Systems & Documentation

The CBRZ contains the supercomputer HSUper, the interactive scientific computing cloud (ISCC) and the two-node Cerebras System CS-3. Below is some introductory information for users regarding the CBRZ systems and available testbeds.

Acknowledgement

The HPC cluster HSUper and the cloud solution ISCC have been provided by the project hpc.bw, funded by dtec.bw — Digitalization and Technology Research Center of the Bundeswehr. dtec.bw is funded by the European Union – NextGenerationEU.

See below for a suggestion of an acknowledgement statement for publications:

dtec.bw is funded by the European Union – NextGenerationEU.

Computational resources (HPC cluster HSUper) have been provided by the project hpc.bw, funded by dtec.bw – Digitalization and
Technology Research Center of the Bundeswehr. dtec.bw is funded by the European Union – NextGenerationEU.

HSUper

HSUper is a supercomputer consisting of more than 580 nodes divided in various partitions with the largest currently consisting of 569 nodes. Jobs can be submitted using the installed slurm workload manager. The following links lead to the HSUper documentation on the HPC Portal.

Technical Specifications

The HSUper cluster consists of

  • Regular nodes: 571 compute nodes each equipped with 256 GB RAM and 2 Intel Icelake sockets; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with (up to) 36 cores, yielding a total of 72 cores per node
  • Fat memory nodes: 5 compute nodes each equipped with 1 TB RAM and 2 Intel Icelake sockets; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with (up to) 36 cores, yielding a total of 72 cores per node
  • GPU nodes:
    • 5 compute nodes each equipped with 256 GB RAM, 2 Intel Icelake sockets, 2 NVidia A100 (40GB) GPUs and 894GB local scratch storage; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with (up to) 36 cores, yielding a total of 72 cores per node
    • 4 compute nodes each equipped with 1 TB RAM, 2 Intel Icelake sockets, 8 NVIDIA L40S GPUs with 48 GB memory and 3.4 TB local scratch storage; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with (up to) 36 cores, yielding a total of 72 cores per node

Besides, HSUper provides access to a 1PB BeeGFS file system, as well as a 1 PB Ceph-based file system and an 1.3 PB ZFS-based backup file system.
All nodes are connected by a non-blocking NVIDIA InfiniBand HDR100 fabric.

ISCC

The Interactive Scientific Computing Cloud (ISCC) aims to fill the gap for users with specific needs that cannot be containerized as well as users with workloads that cannot be satisfied by existing local machines and do not yet require the entire power of HSUper. The following links lead to the ISCC documentation on the HPC Portal.

Technical Specifications

The ISCC cluster consists of 14 hosts in total of which 13 share the same hardware specifications as HSUper, except for the interconnect, which is capable of 50Gb/s over Ethernet instead of InfiniBand HDR100. One new addition has HSUpreme-like hardware.

  • GPU hosts:
    • 2 hosts each equipped with 1 TB RAM, 2 Intel Icelake sockets, 8 NVidia A30 (24GB) GPUs and 2TB local scratch storage; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with 32 cores, yielding a total of 64 cores per host
    • 1 host equipped with 2 TB RAM, 2 Intel Icelake sockets, 8 NVIDIA L40S (48GB) GPUs and 2TB local scratch storage; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with 32 cores, yielding a total of 64 cores per host.
  • Regular hosts: 10 hosts each equipped with 256 GB RAM and 2 Intel Icelake sockets; each socket features a Intel(R) Xeon (R) Platinum 8360Y processor with 32 cores, yielding a total of 64 cores per host.
  • HSUpreme-like host: 1 host equipped with 2304 GB RAM and 2 (dual-socket) AMD EPYC 9655 with 96 cores, yielding a total of 192 cores per host.

Cerebras System

The Cerebras System is a two-node CS-3 system with two Wafer Scale Engines (WSE-3). Built on a 5nm process, the WSE-3 integrates 900,000 AI-optimized cores onto a single wafer. The architecture supports both AI (up to 240 billion parameters) and HPC workloads. The following links lead to the Cerebras documentation on the HPC Portal.

Fujitsu A64FX Testbed

Please note: Not part of the CBRZ! Access requests are handled separately.

  • 8 nodes
  • 48 cores @2.00 GHz per node
  • 32 GB RAM per node

AMD Epyc Testbed

Please note: Not part of the CBRZ! Access requests are handled separately.

  • 4 nodes
  • 64 cores @2.45 GHz per node
  • 256 GB RAM per node

Support

The administration / technical support can be reached via the ticket system (login with RZ credentials, Microsoft’s multi-factor authorization may intercept your request):

Alternatively, send an email to: [email protected]

HSU

Letzte Änderung: 11. November 2026