The Texas Advanced Computing Center (TACC) is a research center at the University of Texas at Austin (UT Austin) reporting to the Office of the Vice President for Research. TACC provides advanced computing resources & services to enable computationally-intensive research and conducts research & development to enhance the capabilities of these resources.

Mission

The mission of the Texas Advanced Computing Center is to enhance the research and education programs of the University of Texas at Austin and its partners through research, development, operation, and support of advanced computing technologies.

To accomplish this mission, TACC engages in the following activities:

• evaluates, acquires, and deploys advanced computing resources, including both computing systems and software;
• offers training workshops, seminars, and lectures in academic classes to educate and prepare new users of these resources;
• provides expert consulting and technical documentation to assist researchers in using these resources effectively;
• conducts research and development activities to produce new computational techniques and technologies that enhance the capabilities of advanced computing resources; and
• collaborates with computational researchers to apply advanced computational techniques in their research activities.

---

Resources & Support

TACC deploys and operates advanced computational infrastructure to enable computational research activities of faculty, staff, and students at UT Austin, UT System, and Texas higher education institutions. TACC also provides consulting, technical documentation, and training to support users of these resources. Through the National Science Foundation's TeraGrid (http://teragrid.org), these resources and services are also made available to the national academic research community.

TACC provides comprehensive advanced computing resources, including:

• high performance computing (HPC) systems of a variety of architectures to enable larger simulations analyses and faster computation times than are possible using computers available to individual researchers, academic departments, and research centers and institutes;
• advanced scientific visualization (SciVis) resources including computing systems with high performance graphics hardware, large displays, and immersive environments, and high-end post-production facilities to enable large data analysis and promote knowledge discovery; and
• massive data storage/archival systems to store the vast quantities of data that result from performing simulations on HPC systems and developing visualizations of large data sets.

TACC HPC systems include the following:

• Ranger Sun Constellation Cluster contains 62,976 2.0GHZ AMD Opteron cores within 3,936 quad-core SunBlade x6420 server-nodes, 72 Sun x4500 I/O data servers, 2 Sun x4600 Metadata servers, and 4 Sun x4600 login/management
• Lonestar Dell Linux Cluster contains 5,840 2.66GHz Xeon cores within 1,460 Dell dual-processor (dual-core) PowerEdge 1955 compute blades, 16 Dell PowerEdge 1850 compute-I/O server-nodes and 2 Dell dual-processor (dual-core) PowerEdge 2950 login/management nodes.
• Champion IBM Power5 System contains 96 1.9 GHz Power5 processors and 192 GB of aggregate memory.
• Stampede Dell Linux cluster contains 1744 2.33GHz Intel Xeon cores within 218 Dell quad-core PowerEdge 1950 servers, and 2 PowerEdge 1950 login/management nodes.

TACC operates an immersive visualization laboratory with the following resources:

• terascale remote visualization system, consisting of a Sun E25K with 128 processors, 512 Gigabytes of shared memory, and access to over a Terabyte of storage
• 8-processor SGI Prism with 4 ATI FireGL X3 256MB graphics cards
• cylindrically-symmetric, 3x1 edge-blended front-projection power wall
• large-panel, 5x2 tiled power wall
• video and audio editing systems

TACC also operates a data storage system comprised of a Sun x4600 metadata server running the Sun StorageTek SAM-FS software and supported by a Sun StorageTek SL8500 Modular Library System with a media capacity of over 5 petabytes of user data.

U.S. academic researchers may apply online for computing resource allocations on TACC systems through TeraGrid. UT Austin, UT System, and Texas higher education researchers can apply through TeraGrid or directly through TACC. Applications are reviewed on a quarterly basis, and allocations are made on the basis of scientific merit, suitability of TACC systems for the proposed work, and overall demand for high performance i computing cycles.

---

Research & Development

In addition to providing advanced computing infrastructure and support to enable the research efforts of UT Austin, UT System, Texas higher education and TeraGrid users, TACC staff conduct 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 and of algorithms and codes on these 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 departments 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. TACC research and development activities are supported by several federal programs, 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.

The Texas Advanced Computing Center is organized into six groups, each with distinct areas of responsibility:

Please reference TACC in any research report, journal or publication that requires citation of any author's work. The recognition of the TACC resources you used to perform research is important for acquiring funding for the next generation hardware, support services, and our Research & Development activities in HPC, visualization, data storage, and grid infrastructure. The minimal content of a citation should include:

       Texas Advanced Computing Center (TACC)
       The University of Texas at Austin

Our suggested acknowledgement is:

       The authors acknowledge the Texas Advanced Computing Center
       (TACC) at The University of Texas at Austin for providing
       {HPC, visualization, database, or grid} resources that
       have contributed to the research results reported
       within this paper. URL: http://www.tacc.utexas.edu

Select one or more of the items within the braces, {}.