330 Pflops to fight coronavirus: IBM and DoE create an HPC consortium

IBM announced on Sunday that it is partnering up with the US Department of Energy (DoE) to build a COVID-19 High-Performance Computing (HPC) Consortium that will use high-performance computing to control the coronavirus infection.

The consortium will bring together the computing capabilities of some of the world’s most powerful and advanced computers to help scientists around the globe to research and develop treatment methods and prospective drugs.

Overall, 16 supercomputer systems based on 775,000 processor cores and 34,000 GPUs with a combined capacity of over 330 Petaflops will be involved to meet the needs of research. These high-performance computing systems will allow researchers to carry out a significant number of calculations in the field of epidemiology, bioinformatics and molecular modeling in hours or days instead of months or even years.

Two critical uses of the consortium’s computing power may include the development of prognostic models assessing the disease progress and the modeling of new potential treatments and vaccines.

Besides IBM, the consortium includes Amazon Web Services, Google Cloud, Microsoft, Massachusetts Institute of Technology (MIT), Rensselaer Polytechnic Institute (RPI), Lawrence Livermore National Laboratory (LLNL), Argonne National Laboratory (ANL), Oak Ridge National Laboratory (ORNL), Sandia National Laboratories (SNL), Los Alamos National Laboratory (LANL), National Science Foundation (NSF) and NASA.

Alongside its consortium partners, IBM will coordinate the efforts to evaluate proposals from the leading institutions and provide access to HPC facilities for the most relevant projects.

Other news:

The most powerful supercomputer in the world is fighting against coronavirus.

Frontera - World’s most powerful academic supercomputer - launched in the US.

Dell builds the largest industrial supercomputer for Eni.

IBM’s Power9 systems are leading the supercomputers’ race.