UT Wordmark Primary UT Wordmark Formal Shield Texas UT News Camera Chevron Close Search Copy Link Download File Hamburger Menu Time Stamp Open in browser Load More Pull quote Cloudy and windy Cloudy Partly Cloudy Rain and snow Rain Showers Snow Sunny Thunderstorms Wind and Rain Windy Facebook Instagram LinkedIn Twitter email alert map calendar bullhorn

UT News

TACC Provides Multi-Petabyte Data Repository to Enable Research at University of Texas System Institutions

The much-anticipated University of Texas Data Repository (UTDR) named “Corral” is available to researchers at all 15 University of Texas System institutions, the Texas Advanced Computing Center (TACC) at The University of Texas at Austin announced today.

Two color orange horizontal divider

The much-anticipated University of Texas Data Repository (UTDR) named “Corral” is available to researchers at all 15 University of Texas System institutions, the Texas Advanced Computing Center (TACC) at The University of Texas at Austin announced today.

The data repository is part of the overall University of Texas Research Cyberinfrastructure (UTRC) project, a $23 million initiative announced in December 2010 to enable world-class research and foster stronger collaborations among researchers in Texas and around the world. The UTRC project ensures that researchers across Texas can effectively use advanced computing capabilities, including high-performance computing for simulation and analysis, high-capacity storage for large digital data collections, and high-bandwidth networking connecting institutions and resources.

As one of the largest online storage systems available to academic researchers in the United States, Corral provides six petabytes of data, which is equal to 50 times the size of the entire collection of DVDs at Netflix. University of Texas System researchers whose data needs outstrip their local capacity are invited to apply for allocations on Corral using the Allocations Request System available through the TACC User Portal.

In recent years there has been an explosion of “big data” in science and engineering research. Big data is a term applied to data sets whose size is beyond the ability of commonly used software tools and commodity computers to manage. Such data sets range from a few dozen terabytes to many petabytes of data in a single data set. This data comes from many sources such as gene sequencers, imaging systems, real-time sensors that monitor the environment, and from computational simulations.

“Through the UTRC and UTDR effort, the UT System is bringing data infrastructure to researchers to match the massive computational infrastructure available through TACC,” said Patricia Hurn, the system’s associate vice chancellor for health science research.

In January TACC announced that the data repository, which will be composed of two identical installations one in Austin and one in Arlington would enter an early-user phase to encourage feedback and explore additional capabilities that researchers might need such as data security, interfaces and capacity.

“Our work with early users from multiple academic and health campuses within the UT System has helped us to select tools for transferring and managing data in the system, and has shown the system to be stable and ready for wider use,” said Chris Jordan, leader of the Data Management and Collections group at TACC and chair of the storage committee for the UTRC initiative. “As a result, we are now making the data repository open to all eligible UT System researchers.”

The storage is directly accessible from TACC’s Lonestar 4 supercomputer, which was expanded last year as part of the UTRC initiative. In addition, all University of Texas institutions will eventually be connected at 10 gigabits per second to enable faster transfer of data to and from the data repository.

So far, the UTDR project has imported more than 200 terabytes of data to Corral, mostly next-generation sequencing and functional MRI data. The rate of data growth in UTDR is expected to grow as the network connectivity is ramped up across all 15 institutions.

“Corral has been essential for us as we scale-up output from our next-generation DNA sequencing center,” said Scott Hunicke-Smith, director of diagnostics and genome sequencing at the Texas Institute for Drug and Diagnostic Development.

“The TACC installation has been so robust and well supported that we can use Corral to re-distribute data out to dozens of collaborator labs via many different interfaces. We also love Corral’s ability to assign arbitrary metadata to these large and valuable data files for searching, verification or provenance management,” he said.

Researchers who need five terabytes of data storage or less will have free access during the first year, and researchers requiring more can purchase storage for $250 a terabyte per year. Some storage will also be set aside to support strategic, collaborative projects that enhance the leadership position of University of Texas System institutions.

Researchers may request allocations on Corral via an online web page through the TACC User Portal. Training sessions on data management topics including the use of Corral will be provided on an ongoing basis. Please refer to the “Events and Training” section of TACC’s website.