As part of its ongoing Computational Science Initiative (CSI) targeting data-intensive science and AI workloads, Brookhaven National Laboratory added a Nvidia DGX-2 supercomputer last month. The move is perhaps not surprising given the gush of data Brookhaven deals with.

“We have the second largest scientific data archive in the U.S. and the fourth largest in the world,” Adolfy Hoisie, director of CSI’s Computational National Security department, told HPCwire last February. “On an annual basis, data to the tune of 35 petabytes are being ingested, 37 petabytes are being exported, and 400 petabytes of data analyzed.”

The new system, stood up in October and nicknamed Minerva, is briefly profiled in an article posted today on the BNL website. According to Hoisie, quoted in the article, the new system delivers 2-petaflops of performance [that’s half-precision], made possible by a scalable architecture built on the Nvidia’s NVSwitch AI network fabric.

“We will expose the Nvidia DGX-2 to data-intensive workloads for many programs, such as those of import to DOE science programs at the Lab’s Office of Science User Facilities –  including the Relativistic Heavy Ion Collider, National Synchrotron Light Source II, and Center for Functional Nanomaterials – and to Department of Defense (DoD) data-intensive workloads of interest,” Hoisie said.

“Given significant bandwidth in and out of the system, we can pursue data analyses in multiple paradigms, for example, streaming data or fast access to vast amounts of data from Brookhaven Lab’s massive scientific databases. Such improvements will afford tremendous strides in data analyses within the Lab’s core high energy physics, nuclear physics, biological, atmospheric, and energy systems science areas and cryogenic technologies, as well as for specific research areas in computing sciences of interest to DOE and DoD,” he noted.

Because the Nvidia DGX-2 specifically was designed to tackle the largest data sets and most computationally intensive and complex models, says BNL, it will also play an important role in the lab’s machine learning efforts. One such beneficiary will be the ExaLearn collaboration, an Exascale Computing Project co-design center featuring eight DOE national laboratories and led by CSI’s Deputy Director, Francis J. Alexander. The ExaLearn team primarily is developing machine learning software for exascale applications.

Noteworthy, Minerva also will be a resource for Nvidia as part of a collaboration. As research involving the system advances, its capability in impacting applications, speed to solutions, or even markers of its own overall performance will be shared between Brookhaven Lab and Nvidia developers.

Link to full article: https://www.bnl.gov/newsroom/news.php?a=113206