Revised SciDAC Mission

The SciDAC program was initiated in 2001 (original mission) to create the high performance computing software tools needed to advance scientific discovery using terascale supercomputers (computers capable of performing trillions of calculations per second). During the past 20 years, supercomputers have become essential to addressing scientific problems of national interest, including climate change, combustion, fusion energy, new materials and astrophysics. More powerful computers enable scientists to study such problems in greater detail and create simulations with greater accuracy.

However, as supercomputers become ever more powerful, scientific software applications developed over the years may not be well-suited to taking full advantage of these new systems. The SciDAC program was launched to leverage the nation’s intellectual investment in computational science to yield additional scientific discoveries.

Although high-performance computers have enabled researchers to achieve key scientific insights in a number of areas of national importance, many multi-scale, multi-disciplinary problems now facing science programs in DOE require even more advanced modeling and simulation capabilities. Another scientific challenge is the need to capture, store, transmit, share and analyze large-scale experimental and observational data, as well as data from simulations.

Now entering its second cycle (in 2006), SciDAC will address the computational science challenges and opportunities posed by petascale computers capable of performing quadrillions of calculations per second. Such petascale systems are expected to become available in 2010.

Future SciDAC directions include:

• The creation of a comprehensive scientific computing software infrastructure that fully integrates applied mathematics, computer science, and computational science in the physical, biological, and environmental sciences for scientific discovery at the petascale level, and
• A new generation of data management and knowledge discovery tools for the large data sets obtained from large experimental facilities and from high end simulations.

Future SciDAC applications are expected to:

• Address obtaining significant insight into, or actually solve through computational science, a challenging scientific or engineering problem of national significance that is clearly related to DOE missions;
• Create scientific simulation codes that: achieve high single node performance, scale to thousands of nodes and tens-of-thousands of processors, and can be readily ported to other computer architectures;
• Develop applied mathematics and computer science methodology focused on computational science at the petascale, and work with application teams to apply innovations;
• Integrate computational science with discipline-driven applications through teaming and partnerships with computer scientists and applied mathematicians;
• Engage experimental and observational data-intensive science; and/or
• Empower new scientific communities to achieve scientific discovery through computational science.

Although SciDAC is a partnership involving all SC program offices — Advanced Scientific Computing Research, Basic Energy Sciences, Biological and Environmental Research, Fusion Energy Sciences, High-Energy Physics and Nuclear Physics — the program is also built around collaborative teams of experts from national laboratories, universities and other research organizations. This approach not only taps into the broadest range of expertise, but also ensures that the resulting tools and methods will be available to the wider research community.