Resources of the High Performance Computer 'Elwetritsch'

Jobs are organized in partitions according to their resource requirements. Best practice is not to use partitions directly for job submission, but resource requirements and leave the selection of a partition 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	10	UP	899	20146	10 d	296	0	1597
gpuidle	2	20	UP	88	3180	10 d	16	0	60
cpuidle	2	20	UP	326	6256	10 d	0	0	0
epyc-128	3	30	UP	2	64	30 d	0	0	0
epyc-256	3	30	UP	216	3456	30 d	2908	0	22432
epyc-384	3	30	UP	22	704	30 d	0	0	0
epyc-768	3	30	UP	26	832	30 d	0	0	0
skylake-96	3	30	UP	300	7200	30 d	4896	0	3800
skylake-384	3	30	UP	26	624	30 d	360	0	0
haswell-64	3	30	UP	96	1536	30 d	1520	0	5104
haswell-256	3	30	UP	32	512	30 d	178	0	0
haswell-64s	3	30	UP	24	192	30 d	22	0	0
informatik-mind	3	70	UP	3	120	UNLIMITED	76	0	0
bio-csb	3	70	UP	4	224	UNLIMITED	0	0	0
bio-eco	3	70	UP	1	256	UNLIMITED	24	0	0
mv-fbk	3	70	UP	1	16	UNLIMITED	0	0	0
mv-mvt	3	70	UP	1	16	UNLIMITED	0	0	0
mv-ltd	3	70	UP	2	52	UNLIMITED	2	0	0
mv-ltm	3	70	UP	9	62	UNLIMITED	0	0	0
physik-eggert	3	70	UP	3	192	UNLIMITED	0	0	0
physik-fleischhauer	3	70	UP	2	72	UNLIMITED	0	0	0
physik-schneider	3	70	UP	10	176	UNLIMITED	0	0	0
ivw	3	70	UP	4	128	UNLIMITED	0	0	0
uds-hub	3	70	UP	48	2352	21 d	0	0	0
gpu	3	70	UP	33	560	10 d	254	0	6
dgx	3	70	UP	2	320	10 d	0	0	0
bigmem	3	70	UP	5	128	30 d	92	0	3456
							10644	0	36455