ALERT! Warning: your browser isn't supported. Please install a modern one, like Firefox, Opera, Safari, Chrome or the latest Internet Explorer. Thank you!
Startseite » ... » Zentrale Einrichtungen  » ZIH  » Wiki
phone prefix: +49 351 463.....

HPC Support

Operation Status

Ulf Markwardt: 33640
Claudia Schmidt: 39833

Login and project application

Phone: 40000
Fax: 42328

pencil_goRestoreRestore previous versiontext_align_leftRawView wiki markupeyeViewView formatted topictimeHistoryView revision historystart FirstView first revisionprev PreviousView previous revisionnext NextView next revisionend LastView last revisioncrossCloseClose this dialog
You are here: Compendium » SystemTaurus

Difference: SystemTaurus (r81 vs. r82)


Taurus has sets of nodes with a different amount of installed memory which affect where your job may be run. To achieve the shortest possible waiting time for your jobs, you should be aware of the limits shown in the following table.

PartitionNodes# NodesCores per NodeAvail. Memory per CoreAvail. Memory per NodeGPUs per node
haswell64taurusi[4001-4104,5001-5612,6001-6612]1328242583 MB62000 MB-
haswell128taurusi[4105-4188]84245250 MB126000 MB-
haswell256taurusi[4189-4232]442410583 MB254000 MB-
gpu1=gpu1=taurusi[2001-2042]=taurusi[2001-2042]=42=42=16=16=3000 MB=3000 MB=48000 MB=48000 MB=2=2=
gpu2taurusi[2045-2106]62242583 MB62000 MB4 (2 dual GPUs)
gpu1-interactivetaurusi[2001-2044]44163000 MB48000 MB2
gpu2-interactivetaurusi[2045-2108]64242583 MB62000 MB4 (2 dual GPUs)
smp1taurussmp[1-2]23231875 MB1020000 MB-
smp2taurussmp[3-7]55636500 MB2044000 MB-
=knl==taurusknl[1-32]=3264 (HT: 256)
1468 MB94000 MB-
broadwelltaurusi[4233-4264]32282214 MB62000 MB-
hpdlftaurusa[3-16]14127916 MB95000 MB3
mltaurusml[1-32]3244 (HT: 176)
1443 MB*254000 MB6
romeotaurusi[7001-7192]192128 (HT: 256)
1972 MB*505000 MB-
juliataurussmp81896 (HT: 1792)
27343 MB*49000000 MB-

* note that the ML nodes have 4way-SMT, so for every physical core allocated (e.g., with SLURM_HINT=nomultithread), you will always get 4*1443MB because the memory of the other threads is allocated implicitly, too.