More than 8.7 million CPU-hours/week awarded to projects that address compelling large-scale problems
LLNL Supercomputer

Grand Challenge Projects Awarded Supercomputing Time

Wednesday, October 30, 2013

Research projects ranging from the predictive assessment of pharmacological cardiotoxicity to understanding dark matter in the universe were among those allocated time on LLNL supercomputers under the recently announced Institutional Unclassified Computing Grand Challenge Awards.

The 8th Annual Computing Grand Challenge program awards more than 8.7 million CPU-hours/week to projects that address compelling large-scale problems, push the envelope of capability computing, and advance science. Now in its eighth year, Grand Challenge allocations have accelerated code development for stockpile stewardship and research in such critical areas as energy efficiency and grid management.

“The Grand Challenge program encourages lab scientists to leverage our high performance computing expertise developed for stockpile stewardship to advance a broad range of science critical to the nation,” said Dona Crawford, associate director for Computation. “Allocating time on some of our most powerful supercomputers is an important investment we make in LLNL’s science and technology.”

Teams with winning proposals were allocated time Oct. 1 on Sierra, a 261-teraFLOP/s machine, and Vulcan, a 5-petaFLOP/s machine. Sierra and Vulcan are systems dedicated to unclassified research through LLNL’s Multiprogrammatic & Institutional Computing program.

Central processing unit or CPU time is measured across the multiple CPUs in a computer. For example, two CPU hours can be one CPU used for two hours or two CPUs used for one hour. High performance computers generally consist of thousands of CPUs; the Sierra system has 1,944 nodes with 12 cores, for a total of 23,328 cores, while Vulcan has 313,216 CPUs.

“We had a good mix of returning and new proposals,” said Fred Streitz, director of the Institute for Scientific Computing Research.”I am excited that so many teams are willing to take on the challenge of advancing science by pushing the state-of-the-art in HPC.”

>Project proposals were reviewed by both internal and external referees. Project selection criteria included quality and potential impact of proposed science and/or engineering, impact of proposed use of Grand Challenge computing resources, ability to effectively use a high performance computing (HPC) system, quality and extent of external collaborations, and alignment with the Laboratory’s strategic vision. Allocations were awarded in two categories, Tiers 1 and 2. Tier 1 projects receive a higher allocation and a higher priority.

Over the last 15 years, HPC resources dedicated to unclassified research have increased more than a 10,000-fold, from 72 gigaFLOPS in 1999 to more than 5 petaFLOPS today. To put that in perspective, only six countries in the world possess more computing resources than LLNL makes available for unclassified computing.