Since 2021 GWDG and the University of Göttingen form one of eight Centers for National High Performance Computing (NHR Centers) nationwide. For GWDG and the University of Göttingen this represents a continuation of the HLRN project, in which additional funding is now available for computing resources, research, teaching and user consulting. The special focus is on expanding competencies in the areas of life sciences, earth system sciences, fluid mechanics, AI and Big Data, and digital humanities. Here, GWDG forms the NHR-North together with the ZIB and their joint expert consulting network.
Currently, GWDG operates the NHR system Emmy (HLRN-IV), for the northern German states of the HLRN. Since October 2020, the second phase has been in operation, which made it necessary to move to a modular data center. The HPC team is heavily involved in its planning and operation. Details of the HLRN-IV system can be found on the HLRN web pages.
Emmy is used in particular by scientists at universities and institutions in the participating federal states, but are also available to researchers outside the federal states network. Depending on the institutes affiliation, different user fees apply.
As part of the national high performance computing strategy, every center has defined research and application fields in which it is specialised. For Göttingen, these areas are
The GWDG can resort to many experiences with and from the different existing user communities. In addition, the manifold services by the GWDG as IT service provider and the HPC department in particular, complete the NHR-portfolio.
The supercomputer Emmy has been procured in 2018 as the HLRN-IV system together with our partners at ZIB, who operate Lise. It is operated for the northern German federal states Berlin, Brandenburg, Bremen, Hamburg, Mecklenburg-Western Pomerania, Lower Saxony and Schleswig-Holstein. The users are supported by the HLRN-consultants network.
Emmy has 1423 compute nodes, offering a total compute power of 5,95 PetaFLOP/s with several high memory GPU nodes for pre- and postprocessing. This system is ideal for large-scale (GPU-) applications and advanced users who can take full advantage of the system.
If you are running an application on a local system and would like to migrate to the NHR-system, please don’t hesitate to contact us.