HPC Cluster Q
For support or further information about the HPC Systems at FHI, please contact:
Simeon Beinlich (Phone: +49 30 8413 5270, Email: beinlich@fhi-berlin.mpg.de)
IMPORTANT: The Q-cluster was decomissioned end of 2024.
For former users this meant:
- Move any relevant data from Q and TLJH to your computer / home directories / other storage spaces. If you don't know where to put it, if you don't have enough space, or if you dont know how to move the data, please contact us.
- Deactivate / remove any licenses from Q so that you can reuse them.
- If you require a replacement for Q, have a look at the compute services above and the viper system!
System Overview
The Q cluster currently combines 40 dual-socket compute nodes with:
- 2x Intel Xeon Gold 6130 CPUs (2x 16cores, 2x 32 threads)
- 192GB of Memory
Two of these nodes are equipped with NVIDIA Tesla A100 GPUs.
In addition, 20 compute nodes of the former yFHIx cluster are available via the yfhix.q scheduler queue.
- 2x Intel Xeon E5-2660 CPUs (2x 10cores, 2x 20 threads)
- 128GB of Memory
Documentation and Git
Please refer to the Q Cluster Wiki in the FHI GITLAB Q Cluster Repository If you do not yet have a FHI GITLAB account, register now (FHI members only).
Mailing list
Please subscribe to the FHI-HPC-Users Mailing list for important information on the FHI HPC systems and maintenance notes. This is a newsletter mailing list, not a public one, so you will only be notified for important messages!
Accounts
Any member of the FHI can use the Q cluster. In order to get an account, please contact Simeon Beinlich (Phone: +49 30 8413 5270, Email: beinlich@fhi-berlin.mpg.de).
For further information regarding the Q cluster accounts see the Q Cluster Accounts.