High Performance Computing cluster - Hábrók
In 2023, the computing cluster Hábrók was put into operation. In Norse mythology, Hábrók is described as the finest hawk. The HPC team's computing clusters have all been named after birds of prey, with Hábrók being the fastest and best of them.
Specifications Hábrók
-
84 computers with 128 cores and 512 GB memory. These systems are specially tailored for data-intensive tasks;
-
48 computers with 128 cores, 512 GB memory and a super fast, low latency interconnect. These systems are suitable for large-scale processing of multiple computers;
-
4 nodes with 80 cores and 4 TB of memory for memory-intensive tasks;
-
3 nodes with 128 cores, 1.5 TB of memory and each 8 Nvidia RTX Pro 6000 GPU's, amongst other things suitable for the most new AI-workloads;
-
6 nodes with 64 cores, 512 GB memory and 4 Nvidia A100 cards with 40 GB memory each. These can, for example, accelerate machine learning;
-
19 nodes with 36 cores, 768 GB memory and 2 Nvidia V100 cards with 32 GB memory each, amongst other things suitable for AI-applications.
-
3PB shared storage for data to be processed on or generated by the cluster.
HPC Courses and Trainings
We regularly organize starters courses and advanced courses for our users. In the course overview of the CIT you will find more information about all the courses.
Request an Account
Would you like to request an account to be able to use the cluster? Please fill out the request form.
Please note!: As a researcher at the UG, you may also request an account for a student. If you are trying to request an account for a student, fill out their data (name, email etc.) If this is not the care, please fill out your own data.
Maintenance and Problems
You can find an overview of scheduled maintenance and current problems on the HPC-status page.
