Main Navigation

Secondary Navigation

Page Contents

Contents

Resources of the High Performance Computer 'Elwetritsch'

Hardware Complexes

During time different hardware entered the High Performance Computer. To guarantee reproducibility and for parallel job a homogeneous environment, these different hardware components are clustered in complexes. Special among the complexes are head and dedicated which are reserved and not usable for longer jobs. The head nodes are intended for interactive work and dedicated nodes are owned by others and only available for their owners.

Login Nodes Login Server Properties Summary
Host Type CPUs Cores Memory Interconnect # Servers ∑ Cores ∑ Memory
TUK elwe1: Intel XEON SP 6126 2 24 384 GB 10 GE + IB QDR 1 24 384 GB
elwe2: Intel XEON SP 6126 2 24 384 GB 10 GE + IB QDR 1 24 384 GB
elwe3: Intel XEON SP 6126 2 24 384 GB 10 GE + IB QDR 1 24 384 GB
elwe4: Intel XEON SP 6126 2 24 384 GB 10 GE + IB QDR 1 24 384 GB
RARP elwe1: Intel E5-2670 2 16 128 GB 10 GE + IB QDR 1 16 128 GB
elwe2: Intel E5-2670 2 16 128 GB 10 GE + IB QDR 1 16 128 GB
6 128 1792 GB
Complex Server Properties Summary
Host Type CPUs Cores Memory Interconnect # Servers ∑ Cores ∑ Memory
sandybridge-32 Intel E5-2670 2 16 32 GB IB QDR 154 2464 4928 GB
sandybridge-64 Intel E5-2670 2 16 64 GB IB QDR 112 1792 7168 GB
sandybridge-128 Intel E5-2670 2 16 128 GB IB QDR 18 288 2304 GB
sandybridge-1024 Intel XEON E5-4650 4 32 1024 GB IB QDR 1 32 1024 GB
haswell-64 Intel E5-2640v3 2 16 64 GB IB QDR 96 1536 6144 GB
haswell-256 Intel E5-2640v3 2 16 256 GB IB QDR 24 384 6144 GB
haswell-64s Intel E5-2637v3 2 8 64 GB IB QDR 24 192 1536 GB
skylake-96 Intel XEON SP 6126 2 24 96 GB OPA 300 7200 28800 GB
skylake-384 Intel XEON SP 6126 2 24 384 GB OPA 24 576 9216 GB
gpu Intel E5-2670 + 2x NVIDIA Tesla M2090 2 16 32 GB IB QDR 3 48 96 GB
Intel E5-2670 + 2x NVIDIA Tesla M2090 2 16 64 GB IB QDR 3 48 192 GB
Intel E5-2670 + 2x NVIDIA Tesla K20x 2 16 64 GB IB QDR 2 32 128 GB
Intel E5-2670 + 4x NVIDIA Tesla K20x 2 16 64 GB IB QDR 1 16 64 GB
Intel E5-2640v3 + 1x NVIDIA Tesla K80 2 16 256 GB IB QDR 1 16 256 GB
Intel XEON SP 6126 + 1x NVIDIA Tesla V100 2 24 192 GB OPA 2 48 384 GB
Intel XEON SP 6126 + 4x NVIDIA Tesla V100 2 24 192 GB OPA 1 24 192 GB
mic Intel E5-2670 + 2x Intel XEON Phi 5110P 2 16 32 GB IB QDR 1 16 32 GB
Intel E5-2670 + 2x Intel XEON Phi 5110P 2 16 64 GB IB QDR 2 32 128 GB
knl Intel Xeon Phi Processor 7290 (KNL) 1 72 192 GB OPA 2 144 384 GB
vgl Intel E3-1270 + NVIDIA Quadro 4000 1 4 16 GB IB QDR 9 36 144 GB
Intel E6-1620v4 + NVIDIA Quadro P2000 1 4 64 GB OPA 7 28 448 GB
Intel E6-1620v4 + NVIDIA Quadro P2000 1 4 256 GB OPA 2 8 512 GB
misc 40 800 4328 GB
829 15760 74648 GB

Queues

Jobs are organized in queues or partitions according to their resource requirements. Best practice is not to use queues or partitions for job submission but resource requirements and leave the selection of a queue to the batch system. A very important resource is the job run time. It should be specified approximately, see guide. Other important resources are the requested memory of a job or the hardware of a CPU, all described in the guide.

Name Tier Priority State Nodes Job Slots Max Walltime Running Suspended Pending
idle 1 1 UP 830 16720 10 d 7948 0 8672
short 2 10 UP 771 15728 01:30 h 0 0 0
mem 2 11 UP 41 656 30 d 0 0 0
gpu 2 11 UP 13 232 10 d 8 0 3
mic 2 11 UP 3 96 10 d 0 0 0
knl 2 11 UP 2 576 10 d 576 0 0
extralong 2 12 UP 148 2160 30 d 0 0 0
long 2 13 UP 232 3504 10 d 0 0 0
normal 2 14 UP 374 5776 2 d 0 0 0
skylake 2 15 UP 322 7728 30 d 720 0 0
sandybridge-1024 2 21 UP 1 32 30 d 0 0 0
sandybridge-128 2 22 UP 17 272 30 d 96 0 0
sandybridge-64 2 23 UP 98 1568 30 d 176 0 0
sandybridge-32 2 24 UP 154 2464 30 d 2104 0 0
haswell-256 2 31 UP 24 384 30 d 304 0 0
haswell-64s 2 32 UP 24 192 30 d 60 0 0
haswell-64 2 32 UP 96 1536 30 d 1380 0 0
skylake-384 2 41 UP 22 528 30 d 480 0 0
skylake-96 2 42 UP 300 7200 30 d 1680 0 0
epyc-128 2 51 UP 2 128 30 d 64 0 0
biologie-stoeck 2 70 UP 1 24 UNLIMITED 0 0 0
physik-theophys 2 70 UP 3 40 UNLIMITED 0 0 0
ivw 2 70 UP 2 64 UNLIMITED 0 0 0
physik-schneider 2 70 UP 1 32 UNLIMITED 0 0 0
physik-fleischhauer 2 70 UP 2 108 UNLIMITED 45 0 0
mv-mvt 2 70 UP 3 44 UNLIMITED 16 0 0
physik-urbassek 2 70 UP 22 744 UNLIMITED 428 0 0
rhrk-test 2 80 UP 830 16720 UNLIMITED 0 0 0
interactive 2 81 UP 36 432 7 d 28 0 0
reservation 2 82 UP 830 16720 UNLIMITED 48 0 2
16161 0 8677

File Systems

The High Performance Computer comes up with different file systems for different purposes and policies. Please be aware that all files are deleted after your RHRK account has expired or your project has ended.

PathTypeSizeFreeCluster-wideQuotaBackupPurpose
$HOMENFS9 TB5 TByes40 GBvia NetApp snapshots
in /home/.snapshot
personal files, self-compiled programs
(will be deleted when your RHRK account expires)
$SCRATCHFhGFS1284 TB623 TByesnonenolarge files that can be read and written in parallel
(oldest files will be deleted when file system is 85% full)
$WORKNFS30 TB10 TByesnonenosmall files for simulations - on request only
(will be deleted when your RHRK account expires)
$TMPDIRext4varyingn/anononenoshort-time storage of local files
(will be deleted after job ends)