Dardel status after the upgrade to a new software stack
Dardel was upgraded to a different cluster management system called HPCM some weeks ago. The upgraded system also has a newer version of the Cray programming environment (cpe/23.12), and the compute nodes are now running a newer version of the Cray operating system. This caused severe problems with the GPU partition (Dardel-GPU) at first. PDC now thinks most of these problems are resolved, and the GPU partition is open for all users. Unfortunately, there are still some problems with running large jobs (that is, jobs that use many nodes) on the CPU partition. Those jobs may hang after a while. HPE is working to resolve that problem.
Most software running on more than one node needs to be recompiled after the upgrade. Users developing software or maintaining a special version of a standard package may need to recompile the software. PDC has recompiled/reconfigured most of the standard applications for the new software stack.
To access the new software, you need to load the “PDC/23.12” (or PDC) module. For example:
ml PDC ml av openfoam --------------- /pdc/software/PDC/23.12/other --------------- openfoam/v2312 openfoam/6 openfoam/9 openfoam/11 (D)
Note: The modules PDC/23.03 and PDC/22.06 contain software that cannot be used on the current system, so please load PDC/23.12 instead.
Please contact PDC support if you notice any applications that are missing or if you encounter any other issues.