Main Content

High Performance Computing

With the commissioning of MaRC3a, a powerful compute cluster is available for research and science. The cluster is continuously adapted to the requirements of modern high-performance computing (HPC).

Not only to meet current requirements, but also to provide the best possible support for top-level research in the field of BigData and artificial intelligence, the approximately 10-year-old HPC cluster MaRC2 is expected to be replaced by MaRC3a in December 2021 and later supplemented by further expansion stages. Preparations for MaRC3b (MaRCQuant) focusing on quantum physical computation and MaRC3c focusing on medical-psychological computation are already underway. MaRC3a is currently (Sept. 2021) in test operation, for details see Worth knowing.

The HPC cluster MaRC3a is complemented by the high-availability Marburg Storage Cluster (MaSC), which enables the efficient handling of large amounts of data. With MaRC3 and MaSC, Philipps University is pursuing a consolidation approach for high-performance computing and compute-related storage. On the one hand, an overarching interface is implemented for the use of all systems; on the other hand, individual workgroups have the option of contributing their own nodes or GPUs.

In principle, the two clusters MaRC3a and MaSC are available to all scientists and researchers of the Philipps-Universiy for smaller projects; extended resources can be provided via optional participations. If you have a need for computing services, please contact our HPC team, see Support and help.

Target group

Scientists and researchers of the university

Requirement

  • Central User Account (Uni-Account)
  • Declaration of Use, signed by the head of the working group (to be sent on request)

Instructions

  • Inhalt ausklappen Inhalt einklappen Support and helpSupport and help

    You can reach the HPC team at . Please indicate your account and a meaningful subject when making inquiries.

  • Inhalt ausklappen Inhalt einklappen Worth knowingWorth knowing

    MaRC3a is located in the "Zentrum für Synthetische Mikrobiologie" (ZSM2). The cluster was realized in cooperation with different research groups of the Philipps University and is operated by the HRZ. Currently, MaRC3a consists of 26 compute nodes, which together provide 1.664 processor cores and have 256 to 1.024 GB of RAM. In addition, 28 GPU accelerators (NVIDIA V100S and A100) are available for massively parallel applications such as artificial intelligence, image processing, and physical simulations. For data storage, MaRC3a has a 266 TB parallel file system and also has direct access to the MaSC storage cluster.

    The HPC cluster MaRC2, which has been in use for 10 years, still has a peak compute performance of about 44 TFLOPs after a series of hardware failures. With its replacement by MaRC3a, the combined peak performance of CPUs (approx. 53 TFLOPs) and GPUs (approx. 250 to 6.500 TFLOPs depending on the required computational precision) will be available.

-