November 01, 2013
Nov. 1 -- UT has received funding from computer chip maker Intel to develop computer codes to make personalized medicine and other transformative scientific discoveries possible.
The funding will open an Intel Parallel Computing Center at the Joint Institute for Computational Sciences (JICS) at UT and Oak Ridge National Laboratory. Parallel computing, used in supercomputers, is a form of computation in which many calculations are carried out simultaneously. The focus of the center will be to take supercomputing to the next level to meet scientific computing demands. Today’s research faces limitations due to the amount of data, time, and energy it takes to run calculations.
The center will initially focus on two projects in computational biology that may lead to medical advances.
“We are making great scientific advances, but our computing machines are not keeping pace with the enormous data growth,” said Tony Mezzacappa, JICS director and project lead. “We are grateful to Intel for supporting this center which allows us to develop codes that can catalyze scientific advances and fuel the future of personalized medicine and biotechnology.”
The first project will enable a team led by Jeremy Smith, UT-ORNL Governor’s Chair for Molecular Biophysics, to optimize a molecular dynamics code called GROMACS to operate on next-generation Intel machines. GROMACS is primarily used to study the interactions of biochemical molecules, enabling drug discovery, and metabolic research.
“The GROMACS package has been employed in more than ten-thousand published scientific applications since 2000. Optimizing this code for next-generation Intel machines is an important step in making these simulations run more efficiently and faster,” said Smith. “This allows these simulations to be more accurate and detailed, helping us understand the living world around us better.”
The second project will enable a team led by Glenn Brook, JICS chief technology officer and co-project lead, and Bhanu Rekepalli, computational scientist, to optimize a gene sequence analysis code called BLAST to operate efficiently on future computing platforms. BLAST is key to genomics and the future of biotechnology and personalized medicine.
“There is an overwhelming amount of data, particularly in genomics, and we have only been able to scratch the surface,” said Brook. “Optimizing critical codes like BLAST for next-generation Intel machines will allow us to interpret the data faster and more effectively.”
“The machines will also change the way we do science,” said Mezzacappa. “For example, instead of performing years of clinical trials, we can do computations that narrow the focus to get drugs to the market faster and at less cost.”
The center continues a legacy of supercomputing excellence in East Tennessee, home to JICS and the world’s fastest supercomputers.
“The University of Tennessee and its partner, Oak Ridge National Laboratory, are the epicenter of supercomputing,” said Chancellor Jimmy G. Cheek. “Researchers worldwide tap into our unparalleled resources, and partnerships like this one allow them to push to the forefront of discovery.”
The Intel Parallel Computing Center began operations earlier this month. Collaborators include Roland Schulz, John Eblen, Travis Thompson, and Shane Sawyer. Other projects also are being developed.
There are four other Intel Parallel Computing Centers located at Purdue University, Texas Advanced Computing Center at the University of Texas in Austin, Zuse Institut Berlin in Germany, and CINECA, a nonprofit consortium of Italian universities and institutions.
JICS manages the National Institute for Computational Sciences for the National Science Foundation, operating supercomputers that rank among the most powerful systems in the world.
For more information, visit the JICS website.
Source: University of Tennessee
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?