. Organizations preparing proposals may find more information about the current TeraGrid at www.teragrid.org or by contacting the Cognizant Program Officers.
Modern research and education are eagerly exploiting advances in observing and computational technologies, coupled with increasing expertise in the theory of complex systems. These advances drive researchers to work with increasingly large data sets, streaming data from observing systems, more complex multi-process and multi-scale simulations, more advanced forms of visualization, and to synchronize observation with analysis and modeling in multi-stage scientific workflows. These trends produce a greater demand for digital services at extreme scale, beyond those typically available within an individual university, and pose new challenges in how best to deliver such services.
The goal of this solicitation is to encourage innovation in the design and implementation of an effective, efficient, increasingly virtualized approach to the provision of high-end digital services – extreme digital services – while ensuring that the infrastructure continues to deliver high-quality access for the many researchers and educators that use it in their work. The integration of extreme-scale digital resources and services into a common framework that makes it easy for researchers to take advantage of multiple resources and services remains a challenge. Especially challenging is the desire of many researchers to be able to move between using local resources and national resources within a single, well integrated environment. New ideas and technologies have emerged that make it timely to revisit the architecture of the TeraGrid and to plan to address these challenges in the coming years. In preparation for the next operational phase of the TeraGrid (Phase III), to begin in 2010, NSF is encouraging proposals from any interested group capable of contributing to the design and execution of (a) the architecture and key integrating services that provide the common framework within which extreme digital services can be provided to researchers and educators, or (b) the provision of an advanced visualization and data analysis service within such a framework. Collaborative proposals are welcome.
The primary goal of the next phase of the TeraGrid is to enable major advances in science and engineering research, in the integration of research and education, and in broadening participation in science and engineering by under-represented groups, by providing researchers and educators with usable access to extreme-scale digital resources, beyond those typically available on a typical campus, together with the interfaces, consulting support and training necessary to facilitate their use. For this reason, we refer to the next phase of the TeraGrid as “eXtreme Digital”, “XD.”
