News from our group and our “mogon ticker” with software / work related news can be found at our webpage. The easiest way to get informed about our news is to subscribe to our rss-feed.

The regulations for use of the data center (ZDV) apply at all times. Further Policies are listed per item:

• Login-Nodes
• Home directory
• Accounts & Accounting
• Conducting courses on Mogon I or II
• For software install requests, please answer the questions of our form.

• How to access the mogon clusters I & II
• Compute nodes with technical description

• Submit jobs on Mogon
• General Notes on Partitions (a.k.a. batch queues)
• Manage and monitor jobs, pending reasons, information on job failures
• Memory reservation
• Managing I/O issues:
  • Node local scratch
  • Ramdisk reservation
  • Special/Dedicated File Systems:
    • EtapFS
    • I/O bandwidth reservation (ATLAS)
• Workflow Organization:
  • Setting up the environment (Modules)
  • Job Dependency
  • Job Arrays
  • Script Based Parallelisation (a.k.a Node-local scheduling)
  • Checkpoint Restarting
• Using Accelerators:
  • Using GPU Nodes

• Filesystems Overview
  • Efficient Transfer
  • Quotas
  • Backup (currently only for Mogon I)
• Archiving Data
  • Preparation Steps prior to Archiving
  • Archiving Data with TSM

• Mogon's Networks (currently under construction)

Here you will find information about specific software installed on Mogon along with several usage instructions. More information on how we build software and how to request installations can be found under this link. However, the direct link for install requests is here.

• Life Sciences
• Physical Simulation and Analytics Software

• JAVA
• MATLAB
• Mathematica
• Perl
• Python
  • Your Personal Environment (Additional Packages)
  • Job Submission
  • Performance Hints
• R
• Shells (with a focus on Bash)

• MPI
• Paraview
• Apache Spark

• LHC Grid documentation

• Scalasca http://www.scalasca.org/
• Allinea http://www.allinea.com//
• OpenSpeedShop http://www.openspeedshop.org/wp/ (further information soon)
• Profiling
  • Intel VTune
  • valgrind
• Optimization
  • Vectorization with regard to GCC

• Ganglia
  • Official Ganglia web page
  • MOGON ganglia monitoring report
  • Specific parameters and monitoring for MOGON
• Shell Based Monitoring

When preparing a journal publication please reference Mogon. We prepared a basic acknowledgement.

We offer various courses, particularly for newcomers via the university's Ilias e-learning system, where you can register for our courses. If you do not have a university account, please write to hpc@uni-mainz.de to register or ask for more information.

All courses, unless otherwise noted, will take place within the rooms of the ZDV. You will find us here.

There is a regular meeting of HPC users and administrators for news, discussions and support.

We offer every Thursday morning, at 10:15 am, to meet us in the 01 332 HPC-Workshop room of the annex building of the ZDV (Map - on the left side of the map).

Please drop us a quick note beforehand and tell us what exactly you want to talk about (a specific problem or a general introduction), so we can make sure that the appropriate person will be there.

If you have any questions or need help regarding high performance computing at the ZDV, send an eMail to hpc@uni-mainz.de (which will create a new ticket in our ticketing system).

Please do not send eMail to our staff directly - using the ticketing system helps us with appropriate scheduling and load balancing while supporting you and every other user.

If you write an eMail, please try to include as much information as possible, including, but not limited to:

• The job command line or the job script (sbatch …)
• JobIDs
• The environment you started the job in (at least the output of module list, maybe even env | sort)
• If possible, the whole job output, or if it is to big, the relevant output from the batch system (at the beginning and the end) and any error messages you encounter.