Penguin Tundra server sled
Today the National Nuclear Security Administration (NNSA) announced a contract with Penguin Computing for a set of large-scale Open Compute HPC clusters. With 7-to-9 Petaflops of aggregate peak performance, the systems will be installed as part of NNSA’s tri-laboratory Commodity Technology Systems program. Scheduled for installation starting next year, the systems will bolster computing for national security at Los Alamos, Sandia and Lawrence Livermore national laboratories.
The National Nuclear Security Administration (NNSA) just announced that one of the largest ever open compute-based high performance computing cluster installations, 7-to-9 petaflops peak performance, was awarded to Penguin Computing under NNSA’s tri-laboratory Commodity Technology Systems program. The systems will bolster computing for national security at Los Alamos, Sandia and Lawrence Livermore national laboratories.
NNSA’s selection of an open compute-based installation for such an important national security role gives tremendous credibility to open computing in HPC. It’s further validation of what Facebook started in 2011 with its Open Compute Project, which continues to build momentum with a multitude of vendors and with customers in the private and public sectors. This open source effort for hardware mirrors the benefits that have been realized over the years in open source software.
In this video from SC14, Phil Pokorny from Penguin Computing describes the company’s innovative new Tundra OpenHPC hardware based on the Open Computing Project standard.
