Computing resources

General information about the queue / partition structure

The so-called queues known from LSF are now 'partitions' under Slurm. In most cases, you do not need to specify a partition, because an advanced automatic job submission mechanism is implemented to simplify this process.

For special cases (e.g. lectures and courses) you may need to specify an account, a reservation or a partition in your job scripts. For this, you will get additional details separately.

Configuration of batch jobs for different hardware

By default, jobs will be dispatched to any compute node(s) of the cluster, ie. to nodes of all phases (expansion stages) and types.

For special use cases like programs requiring special hardware, you need to define more sophisticated resource requirements. The most common distinction is by CPU architecture and by accelerator type, but you can also specify a particular section, as listed in the following table.

All other common resources like run time and memory consumption will be adequately attributed to the affected node types and sections.

Processor type
Resources Section Node range Details
avx512 MPI 3 mpsc MPI section, LB 2 phase I
NVD 3 gvqc, gaqc ACC section, LB 2 phase I
MEM 3 mpqc MEM section, LB 2 phase I
avx2 (or dgx) DGX 1 gaoc ACC section, LB 2 phase I, DGX A100
Accelerator type
(selected by “Generic Resources” instead of by “constraint/feature”)
GRes Accelerator type Node range Details
--gres=gpu Nvidia (all) gvqc, gaqc ACC section (all)
--gres=gpu:v100 Nvidia Volta 100 gvqc ACC section, LB 2 phase I
--gres=gpu:a100 Nvidia Ampere 100 gaqc ACC section, LB 2 phase I
Sections
Resources Section name Node range Details
mpi MPI mpsc MPI sections (all)
mem1536g MEM mpqc MEM section, LB 2 phase I

Resources can be requested with the parameter -C (“constraint”).

Several resource requirements can be combined with either & (lovgical AND) or | (logical OR):

Examples:

-C avx512
requests nodes with CPU architecture “avx512”
-C "avx512&mem1536g"
requests nodes with AVX512 instruction set AND 1.5 TByte RAM.
-C avx512
--gres=gpu:v100:2
requests nodes with CPU architecture “avx512” and 2 GPUs of type “Volta 100”