Fork me on GitHub

Lrz HPC Systems

发表于 | 更新于 | 分类于 | 评论数：
本文字数： | 阅读时长 ≈

Access and overview of HPC(High Performance Systems)

http://doku.lrz.de

HPC opend for ignight

mpp2 mpp3 ivymuc inter

System Name Cores per node RAM per node(GB) MaxJobLimitsNodes MaxJobLimitsCores AllTime Queue Login Node
Linux Cluster CoolMUC-2 28 64 60 1680 48h mpp2 lxlogin5.lrz.de, lxlogin6.lrz.de, lxlogin7.lrz.de
Linux Cluster CoolMUC-3 64 96 25 1600 48h mpp3 lxlogin8.lrz.de
Linux-Cluster IvyMUC 16 64 12 192 72h ivymuc lxlogin10.lrz.de
Linux Cluster Teramem 96 6144 1 96 48h inter lxlogin5.lrz.de, lxlogin6.lrz.de, lxlogin7.lrz.de

operation

submit jobs

1
subtch *.sh

check jobs

1
squeue --cluster=mpp3

cancel jibs

1
2
scancel -M ivymuc -n pph
 #-M Cluster -n Jobname

example scripts

MPP2 (–time=48:00:00)
1
2
3
4
5
6
7
8
9
10
#!/bin/bash
#SBATCH --job-name=QUACANONT
#SBATCH --reservation=IGNITE
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=28
#SBATCH --mail-type=ALL
#SBATCH --clusters=mpp2
#SBATCH --time=48:00:00
#SBATCH --mem=55000
#SBATCH --err=10a_cgat_quast_canu_ont_ref.err
MPP3 (–time=48:00:00)
1
2
3
4
5
6
7
8
9
10
11
#!/bin/bash 
#SBATCH --job-name=metawrap
#SBATCH --output=output_metawrap.%j.%N.log
#SBATCH --error=error_metawrap.%j.%N.log
#SBATCH --get-user-env 
#SBATCH --clusters=mpp3
#SBATCH --nodes=3
#SBATCH --ntasks-per-node=64
#SBATCH --mail-user=user@lrz.uni-muenchen.de
#SBATCH --mail-type=ALL 
#SBATCH --time=48:00:00
IVYMUC (do not specify memory SBATCH –mem=448gb) (–time=72:00:00)
1
2
3
4
5
6
7
8
9
10
11
12
#!/bin/bash 
#SBATCH --job-name=metawrap
#SBATCH --output=output_metawrap.%j.%N.log
#SBATCH --error=error_metawrap.%j.%N.log
#SBATCH --get-user-env 
#SBATCH --clusters=ivymuc 
#SBATCH --nodes=7
#SBATCH --cpus-per-task=16
#SBATCH --ntasks-per-node=1
#SBATCH --mail-user=user@lrz.uni-muenchen.de
#SBATCH --mail-type=ALL
#SBATCH --time=72:00:00
TERAMEM (–time=48:00:00)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
#!/bin/bash 
#SBATCH --job-name=trans_pipeline
#SBATCH --output=output_trans_pipeline.%j.%N.log
#SBATCH --error=error_trans_pipeline.%j.%N.log
#SBATCH --get-user-env 
#SBATCH --clusters=inter
#SBATCH --partition=teramem_inter
#SBATCH --nodes=1
#SBATCH --cpus-per-task=96
#SBATCH --ntasks-per-node=1
#SBATCH --mem=2000gb
#SBATCH --mail-user=user@lrz.uni-muenchen.de
#SBATCH --mail-type=ALL
#SBATCH --time=48:00:00
------ END Thankyou ------