In addition to providing advanced computing infrastructure and support to enable the research efforts of UT Austin, the UT System, and TeraGrid users, TACC’s staff conducts research and development activities to develop new computing techniques and technologies.
TACC's current research and development activities and areas of interest include:
- Evaluating and modeling the performance characteristics of HPC systems;
- Evaluating the performance of algorithms and applications on HPC systems;
- Exploring the impact of large displays and immersive techniques on data analysis and knowledge discovery;
- Developing new visualization tools for collaborative and remote visualization;
- Building reliable, high-performance commodity clusters for HPC simulations and scientific visualization; and
- Developing computational grid software to seamlessly integrate TACC HPC, scientific visualization, and data storage systems and to link these systems with systems in other UT Austin departments and centers, at other Texas universities, and at other TeraGrid partner institutions.
TACC scientists collaborate with many other researchers in these activities. TACC collaborators include researchers in other UT Austin and UT System departments, institutes and centers, at other Texas universities in the High Performance Computing Across Texas Consortium (HiPCAT), at other TeraGrid institutions, and at other U.S. universities and government laboratories.
Several federal programs support TACC research and development activities, including:
- The National Science Foundation TeraGrid program;
- The NSF Information Technology Research (ITR) program;
- The NSF National Middleware Initiative (NMI) Testbed program;
- The Department of Defense (DoD) High Performance Computing Modernization Office (HPCMO) Programming Environment & Training (PET) program;
- The Department of Energy (DoE) Scientific Discovery through Advanced Computing (SciDAC) program; and
- The National Aeronautics and Space Administration (NASA) Information Power Grid (IPG) program.
