Skip to Content

Changes for page Slurm

Last modified by Thomas Coelho (local) on 2025/03/18 13:17
From version 8.1
edited by Thomas Coelho (local)
on 2023/08/28 15:17
Change comment: There is no comment for this version
To version 5.1
edited by Thomas Coelho
on 2022/12/08 11:05
Change comment: There is no comment for this version

Summary

Details

Page properties
Author
... ... @@ -1,1 +1,1 @@
1 -XWiki.coelho
1 +XWiki.thw
Content
... ... @@ -29,9 +29,7 @@
29 29  |barcelona|8|40|320|192|Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz|(((
30 30  Group Valenti
31 31  )))
32 -|barcelona|1|40|40|512|(((
33 -Intel(R) Xeon(R) Silver 4316 CPU @ 2.30GHz
34 -)))|Group Valenti
32 +|barcelona|1|40|40|512| |Group Valenti
35 35  |mallorca|4|48|192|256|AMD EPYC 7352 24-Core Processor|Group Valenti
36 36  |calea|36|64|2304|256|Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz|(((
37 37  Group Rezzolla
... ... @@ -61,8 +61,13 @@
61 61  You don't have to worry about the number of processes or specific nodes. Both slurm and openmpi know
62 62  about each other.
63 63  
64 -Running **SMP jobs** (multiple threads, not necessary mpi). Running MPI jobs on a single node is recommended for the
62 +If you want **infiniband** for your MPI job (which is usually a good idea, if not running on the same node), you have to request the feature infiniband:
65 65  
64 +{{{ sbatch -p dfg -C infiniband -n X jobscript.sh}}}
65 +
66 +Note: Infiniband is not available for 'fplo' and 'dfg-big'.
67 +
68 +Running **SMP jobs** (multiple threads, not necessary mpi). Running MPI jobs on a single node is recommended for the
66 66  dfg-big nodes. This are big host with up to 64 cpu's per node, but 'slow' gigabit network connection. Launch SMP jobs with
67 67  
68 68  {{{ sbatch -p PARTITION -N 1 -n X jobscript.sh}}}
... ... @@ -81,7 +81,7 @@
81 81  
82 82  where <MB> is the memory in megabytes. The virtual memory limit is 2.5 times of the requested real memory limit.
83 83  
84 -The memory limit is not a hard limit. When exceeding the limit, your memory will be swapped out. Only when using more the 110% of the limit your job will be killed. So be conservative, to keep enough room for other jobs. Requested memory is blocked from the use by other jobs.
87 +The memory limit is not a hard limit. When exceeding the limit, your memory will be swapped out. Only when using more the 150% of the limit your job will be killed. So be conservative, to keep enough room for other jobs. Requested memory is blocked from the use by other jobs.
85 85  
86 86  {{{ -t or --time=<time>}}}
87 87