Accessing the Chimera Cluster
Most of the Chimera cluster services are accessible using your existing SIS login/password.
To login to the head node of Chimera cluster use the ssh command and enter your sis credentials:
ssh <sis_login_name>@hpc.troja.mff.cuni.cz
This head node is not intended for any CPU-intensive tasks.
Other services:
- GitLab account at gitlab.mff.cuni.cz (Note: Karlin local GitLab is separate service at gitlab.karlin.mff.cuni.cz)
- Initialize your JupyterHub Chimera account by loging at https://hpc.troja.mff.cuni.cz:8000
- Optional: Mattermost (collaboration platform designed for technical and operational teams).
- To report general problem with the Chimera cluster and get useful to get notifications from admins about planned outages and report use https://gitlab.mff.cuni.cz/mff/hpc/clusters/-/work_items
For users from mathematical section, please send email to hron@karlin.mff.cuni.cz to be added to math account to get priority access to partition of mathematical section (=hardware resources).
Computational resources
The cluster is mannaged by a SLURM system which divides the resources into partitions, serving as queues for jobs with different priorities. Each user belongs to certain accounts giving him access to selected partitions.
Accounts
To see the accounts you are a member of use command sshare -U. Every user should be member of ffa (free for all) account.
Please send email to hron@karlin.mff.cuni.cz to be added to math account to get priority access to partition of mathematical section.
Partitions
The list of all partitions can be generated by command sinfo -s. Partitions starting with ffa (ffa-short, ffa-preempt, ffa-checkpoint, ffa-long) are available to everyone with low priority. Partition math is available to all members of the math account.
You can use our utility freenodes to see nodes nad partitions status. To see particular partion (for example math) use freenodes -p math.
freenodes -p math
Cluster: chimera
node name ↔ busy cores state alloc cores in: partitions
r41⇄ ( 1 of 36x2) part 2BJMUV [..................|..................]
r42⇄ ( 0 of 36x2) free 2BJMUV [..................|..................]
r43⇄ ( 0 of 36x2) free 2BJMUV [..................|..................]
r44⇄ ( 0 of 36x2) free BJMUV [..................|..................]
r45⇄ ( 0 of 36x2) free BJMUV [..................|..................]
r46⇄ ( 0 of 36x2) free BJMUV [..................|..................]
r47⇄ ( 0 of 36x2) free BJMUV [..................|..................]
r50⇄ ( 0 of 192x2) free JUV [..... ...... .... .... ..... ....... ....... ... ....... ...... ... ........ ... ..... ..... .... ...... ... .....| ................ ................ ........... ............... ............... .............. .........]
There are 111 running jobs and 37 queued pending jobs.
partition allocation duration cores jobs running [ queue % ] jobs in queue next job to go in hh:mm
J math 1 day (max 0h) 444 0 ( 0 cores) [..........] 0% 0 ( 0 cores)
TOTAL 444 0 ( 0 cores) [..........] 0% 0 ( 0 cores)
More detailed tutorial on slurm usage is in preparation.
Data storage options
Every user has a home folder /home/<sis_login_name> with quota of 10 GB and hard limit of 15 GB of disc space.
If that is not sufficient, please send email request to J. Hron (hron@karlin.mff.cuni.cz) or J. Eliášek (jiri.eliasek@matfyz.cuni.cz) to setup a work folder with larger amount of disk space.
/home/...home folder, fast, space limmited/work/...storage for large data and computed results/scratch/...temporal fast storage/archive/...slow, long-term data storage
Environment modules
Software packages for users:
module available
--------------------------------------------------------- /etc/modulefiles ----------------------------------------------------------
DMTCP oneapi/debugger/2023.2.0 oneapi/intel_ippcp_intel64/2021.8.0
Mathematica/13.3 oneapi/debugger/2025.2.0 (D) oneapi/intel_ippcp_intel64/2025.2 (D)
UKRmol oneapi/dev-utilities/latest oneapi/ishmem/latest
....
Additional modules migrated from Snehurka cluster - still ongoing. Send email to J. Hron (hron@karlin.mff.cuni.cz) to request additional modules.
module use /home/hron/WORK/pkg/modulefiles
module load Arch/linux-rocky9-x86_64
module available
------------------------------------- /home/hron/WORK/pkg/Modules/User/linux-rocky9-x86_64/Math -------------------------------------
pari/2.17.3
------------------------------------- /home/hron/WORK/pkg/Modules/User/linux-rocky9-x86_64/Sets -------------------------------------
fenics/2019.1.0 (E) firedrake-env/2025.10 firedrake/2025.10 python-env/2026.04
------------------------------------- /home/hron/WORK/pkg/Modules/User/linux-rocky9-x86_64/Core -------------------------------------
R/4.5.2 (E) dmd/2.081.1 python/3.13.12 rclone/1.70.2 (T,L)
-------------------------------------------------- /home/hron/WORK/pkg/modulefiles --------------------------------------------------
Arch/linux-rocky9-cascadelake Arch/linux-rocky9-x86_64 (L) Arch/StdEnv (D)
Moving data to/from the cluster
Basic commands to transfer your data from Karlin (r3d3.karlin.mff.cuni.cz) to Chimera (hpc.troja.mff.cuni.cz). First login to r3d3.karlin.mff.cuni.cz with your karlin account. Then copy your files to troja by:
- Copy one file from local machine to the chimera cluster
scp local.dat <sis_login_name>@hpc.troja.mff.cuni.cz:/path/to/ - Copy whole local folder
scp -r local_folder<sis_login_name>@hpc.troja.mff.cuni.cz:/path/to/ - Synchronize a directory (recommended for repeated or large transfers)
rsync -avzP ./results/<sis_login_name>
This can be done also by loging to the Chimera cluster first and then copy the data from remote location, for examplescp <karlin_login>@r3d3.karlin.mff.cuni.cz:/path/to/folder ~/destination/
If you encounter any problems, please contact us at clusteradmin@karlin.mff.cuni.cz.
Useful chimera resources
Collection of useful notes for migration from Sněhurka cluster to Chimera cluster.
- Jaroslav Hron's presentation (PDF, 54 kB) from the training session
- Video recording (MP4, 445 MB) from the training session
- Zdeněk Mašín: Research Software Engineering [RSE] (PDF, 2 MB)
- 7. 4. 2026 updated: RSE webpage is https://rse.cuni.cz
- Institute of Particle and Nuclear Physics: Chimera: University HPC Cluster Tutorial – material for training held on 15. 10. 2025
Official Chimera information sources
Contacts
- general questions about Chimera cluster: Gitlab cluster work items at gitlab.mff.cuni.cz/mff/hpc/clusters or email to J. Eliášek (
jiri.eliasek@matfyz.cuni.cz) - questions or software additions for mathematical section: email to J. Hron (hron@karlin.mff.cuni.cz)
- data transfers from Snehurka cluster: email to clusteradmin@karlin.mff.cuni.cz