``Computational Grids - The New Paradigm for Computational Science and Engineering''
Prof. Jack Dongarra and Dr. Terry Moore
University Of Tennessee
Department of Computer Science
Innovative Computing Laboratory
Knoxville, TN 37996-4030
E-mail: terry-moore@utk.edu
URL: http://www.cs.utk.edu/~moore

There is the evidence on a number of different fronts that we are entering a new stage in the evolution computational science and engineering. Fueled by constant advances in computing and networking technologies, the research community has begun to develop and implement a new vision for science and engineering that aims to accelerate progress by focusing on computer generated models and simulations of unprecedented scope and power. Well funded prototypes for this new, simulation-intensive approach are already under development in NASA, NSF's Partnerships for Advanced Computational Infrastructure (PACI) program and DOE's ASCI program. What these initial efforts reveal is that this new way of structuring the work of the science and engineering community requires a corresponding change of paradigm in the use of computational resources. The terms ``information power grid,'' ``computational power grid,'' or just ``computational grid'' have gained currency as interchangeable names for this new paradigm.

The concept of a computational grid is intended to capture the idea of using high-performance network technology to connect hardware, software, instruments, databases, and people into a seamless web that supports a new generation of computationally rich problem-solving environments for scientists and engineers. The underlying metaphor of a ``grid'' refers to distribution networks that developed at the beginning of the twentieth century to deliver electric power to a widely dispersed population. Just as electric power grids were built to dependably provide ubiquitous access to electric power at consistent levels, so computational grids are being built to provide access to computational resources that is equally reliable, ubiquitous, and consistent.

The most important aspect of computational grids, however, is their ability to provide on-demand concentrations of the massive computational and information resources required for simulation-intensive research. The general problem is that this escalated use of computer generated modeling and simulation requires a tremendous amount of resources of all kinds. The scientific problems under investigation are computationally intensive, data intensive, and can require real-time interactions of various kinds as well. To solve such problems, tremendous computational power has to be combined in a timely way with highly skilled research teams, instruments, simulators, and large databases. But for a variety of powerful economic and practical reasons, these elements are almost always dispersed geographically, so that the only feasible way to bring them together in the required way is through innovative applications that build on high-performance networking. In other words, this approach to science requires the formation of computational grids.

We believe that the ongoing development computational grids will play a central role in the work of scientific and engineering community over the next decade, and therefore, that the emergence of computational grids will have a dramatic impact on key issues for the DICPM workshop. The impact of the grid and of grid-based, simulation-intensive research on the world of scientific database management relates primarily to two key factors: 1) the much more fluid and dynamic characteristics of information locality allowed by grid-based computation and 2) the higher level of compositionality required in software systems that can take advantage of the power and flexibility that computational grids will permit. Among more specific issues are the following: