Cooperations & Memberships

Two years after the Gauss-Centre has been created to coordinate the European supercomputing activities, Germany took the next step to shape the future of high performance computing (HPC) on a national level. On December 3, 2008 the nations leading supercomputing centers met in Bonn to create the Gauß-Allianz. While the Gauss-Centre was successfully addressing the needs on the top end, it was clear from the beginning that an additional layer of support was required to maintain the longevity with a network of competence centers across whole Germany. This gap is now addressed by the Gauß-Allianz, where regional and topical centers team up to create the necessary infrastructure. Further information can be found on the website. 

The Jülich Aachen Research Alliance (JARA), a cooperation between RWTH Aachen University and Forschungszentrum Jülich, provides a top-level research environment that is in the top international league and is attractive to the brightest researchers worldwide.

The JARA Center for Simulation and Data Science (JARA CSD) provides a platform for scientific exchange that brings together researchers from mathematics and computer science to engineering and the natural sciences. The overarching scientific challenge is to combine data-driven and physics-based computational approaches into explainable and reliable solutions for analysis and prediction. JARA CSD advances research software engineering and provides a corresponding forum for the exchange of knowledge and research-oriented training across all career levels. JARA CSD thus acts as an incubator for interinstitutional and interdisciplinary collaborations and projects, fosters scientific excellence and provides a hub for innovation. The center provides and utilizes high-performance computational infrastructure, including next-generation computing. Further information can be found on the website. 

The MPI Forum is the standards committee that develops the Message Passing Interface (MPI). Message passing is a proven method for programming distributed memory computer systems, and MPI is the de facto standard for message passing in high-performance computing (HPC). In addition to interfaces for communication and parallel IO, MPI also provides an interface for application development tools (performance and correctness analysis) that help application developers to develop correct and efficient HPC applications.

The HPC group develops such tools itself and is actively involved in the further development of this interface in the MPI Forum working group for "Tool Interfaces". The synergies from this work directly benefit the applications and developers.

Pooling resources and competencies of university-based high-performance computing and advancing research: this is what the NHR Alliance stands for. The Alliance coordinates the supraregional, sustainable and resource-efficient use of computing capacity and expertise. The big plus for national researchers: They can access resources nationwide and as needed, regardless of their location! The collaboration promotes knowledge exchange and interdisciplinary cooperation.

The IT Center is one of nine high-performance computing centers that are members of the association, which was founded in 2021. Together with TU Darmstadt, RWTH forms the National High Performance Computing Center for Computational Engineering Science (NHR4CES). Within the framework of NHR4CES, RWTH offers scientists from German universities resources on its high-performance computers free of charge. Equally important components of the NHR concept are the services offered by the centers: Strengthening the methodological competence of scientists from a wide range of application areas, providing training and continuing education in high-performance computing, expanding new competencies, and thus ensuring the long-term performance of scientific computing in Germany.

Since 1998 the High Performance Comuting Team of the Center for Computing and Communication of the RWTH Aachen University is engaged in the topic of Shared-Memory-Parallelisierung with OpenMP. OpenMP is productively used on the currently largest Shared- Memory Computers of the Center for Computing and Communication with up to 1024 processor cores. OpenMP meanwhile supports also heterogeneous computers as well as vectorization. 
Details can be found on the OpenMP website.

Since 2013, the IT Center of RWTH Aachen University is part of SPEC and actively engaged in its High Performance Group (HPG). SPEC’s HPG is a forum for discussing and developing benchmark methodologies for High Performance Computing (HPC) systems. At the same time, the group releases production quality benchmark suites like SPEC MPI2007, SPEC OMP2012, and SPEC ACCEL, that can evaluate all dimensions of parallelism. These benchmark suites are used in academia and industry to conduct research in HPC systems, facilitate procurement, testing, and tuning of HPC systems. Further information can be found on the SPEC website.