The first 2 petaFLOPS system NVIDIA DGX-2 AI supercomputers arrive in the U.S. at the nation’s leading research labs to boost up important scientific discoveries.
The new level NVIDIA DGX-2 is the first 2 petaFLOPS system that combines 16 fully interconnected GPUs for 10X the deep learning performance. The new system will make its debut in numerous labs like; Brookhaven National Laboratory, in Upton, New York; Oak Ridge National Laboratory, in Oak Ridge, Tennessee; Pacific Northwest Laboratory, in Richland, Washington; and Sandia National Laboratories, in Albuquerque, New Mexico.
The labs are specifically engaged in work ranging from fusion research and climate simulation to human genomics. It is designed in an ultra way to handle the most compute-intensive applications; DGX-2 systems offer performance breakthroughs in the most demanding areas of scientific computing, AI and machine learning.
Brookhaven National Laboratory is using the DGX-2 to appraise several deep learning algorithms for advanced image analysis. The team is planning to test how well their machine learning-based streaming, real-time analysis workflows will perform on the system, particularly with high data throughput and multiple users.
We want to take HPC workloads that are not machine learning-centric. – Nicholas D’Imperio, Computational Science Laboratory chair
For him, this will provide a better picture of performance gained overall that may improve legacy codes and HPC workflows to operate on such GPU-dense systems.
Oak Ridge National Laboratory debuts the system in experimental facilities and instrumentation produce as well as using it in scientific datasets. The system will also provide an onramp to summit the world’s most powerful supercomputer by enabling smaller and more experimental projects to be developed.
The Pacific Northwest National Laboratory intends to model atmospheric phenomena, such as hurricane intensity, using 4-dimensional temperature and pressure profiles across thousands of square kilometers. The new system enables scientists to study systems that were much larger and more complex than was possible before hence catalyzing new discoveries and deep learning approaches to advance the state of the art.
Lastly, the Sandia National Laboratories acquires the DGX-2 systems to be the backbone infrastructure for the newly developed Machine Learning as a Service. Their main aim is to allow engineers and scientists unfamiliar with machine learning to take advantage of the capability to rapidly solve difficult problems.
