The Computing Services of MPCDF

The Computing Services of MPCDF

The MPCDF provides facilities for high-performance computing (HPC) and data analytics/machine learning (HPDA/ML) , capacity computing (Linux clusters) and remote visualization and supports general-purpose and dedicated systems.

 A list of the major computing systems can be found below. A detailed description and technical documentation can be found at the MPCDF user documentation.

High-Performance Computing

The MPCDF hosts the central HPC resources of the Max Planck Society with a typical renewal cycle of 5 years. Open to scientists affiliated with Max-Planck Institutes which joined the corresponding proposals to the Max Planck Society (test access can be granted on request).

Viper CPU machine. Image credits: Klaus Zilker (MPCDF)
Based on AMD EPYC Genoa 9554 processors: 768 CPU compute nodes, 98304 CPU cores, 432 TB RAM (DDR5), 4.9 PFlop/s theoretical peak performance (FP64). In the course of 2024, a second phase with 300 GPU nodes comprising 600 AMD Instinct MI300A APUs will be deployed.
MPG Supercomputer Raven (since 2020)
Based on Intel Xeon IceLake-SP processors and Nvidia A100 GPUs. Deployment in two phases (April and June 2021) with 1592 CPU compute nodes, 114,624 CPU-cores, 375 TB RAM (DDR4), 8.8 PFlop/s theoretical peak performance (FP64), 192 GPU-accelerated nodes providing 768 Nvidia A100 GPUs,  30 TB GPU RAM (HBM2), 16 PFlop/s theoretical peak performance (FP64 incl. tensor cores)

Linux Compute Clusters

The MPCDF hosts dedicated compute clusters for many Max Planck Institutes. Open to scientists affiliated with the Max-Planck Institute(s) owning the resouces.

Dedicated Linux Compute Clusters
Dedicated Linux Compute Clusters hosted for several Max Planck Institutes

HPC Cloud

The HPC Cloud provides MPG projects with a flexible self-service cloud solution based on OpenStack, Ceph, and IBM Spectrum Scale on a rental basis.

HPC Cloud
A flexible and powerful computing environment for complex workflows, complementing the HPC systems.

Remote visualization service

Compute infrastructure for remote visualization and data analysis
Jupyter notebooks, remote visualization, remote desktops enable convenient web-based access to the HPC systems and selected linux compute clusters
Go to Editor View