Visit additional Tabor Communication Publications
October 27, 2006
With 54 teraflops of computing power, Oak Ridge National Laboratory's Cray XT3 is helping solve scientific grand challenges, but scheduling the many research projects and keeping the massive machine operating at peak capacity are challenges of their own.
The Cray, known as Jaguar, requires a complex infrastructure that can cool more than 5,000 dual-core processors; ensure reliable power; maintain optimum operation; and accommodate future expansion.
The facilities at ORNL are among the few in the world that meet these and other demanding criteria required for computer simulations at this scale in chemistry, combustion, astrophysics, biology, fusion, climate and physics.
Big science and the accompanying big applications that make the best use of the machine receive priority. In fact, ORNL frequently has a single project that uses all of the processors for up to 24 hours. The constant goal is to make the most of the computing resource.
"We have people and programs to ensure that we're utilizing the computer as efficiently as possible," said Doug Kothe, director of science for the National Center for Computational Sciences. "That's part of our duty and responsibility to the taxpayers who support this leadership-class open resource."
Built in to the design of Jaguar is the ability to detect and compensate for failures likely to occur in such a complex system. ORNL and Cray have people dedicated full time to keeping the machine operating.
Allocations of computing time (processor hours) for research projects are made under the U.S. Department of Energy's Innovative and Novel Computational Theory and Experiment program. Coordinated by DOE's Office of Science, INCITE is open to all scientific researchers and research organizations, including industry. The program is intended for computationally intensive research projects of large scale that can make high-impact scientific advances through the use of a large allocation of computer time, resources and data storage. Proposals are for projects that run for one to three years.
In the first phase of the INCITE awards process, proposals undergo a technical readiness review.
"We look at how the applications will utilize the capabilities of the Leadership Computing Facility supercomputing resources and make recommendations based on the scalability and performance of those applications," said Ricky Kendall, group leader for the Scientific Computing Group at the Center for Computational Sciences. The technical readiness review team consists of scientists with diverse backgrounds and expertise in computational science.
In the second phase, DOE convenes a panel that reviews all aspects of the proposals for general scientific merit and comparisons are made across scientific disciplines. Proposals for 2007 awards were due in September. The panel will make recommendations to DOE, which will announce the awards in December.
Last year's call for INCITE proposals resulted in 43 submissions requesting more than 95 million processor hours. The proposals covered 11 scientific disciplines: accelerator physics, astrophysics, chemical sciences, climate research, computer science, engineering physics, environmental science, fusion energy, life sciences, materials sciences and nuclear physics.
A total of 18.2 million processor hours were awarded for 2006 INCITE and Leadership Computing Facility projects. Eighty percent of the Cray leadership-class computers -- Jaguar and Phoenix -- at ORNL are available to INCITE. Counting allocation awards from previous years, some 30 million processor hours are being run this year on ORNL's Jaguar and another nearly 6 million are being run on ORNL's Phoenix, a Cray X1E with 18.5 teraflops. The remaining allocations of computing time for this year were made for computers at Lawrence Berkeley, Argonne and Pacific Northwest national laboratories.
The largest Leadership Computing Facility project allocation at ORNL involves multidimensional simulations of core-collapse supernovae and consumes 3.55 million processor hours on Jaguar. The goal is to understand how stars more massive than 10 of our suns explode to produce many of the elements in the universe, like oxygen and iron, necessary for life. The lead researcher is Tony Mezzacappa of ORNL's Physics Division.
Next in line for processor hours with 3.5 million hours on Jaguar and 300,000 hours on Phoenix is a nano- and materials sciences project headed by Thomas Schulthess of the Computer Science and Mathematics Division and the Center for Nanophase Materials Sciences. The project is aimed at a better understanding of complex functional nanostructures, which could lead to more much faster and more energy efficient electronic devices, and better materials for energy storage, transmission and production.
A turbulent combustion project headed by Sandia's Jacqueline Chen is allocated 3 million Jaguar hours and 600,000 processor hours on Phoenix, and Don Batchelor of ORNL's Fusion Energy Division leads a wave-plasma simulation project also awarded 3 million processor hours on Jaguar. Batchelor's work could ultimately help solve one of the obstacles to making fusion a reality. Other users include Dreamworks Animation, The Boeing Company, General Atomics, Harvard University, Auburn University and the University of Washington/Howard Hughes Medical Institute.
The Jaguar is scheduled to be upgraded to 100 teraflops (100 trillion mathematical calculations per second) by the end of this year. ORNL is managed by UT-Battelle for the Department of Energy. More information about INCITE is available at http://hpc.science.doe.gov/allocations/incite/.
Source: Oak Ridge National Laboratory
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
Jun 13, 2013 |
Titan, the Cray XK7 at the Oak Ridge National Lab that debuted last fall as the fastest supercomputer in the world with 17.59 petaflops of sustained computing power, will rely on its previous LINPACK test for the upcoming edition of the Top 500 list.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
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?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.