The new High Performance Computer CLAIX-2025 at the IT Center of RWTH Aachen University is an upgrade of the existing CLAIX system and thus complements CLAIX-2023 as part of a unified 1-cluster concept. The system was specifically tailored to the requirements of RWTH research and delivers another significant performance boost.
With a total of 421 directly water-cooled compute nodes for traditional High Performance Computing (HPC) and 6 + 14 (Tier-2 + WestAI) specialized ML nodes for AI and machine learning (ML), CLAIX-2025 achieves a total performance of over 6 PFLOPS in the CPU domain and a total of approximately 5.4 PFLOPS in the GPU domain for peak performance in the ML segment. The HPC portion is based on modern 2-socket systems with AMD Genoa 9654 CPUs (2×96 cores, 2.4 GHz), of which 108 nodes are equipped with 768 GB of RAM and 313 have 384 GB of RAM—ideal for application-specific requirements.
The ML nodes are based on AMD Turin CPUs (2×64 cores, 768 GB RAM) and are each equipped with four NVIDIA H100 SMX5 GPUs with 80 GB of HBM3e per node, enabling even large models to be trained efficiently. In addition, 14 more ML nodes are being provided through the WestAI project.
CLAIX-2025 uses a Cornelis CN5000 HFA 200 network with 2:1 blocking for fast communication between nodes. The system features 26 PiB of Lustre storage as well as additional BEEOND storage solutions on SSDs (1.6 to 3.2 TB per node). Direct Liquid Cooling (DLC) with a supply temperature of up to 35 °C represents another step toward a sustainable IT infrastructure.
CLAIX-2025 has been optimized with an eye toward the Total Cost of Ownership (TCO) and the typical RWTH job mix. Each year, approximately 708 million core-hours are provided in the HPC segment and 210,000 GPU-hours (+491,000 GPU-h for WestAI) in the ML sector. Together with CLAIX-2023, this results in a combined infrastructure offering over 1.2 billion core-hours and over 2.4 million GPU-hours annually.
A large portion of CLAIX-2025 is operated as part of NHR4CES and is available to researchers throughout Germany.
For more information, please see the post on the IT Center Blog. Instructions on how to use the system can be found on IT Center Help.