The compute nodes of Lise in Berlin (blogin.hlrn.de) and Emmy in Göttingen (glogin.hlrn.de) are organized via the following SLURM partitions:
...
Partition (number holds cores per node) | Node name | Nodes | Max. nodes per job | Max. jobs per user | Usable memory MB per node | CPU, GPU type | Shared | NPL per node hour | Remark | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| standard96 | gcn# | 12:00:00 | 924 | 256 | unlimited | 362 000 | Cascade 9242 | ✘ | 96 | default partition | |||||||||
| standard96:test | gcn# | 1:00:00 | 16 dedicated +48 on demand | 16 | unlimited | 362 000 | Cascade 9242 | ✘ | 96 | test nodes with higher priority but lower walltime | |||||||||
| large96 | gfn# | 12:00:00 | 12 | 2 | unlimited | 747 000 | Cascade 9242 | ✘ | 144 | fat memory nodes | |||||||||
| large96:test | gfn# | 1:00:00 | 2 dedicated +2 on demand | 2 | unlimited | 747 000 | Cascade 9242 | ✘ | 144 | fat memory test nodes with higher priority but lower walltime | |||||||||
| large96:shared | gfn# | 48:00:00 | 2 dedicated +2 on demand | 1 | unlimited | 747 000 | Cascade 9242 | ✓ | 144 | fat memory nodes for data pre- and postprocessing | |||||||||
| huge96 | gsn# | 24:00:00 | 2 | 1 | unlimited | 1522 000 | Cascade 9242 | ✘ | 192 | very fat memory nodes for data pre- and postprocessing | |||||||||
| medium40 | gcn# | 48:00:00 | 368 | 128 | unlimited | 181 000 | Skylake 6148 | ✘ | 40 | ||||||||||
| medium40:test | gcn# | 1:00:00 | 32 dedicated +96 on demand | 8 | unlimited | 181 000 | Skylake 6148 | ✘ | 40 | test nodes with higher priority but lower walltime | |||||||||
| large40 | gfn# | 48:00:00 | 11 | 4 | unlimited | 764 000 | Skylake 6148 | ✘ | 80 | fat memory nodes | |||||||||
| large40:test | gfn# | 1:00:00 | 3 | 2 | unlimited | 764 000 | Skylake 6148 | ✘ | 80 | fat memory test nodes with higher priority but lower walltime | |||||||||
| large40:shared | gfn# | 48:00:00 | 2 | 1 | unlimited | 764 000 | Skylake 6148 | ✓ | 80 | fat memory nodes for data pre- and postprocessing | |||||||||
| gpu | ggpu# | 12:00:00 | 3 | 3 | unlimited | 764 000 MB per node (32GB per gpu) | Skylake 6148 + 4 Tesla V100 | ✘ | 600 | see GPU Usage | |||||||||
| grete (coming soon24.04.2013) | ggpu# | 48:00:00 | 34 | 34 | unlimited | 500 000 MB per node (40GB per gpu) | Zen3 EPYC 7513 + 4 NVidia A100 | ✘ | coming soon 24.04.2013 | ||||||||||
| grete:shared (coming soon24.04.2013) | ggpu# | 48:00:00 | 34 | 34 | unlimited | 500 000 MB per node (40GB per gpu) | Zen3 EPYC 7513 + 4 NVidia A100 | ✓ | coming soon 24.04.2013 | ||||||||||
| grete-mig10g mig-interactive (coming soon24.04.2013) | ggpu# | 48:00:00 | 4 | 4 | unlimited | two 515 810 MB (40 GB per gpu) nodes and two 1 031 620 MB nodes (80 GB per GPU) | two Zen3 EPYC 7513 + 4 NVidia A100 and two Zen2 EPYC 7662 + 8 NVidia A100 nodes | ✓ | coming soon 24.04.2013 | see GPU Usage GPUs are split into slices via MIG (3 slices for the two nodes with 4 GPUs, and 7 slices for the two nodes with 8 GPUs) | |||||||||
| grete-mig10gmig-interactive preempt (coming soon24.04.2013) | ggpu# | 48:00:00 | 4 | 4 | unlimited | two 515 810 MB (40 GB per gpu) nodes and two 1 031 620 MB nodes (80 GB per GPU) | two Zen3 EPYC 7513 + 4 NVidia A100 and two Zen2 EPYC 7662 + 8 NVidia A100 nodes | ✓ | coming soon | grete-mig10g-preemptive (coming soon) | ggpu# | 48:00:00 | 4 | 4 | unlimited | two 515 810 MB (40 GB per gpu) nodes and two 1 031 620 MB nodes (80 GB per GPU) | two Zen3 EPYC 7513 + 4 NVidia A100 and two Zen2 EPYC 7662 + 8 NVidia A100 nodes | ✓ | coming soon24.04.2013 |
Which partition to choose?
...