From Documentation
Jump to: navigation, search
(→‎For mpi jobs on orca)
 
(307 intermediate revisions by 3 users not shown)
Line 1: Line 1:
 +
{{Template:CCMissing}}
 
{{Software
 
{{Software
 
|package_name=LSDYNA
 
|package_name=LSDYNA
Line 7: Line 8:
 
=Introduction=
 
=Introduction=
  
−
Before a research group can use LSDYNA on sharcnet, a license must be purchased directly from LSTC for the sharcnet license server.  Alternately, if a research group resides at a institution that has sharcnet computing hardware (mac, uwo, guelph, waterloo) it maybe possible to use a pre-existing site license hosted on an accessible institutional license server.  To access and use this software you must be a member of the <b><i>lsdyna</i></b> group.
+
Before a research group can use LSDYNA on sharcnet, a license must be purchased directly from LSTC for the sharcnet license server.  Alternately, if a research group resides at a institution that has sharcnet computing hardware (mac, uwo, guelph, waterloo) it maybe possible to use a pre-existing site license hosted on an accessible institutional license server.  To access and use this software you must open a ticket and request to be added to the sharcnet <b><i>lsdyna</i></b> group.
  
 
=Version Selection=
 
=Version Selection=
  
−
==License==
+
==Graham Cluster==
 +
 
 +
===License===
 +
 
 +
Create and customize this file for your license server, where XXXXX should be replaced with your port number and Y with your server number:
 +
 
 +
[roberpj@gra1:~] cat .licenses/ls-dyna.lic
 +
#LICENSE_TYPE: network
 +
#LICENSE_SERVER: XXXXX@licenseY.uwo.sharcnet
 +
 
 +
===Module===
 +
 
 +
The modules are loaded automatically in the testomp.sh and testmpi.sh script shown below in the example section:
 +
 
 +
For single node smp jobs the available versions can be found by doing:
 +
 
 +
[roberpj@gra-login2:~] module spider ls-dyna
 +
        ls-dyna/7.1.2
 +
        ls-dyna/7.1.3
 +
        ls-dyna/8.1
 +
        ls-dyna/9.1
 +
        ls-dyna/9.2
 +
        ls-dyna/10.0
 +
 
 +
To load any version do for example:
 +
 
 +
module load ls-dyna/9.1
 +
 
 +
For multi node mpp jobs the available versions can be found by doing:
 +
 
 +
[roberpj@gra-login2:~] module spider ls-dyna-mpi
 +
        ls-dyna-mpi/7.1.2
 +
        ls-dyna-mpi/7.1.3
 +
        ls-dyna-mpi/8.1
 +
        ls-dyna-mpi/9.1
 +
        ls-dyna-mpi/9.2
 +
        ls-dyna-mpi/10.0
 +
 
 +
To load the 7.1.X modules do the following:
 +
module load openmpi/1.6.5 ls-dyna-mpi/7.1.3
 +
 
 +
To load the 8.X or 9.X modules do:
 +
module load openmpi/1.8.8 ls-dyna-mpi/9.2
 +
 
 +
To load the 10.X modules do:
 +
module load openmpi/1.10.7 ls-dyna-mpi/10.0
 +
 
 +
==Legacy Clusters==
 +
 
 +
===License===
  
 
Once a license configuration is established, the research group will be given a 5 digit port number.  The value should then be inserted into the appropriate departmental export statement before loading the module file as follows:
 
Once a license configuration is established, the research group will be given a 5 digit port number.  The value should then be inserted into the appropriate departmental export statement before loading the module file as follows:
  
 
o UofT Mechanical Engineering Dept
 
o UofT Mechanical Engineering Dept
−
<source lang="bash">export LSTC_LICENSE_SERVER='Port-Number'@license1.uwo.sharcnet</source>
+
<b><font color="purple">export</font></b> <font color="green">LSTC_LICENSE_SERVER</font>=<b><font color="red">Port</font></b>@license1.uwo.sharcnet
  
 
o McGill Mechanical Engineering Department
 
o McGill Mechanical Engineering Department
−
<source lang="bash">export LSTC_LICENSE_SERVER='Port-Number'@license2.uwo.sharcnet</source>
+
<b><font color="purple">export</font></b> <font color="green">LSTC_LICENSE_SERVER</font>=<b><font color="red">Port</font></b>@license2.uwo.sharcnet
  
 
o UW Mechanical and Mechatronics Engineering Dept
 
o UW Mechanical and Mechatronics Engineering Dept
−
<source lang="bash">export LSTC_LICENSE_SERVER='Port-Number'@license3.uwo.sharcnet</source>
+
<b><font color="purple">export</font></b> <font color="green">LSTC_LICENSE_SERVER</font>=<b><font color="red">Port</font></b>@license3.uwo.sharcnet
  
−
==Module==
+
o Laurentian University Bharti School of Engineering
 +
<b><font color="purple">export</font></b> <font color="green">LSTC_LICENSE_SERVER</font>=<b><font color="red">Port</font></b>@license4.uwo.sharcnet
  
−
The next step is to load the sharcnet lsdyna module for the version you want to use.  First check which modules are available by running the <i>module avail</i> command then load one the modules as shown:
+
o Fictitious Example:
 +
 
 +
<b><font color="purple">export</font></b> <font color="green">LSTC_LICENSE_SERVER</font>=<b><font color="red">12345</font></b>@license1.uwo.sharcnet
 +
 
 +
===Module===
 +
 
 +
The next step is load the desired sharcnet lsdyna module version.  Check which modules are available by running the <i>module avail</i> command then load one the modules as shown:
  
 
<source lang="bash">
 
<source lang="bash">
−
[roberpj@saw-login2:~] module avail lsdyna
+
[roberpj@orc-login2:~] module avail lsdyna
−
lsdyna/mpp/r611.79036  lsdyna/mpp/r611.80542
+
------------------------------------ /opt/sharcnet/modules ------------------------------------
−
lsdyna/smp/r711.88920   lsdyna/mpp/r711.88920  lsdyna/hyb/r711.88920
+
lsdyna/hyb/r711.88920    lsdyna/mpp/r711.88920    lsdyna/smp/r611.79036
−
lsdyna/ls980smpB1        lsdyna/ls980mppB1        lsdyna/ls980mppB2
+
lsdyna/mpp/ls971.r85718   lsdyna/mpp/r712.95028    lsdyna/smp/r711.88920
 +
lsdyna/mpp/ls980B1.011113 lsdyna/mpp/r800.95359    lsdyna/smp/r712.95028
 +
lsdyna/mpp/r611.79036    lsdyna/mpp/r901.109912    lsdyna/smp/r800.95359
 +
lsdyna/mpp/r611.80542    lsdyna/smp/ls980B1.78258  lsdyna/smp/r901.109912
 
</source>
 
</source>
  
−
===r7.1.1 versions===
+
====r9.0.1 versions====
 +
 
 +
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/r901.109912</pre>
  
 
o For mpi jobs:
 
o For mpi jobs:
 
<pre>
 
<pre>
−
module load lsdyna/mpp/r711.88920
+
module unload intel openmpi lsdyna mkl
 +
module load intel/15.0.3 openmpi/intel1503-std/1.8.7 lsdyna/mpp/r901.109912
 
</pre>
 
</pre>
 +
 +
====r8.0.0 versions====
  
 
o For serial or threaded jobs:
 
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/r800.95359</pre>
 +
 +
o For mpi jobs:
 
<pre>
 
<pre>
−
module load lsdyna/smp/r711.88920
+
module unload intel openmpi lsdyna mkl
 +
module load intel/15.0.3 openmpi/intel1503-std/1.8.7 lsdyna/mpp/r800.95359
 
</pre>
 
</pre>
  
−
o Note that hybrid threaded/mpi jobs are currently not supported. A minimum or 128cores is expected to be required before using this module once usage instructions are provided. The module is provided for internal testing purposes only:
+
====r7.1.2 versions====
−
<pre>
+
 
−
module load lsdyna/hyb/r711.88920
+
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/r712.95028</pre>
 +
 
 +
o For mpi jobs:
 +
<pre>module unload intel openmpi lsdyna
 +
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028
 
</pre>
 
</pre>
  
−
===r6.1.1 versions===
+
====r7.1.1 versions====
  
−
Note that <i>r611.79036</i> provides both lsdyna_s and lsdyna_d, while <i>r611.80542</i> provides only lsdyna_s.
+
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/r711.88920</pre>
  
−
====For mpi jobs on saw====
+
o For mpi jobs:
 +
<pre>module load lsdyna/mpp/r711.88920</pre>
 +
 
 +
====r6.1.1 versions====
 +
 
 +
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/r611.79036</pre>
 +
 
 +
o For mpi jobs:
 
<pre>
 
<pre>
 
module unload intel openmpi lsdyna
 
module unload intel openmpi lsdyna
  
−
module load intel/11.1.069 openmpi/intel/1.5.4 lsdyna/mpp/r611.79036
+
module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.79036
 
or
 
or
−
module load intel/11.1.069 openmpi/intel/1.5.4 lsdyna/mpp/r611.80542
+
module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.80542
 
</pre>
 
</pre>
  
−
====For mpi jobs on orca====
+
where <i>r611.80542</i> provides lsdyna_s only.<br>
 +
 
 +
====ls980 versions====
 +
 
 +
o For serial or threaded jobs:
 +
<pre>module load lsdyna/smp/ls980B1.78258</pre>
 +
 
 +
o For mpi jobs:
 
<pre>
 
<pre>
 
module unload intel openmpi lsdyna
 
module unload intel openmpi lsdyna
  
−
module load intel/11.1.069 openmpi/intel/1.5.5 lsdyna/mpp/r611.79036
+
module load intel/12.1.3 openmpi/intel/1.4.5 lsdyna/mpp/ls980B1.011113
 
or
 
or
−
module load intel/11.1.069 openmpi/intel/1.5.4 lsdyna/mpp/r611.80542  (xeon nodes only)
+
module load intel/12.1.3 openmpi/intel/1.6.2 lsdyna/smp/ls980B1.78258
 
</pre>
 
</pre>
  
−
====For mpi jobs on hound====
+
Note1) restart capability for ls980smpB1 and ls980mppB1 is not supported
 +
Note2) the module using legacy openmpi/intel/1.4.5 will run extremely slow
 +
 
 +
=Job Submission=
 +
 
 +
==Graham Cluster==
 +
 
 +
The submission scripts myompjob.sh and mympijob.sh for the airbag problem are shown in the <b>Example Job</b> section below, for both graham and orca.  Please note that you should specify your own username if submitting to a def account (not roberpj).  Alternatively you could specify your resource allocation account:
 +
 
 +
Sample threaded job submit script:
 +
 
 +
sbatch myompjob.sh
 +
 
 +
Sample mpi job submit script:
 +
 
 +
sbatch  mympijob.sh
 +
 
 +
==Legacy Clusters==
 +
 
 +
When loading a lsdyna sharcnet legacy module on the new orca or a sharcnet legacy system, the single or double precision solvers are specified with <strong>lsdyna_s</strong> or <strong>lsdyna_d</strong> respectively, as shown in the following sqsub commands:
 +
 
 +
===1cpu SERIAL Job===
 +
<pre>sqsub -r 1h -q serial -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=1</pre>
 +
 
 +
===4cpu SMP Job===
 +
<pre>sqsub -r 1h -q threaded -n 4 -o ofile.%J --mpp=1G lsdyna_s i=airbag.deploy.k ncpu=4</pre>
 +
 
 +
If using an explicit solver, one can specify a conservative initial memory setting on the command line as follows:
 +
 
 
<pre>
 
<pre>
−
module unload intel openmpi lsdyna
+
export LSTC_MEMORY=auto
 +
sqsub -r 1h -q threaded -n 4 -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=4 memory=754414</pre>
 +
where memory is the minimum number of 8 byte words shared by all processors in double precision, or, 4 byte words in single precision.
  
−
module load intel/11.1.069 openmpi/intel/1.5.5 lsdyna/mpp/r611.79036
+
The initial value can be determined by starting a simulation interactively on the command line, and finding the output resembling: <i> Memory required to begin solution      :      754414</i>.   The number of words can be specified as memory=260M instead of memory=260000000,  for further details see https://www.d3view.com/2006/10/a-few-words-on-memory-settings-in-ls-dyna/.
−
or
+
−
module load intel/11.1.069 openmpi/intel/1.5.5 lsdyna/mpp/r611.80542
+
−
</pre>
+
  
−
===ls980 versions===
+
===8cpu MPI Job===
  
−
Restart capability for the beta B1 versions described here are broken.
+
<pre>sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k</pre>
 +
 
 +
The initial memory can also be specified for mpi jobs  on the sqsub command line with "memory=" for the first master processor to decompose the problem  and "memory2=" used on all processors including the master to solves the decomposed problem, where the values are specified as 4 bytes per word in single precision and 8 bytes per word in double precision.   The number of words can be specified as memory=260M instead of memory=260000000 OR memory2=260M instead of memory2=260000000 for further details see https://www.d3view.com/2006/10/a-few-words-on-memory-settings-in-ls-dyna/.  The initial values can be found by running simulation interactively on a orca compute node and checking the output for a line such as: <i>Memory required to begin solution (memory=    464898  memory2=    158794 )</i> which could then be implemented for a job run in the queue by doing:
  
−
o For serial or threaded jobs:
 
 
<pre>
 
<pre>
−
module load lsdyna/ls980smpB1
+
export LSTC_MEMORY=auto
 +
sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k memory=464898 memory2=158794
 
</pre>
 
</pre>
  
−
o For mpi jobs using openmpi 1.4.5 ….
+
The specification of memory2 on sharcnet or compute canada clusters is not beneficial since the queue reserves the same memory per core for all nodes, such that the decomposition master node process cannot be allocated to have larger system memory. Therefore its sufficient to specify a single memory parameter by doing:
 +
 
<pre>
 
<pre>
−
module unload intel openmpi lsdyna
+
export LSTC_MEMORY=auto
−
module load intel/12.1.3 openmpi/intel/1.4.5 lsdyna/ls980mppB1
+
sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k memory=464898
 
</pre>
 
</pre>
  
−
o For mpi jobs using the default environment openmpi 1.6.2 ….
+
where the LSTC_MEMORY variable will only allow the memory to grow for explicit simulations. The following slurm examples demonstrate how to prescribe the memory parameters exactly.
 +
 
 +
=Example Job=
 +
 
 +
Copy the airbag example to your account:
 +
 
 +
rsync -av orca.computecanada.ca:/opt/sharcnet/lsdyna/r901.109912/examples r901.109912_examples
 +
cd r901.109912_examples/examples/misc/airbag
 +
gunzip airbag.deploy.k.gz
 +
 
 +
==Graham (default modules)==
 +
 
 +
Please note that graham does not have the sharcnet legacy modules installed on it.
 +
 
 +
===Threaded Job ===
 +
 
 +
Sample submission script <b>mysmpjob1.sh</b> for 4 core single precision smp job using compute canada default cvmfs modules:
 +
 
 
<pre>
 
<pre>
−
module load lsdyna/ls980mppB2
+
#!/bin/bash
 +
#SBATCH --account=def-roberpj-ab
 +
#SBATCH --nodes=1                          # use one node
 +
#SBATCH --cpus-per-task=4                  # number threads
 +
#SBATCH --mem=4000M                        # total memory
 +
#SBATCH --time=00:30:00                    # hrs:min:sec
 +
#SBATCH --job-name=testsmp1                # %x = jobname
 +
#SBATCH --output=slurm-%x-%N-%j.out
 +
echo "SLURM_CPUS_PER_TASK= "$SLURM_CPUS_PER_TASK
 +
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
 +
# ----------------------------------------------------------
 +
# IMPORTANT:  to set license server do either:
 +
# 1) export LSTC_LICENSE_SERVER=port@some.license.server
 +
# 2) create  ~/.licenses/ls-dyna.lic as shown above
 +
# ----------------------------------------------------------
 +
module load ls-dyna/9.1
 +
ls-dyna_s i=airbag.deploy.k ncpu=4 memory=1000M
 
</pre>
 
</pre>
  
−
=Job Submission=
+
where memory = 4000M / 4 (bytes/word) = 1000M words
  
−
To run the single or double precision solvers specify <strong>lsdyna_s</strong> or <strong>lsdyna_d</strong> respectively:
+
===Mpi Job ===
 +
 
 +
Sample submission script <b>mympijob2.sh</b> for 4 core double precision mpp job using compute canada default cvmfs modules:
  
−
o SUBMIT 1CPU SERIAL JOB
 
 
<pre>
 
<pre>
−
sqsub -r 1h -q serial -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=1
+
#!/bin/bash
 +
#SBATCH --account=def-roberpj-ab
 +
#SBATCH --ntasks=4                    # number of ranks
 +
#SBATCH --mem-per-cpu=4000M            # memory per rank
 +
#SBATCH --time=00:30:00                # hrs:min:sec
 +
#SBATCH --job-name=testmpi2            # %x = jobname
 +
#SBATCH --output=slurm-%x-%N-%j.out
 +
# ----------------------------------------------------------
 +
# IMPORTANT:  to set license server do either:
 +
# 1) export LSTC_LICENSE_SERVER=port@some.license.server
 +
# 2) create  ~/.licenses/ls-dyna.lic as shown above
 +
# ----------------------------------------------------------
 +
module load openmpi/1.8.8 ls-dyna-mpi/9.1
 +
srun ls-dyna_d i=airbag.deploy.k memory=500M memory2=500M
 
</pre>
 
</pre>
  
−
o SUBMIT 4CPU SMP JOB
+
where memory = 4000M / 8 (bytes/word) = 500M words
 +
 
 +
==New Orca (legacy modules)==
 +
 
 +
Please note, while new orca has most compute canada cvmfs modules available by default it does not have the graham the <i>ls-dyna</i> or <i>ls-dyna-mpi</i> modules installed.  Therefore currently the only way to run lsdyna is by using the legacy sharcnet <i>lsdyna</i> modules as shown in the following two smp and mpi examples.
 +
 
 +
===Threaded Job ===
 +
 
 +
Submission script <b>mysmpjob3.sh</b> to run 16 core single precision single node smp job with sharcnet legacy modules:
 +
 
 
<pre>
 
<pre>
−
sqsub -r 1h -q threaded -n 4 -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=4
+
#!/bin/bash
 +
#SBATCH --account=def-roberpj-ab
 +
#SBATCH --nodes=1                          # use one node
 +
#SBATCH --cpus-per-task=16                  # number threads
 +
#SBATCH --mem=4000M                        # total memory
 +
#SBATCH --time=00:30:00                    # hrs:min:sec
 +
#SBATCH --job-name=mysmpjob3-1node-16core    # jobname
 +
#SBATCH --output=slurm-%x-%N-%j.out        # %x = jobname
 +
echo "SLURM_CPUS_PER_TASK= "$SLURM_CPUS_PER_TASK
 +
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
 +
# ----------------------------------------------------------------
 +
# IMPORTANT:  to set license server for legacy modules:
 +
export LSTC_LICENSE_SERVER=31047@license3.sharcnet.ca
 +
# since ~/.licenses/ls-dyna.lic does NOT work with legacy modules
 +
# ----------------------------------------------------------------
 +
module purge --force
 +
export MODULEPATH=/opt/sharcnet/modules
 +
module load lsdyna/smp/r712.95028
 +
lsdyna_s i=airbag.deploy.k ncpu=$SLURM_CPUS_PER_TASK memory=500M
 
</pre>
 
</pre>
  
−
o SUBMIT 4CPU MPI JOB
+
where memory = 4000M / 8 (bytes/word) = 500M words
 +
 
 +
===MPI Job ===
 +
 
 +
To run the sharcnet legacy <i>module lsdyna/mpp/r712.95028</i> efficiently over several compute nodes with many cores requires using orca's xeon nodes as shown in <b> mympijob4.sh</b> below.  To run lsdyna on orca's opteron nodes with <i>module lsdyna/mpp/r712.95028</i> requires using only <b>one</b> opteron node as shown in <b> mympijob5.sh</b> below.  The other legacy sharcnet lsdyna mpp modules, as shown in the Availability Table  lsdyna/mpp/ls971.r85718, lsdyna/mpp/ls980B1.011113, lsdyna/mpp/r611.79036, lsdyna/mpp/r611.80542, lsdyna/mpp/r711.88920, lsdyna/mpp/r800.95359 and lsdyna/mpp/r901.109912 have yet to be tested. If you want to use one but cannot get it working please open a ticket.  Note that lines containing a space between "# and SBATCH" are comments.  To activate such line(s) required removal of the space ie) "#SBATCH".  Its recommended to use <i>module ls-dyna-mpi</i> on graham instead since the machine is far newer, faster and reliable.
 +
 
 +
====Multi Node Slurm Script====
  
−
Hound or Saw:
 
 
<pre>
 
<pre>
−
sqsub -r 1h -q mpi -o ofile.%J -n 4 --mpp=2G lsdyna_d i=airbag.deploy.k
+
[roberpj@orc-login2:~/samples/lsdyna/airbag] cat mympijob4.sh
 +
#!/bin/bash
 +
#SBATCH --account=def-roberpj-ab
 +
#SBATCH --constraint=xeon
 +
#SBATCH --ntasks=48
 +
#SBATCH --mem-per-cpu=4000M
 +
#SBATCH --time=00:30:00
 +
#SBATCH --job-name=mympijob4-Xnodes-48cores-xeon  # jobname
 +
#SBATCH --output=slurm-%x-%N-%j.out            # %x = jobname
 +
# -------------------------------------------------------------
 +
# To set license server when using legacy sharcnet modules:
 +
export LSTC_LICENSE_SERVER=port@some.license.server
 +
# since ~/.licenses/ls-dyna.lic does not work with legacy modules.
 +
# -------------------------------------------------------------
 +
module purge --force
 +
export MODULEPATH=/opt/sharcnet/modules
 +
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028
 +
MACHINEFILE=`srun hostname -s | tr '\n' ':' | sed 's/:/,/g' | sed 's/.$//'`
 +
mpirun --host $MACHINEFILE --mca plm_slurm_args '--cpu_bind=none' lsdyna_s i=airbag.deploy.k memory=250M memory2=250M
 
</pre>
 
</pre>
  
−
Orca:
+
====Single Node Slurm Script====
 +
 
 
<pre>
 
<pre>
−
sqsub -r 1h -q mpi -o ofile.%J -n 4 --mpp=2G -f opteron lsdyna_d i=airbag.deploy.k
+
[roberpj@orc-login2:~/samples/lsdyna/airbag] cat mympijob5.sh
 +
#!/bin/bash
 +
#SBATCH --account=def-roberpj-ab
 +
#SBATCH --constraint=opteron
 +
#SBATCH --nodes=1
 +
# SBATCH --ntasks=24
 +
# SBATCH --mem=0
 +
#SBATCH --ntasks=16
 +
#SBATCH --mem-per-cpu=1000M
 +
#SBATCH --time=00:30:00
 +
#SBATCH --job-name=mympijob5-1node-16cores-opteron  # jobname
 +
#SBATCH --output=slurm-%x-%N-%j.out        # %x = jobname
 +
# -------------------------------------------------------------
 +
# To set license server when using legacy sharcnet modules:
 +
export LSTC_LICENSE_SERVER=port@some.license.server
 +
# since ~/.licenses/ls-dyna.lic does not work with legacy modules.
 +
# -------------------------------------------------------------
 +
module purge --force
 +
export MODULEPATH=/opt/sharcnet/modules
 +
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028
 +
MACHINEFILE=`srun hostname -s | tr '\n' ':' | sed 's/:/,/g' | sed 's/.$//'`
 +
mpirun --host $MACHINEFILE lsdyna_s i=airbag.deploy.k memory=250M memory2=250M
 
</pre>
 
</pre>
  
−
=Example Job=
+
where memory = 1000M / 4 (bytes/word) = 250M words
 +
 
 +
==Legacy Clusters==
  
 
STEP1) The following shows sqsub submission of the [http://www.dynaexamples.com/examples-manual/misc/airbag airbag] example to the mpi queue.  Its recommended to first edit  <i>airbag.deploy.k</i>  and change <i>endtim</i> to 3.000E-00 so the job runs long enough to perform the restart in steps 2 and 3 below:
 
STEP1) The following shows sqsub submission of the [http://www.dynaexamples.com/examples-manual/misc/airbag airbag] example to the mpi queue.  Its recommended to first edit  <i>airbag.deploy.k</i>  and change <i>endtim</i> to 3.000E-00 so the job runs long enough to perform the restart in steps 2 and 3 below:
 
<pre>
 
<pre>
−
cp -a /opt/sharcnet/lsdyna/r611.79036/examples /work/$USER/test-lsdyna
+
cp -a /opt/sharcnet/lsdyna/r611.79036/examples /scratch/$USER/test-lsdyna
−
cd /work/$USER/test-lsdyna/misc/airbag
+
cd /scratch/$USER/test-lsdyna/misc/airbag
 
gunzip airbag.deploy.k.gz
 
gunzip airbag.deploy.k.gz
−
module unload intel openmpi lsdyna
 
−
SAW: module load intel/11.1.069 openmpi/intel/1.5.4 lsdyna/mpp/r611.79036
 
−
ORCA or HOUND: module load intel/11.1.069 openmpi/intel/1.5.5 lsdyna/mpp/r611.79036
 
−
export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
 
 
cp airbag.deploy.k airbag.deploy.restart.k
 
cp airbag.deploy.k airbag.deploy.restart.k
−
export LSTC_LICENSE_SERVER=XXXXX@licenseY.uwo.sharcnet
+
nano deploy.restart.k (reduce plot file creation frequency)
−
SAW or HOUND:
+
  *DATABASE_BINARY_D3PLOT
−
   sqsub -r 1h -q mpi --mpp=2G -n 4 -o ofile.%J lsdyna_d i=airbag.deploy.k
+
  $      dt      lcdtdeploy.restart.k
−
ORCA:
+
  1.000E-01   <--- change from 5.000E-04
−
  sqsub -r 10m -f opteron -q mpi --mpp=2G -n 4 -o ofile.%J lsdyna_s i=airbag.deploy.k
+
export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
 +
module unload intel openmpi lsdyna
 +
module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.79036
 +
sqsub -r 10m -q mpi --mpp=2G -n 8 -o ofile.%J lsdyna_d i=airbag.deploy.k
 
</pre>
 
</pre>
  
Line 165: Line 406:
  
 
<pre>
 
<pre>
−
SAW or HOUND:
+
sqsub -r 1h -q mpi --mpp=2G -n 8 -o ofile.%J lsdyna_d i=airbag.deploy.restart.k r=d3dump01
−
  sqsub -r 1h -q mpi --mpp=2G -n 4 -o ofile.%J lsdyna_d i=airbag.deploy.restart.k r=d3dump01
+
−
ORCA:
+
−
  sqsub -r 1h -f opteron -q mpi --mpp=2G -n 4 -o ofile.%J lsdyna_d i=airbag.deploy.restart.k r=d3dump01
+
 
</pre>
 
</pre>
  
 
=General Notes=
 
=General Notes=
  
−
==Affinity Issues==
+
==Graham Cluster==
  
−
It was reported Jan 14/2015 that using openmpi/intel/1.5.5 with lsdyna/mpp/r611.80542 can result in affinity errors on orca.  Therefore the instructions have been revised accordingly in https://www.sharcnet.ca/help/index.php/LSDYNA#For_mpi_jobs_on_orca to recommend using openmpi/intel/1.5.4 instead.  Because this is also enforced by the module load command the module switch command must be used move back to 1.5.5 as follows:
+
There are no special notes at the present time in regards to using lsdyna on graham.
  
−
<pre>
+
 
−
[roberpj@orc-login2:~] module unload intel openmpi lsdyna
+
==Command Line Use==
−
[roberpj@orc-login2:~] module load intel/11.1.069 openmpi/intel/1.5.4 lsdyna/mpp/r611.80542
+
 
−
[roberpj@orc-login2:~] module switch openmpi/intel/1.5.4 openmpi/intel/1.5.5
+
Following the upgrade of orca to the compute canada module stack, the orca development nodes were discontinued.<br>
−
</pre>
+
Therefore this section is no longer relevent and remain for historical purposes only.
 +
 
 +
Parallel lsdyna jobs can be run interactively on the command line (outside the queue) for short run testing purposes as follows:
 +
 
 +
o Orca Development Node MPP (mpi) Example
 +
 
 +
ssh orca.sharcnet.ca 
 +
ssh orc-dev1  (or dev2,3,4)
 +
module unload intel openmpi lsdyna
 +
module load intel/12.1.3 openmpi/intel/1.6.2 lsdyna/mpp/r711.88920
 +
mpirun -np 8 lsdyna_d i=airbag.deploy.k
 +
 
 +
o Orca Development Node SMP (threaded) Example
 +
 
 +
ssh orca.sharcnet.ca 
 +
ssh orc-dev1  (or dev2,3,4)
 +
module unload intel openmpi lsdyna
 +
module load lsdyna/smp/r711.88920
 +
lsdyna_d i=airbag.deploy.k ncpu=8
  
 
==Memory Issues==
 
==Memory Issues==
Line 193: Line 449:
 
this is probably something that should be reported to the OMPI developers.
 
this is probably something that should be reported to the OMPI developers.
 
--------------------------------------------------------------------------
 
--------------------------------------------------------------------------
 +
</pre>
 +
 +
Another error message which can occur after a job runs for a while if mpp is chosen to small is:
 +
 +
<pre>
 +
>>>>> Process 45 <<<<<
 +
>>>>> Signal 11 : Segmentation Violation <<<<<
 
</pre>
 
</pre>
  
Line 214: Line 477:
 
</pre>
 
</pre>
  
−
==Version Revision==
+
==Version and Revision==
  
 
Again run grep on the output file to extract the major and minor revision:
 
Again run grep on the output file to extract the major and minor revision:
Line 225: Line 488:
 
</pre>
 
</pre>
  
−
==Using lstc_qsun==
+
==Check License Status==
  
−
The available options for the <i>lstc_qrun</i> are given by:
+
===Running and Queued Programs===
  
−
<pre>
+
To get a summary of running and/or queued jobs use the <i>lstc_qrun</i> command as follows, where queued means the job has started running according to the sqsub command but its actually sitting waiting for license resources to come available.  Once these are acquired the job will start running on the cluster and appear as a Running Program according to lstc_qrun ie)
−
[roberpj@hnd19:~]  lstc_qrun -help
+
−
  o PRINT HELP AND QUIT:                lstc_qrun -help
+
−
  o PRINT VERSION INFO AND QUIT:        lstc_qrun -v
+
−
  o PRINT SERVER LIST:                  lstc_qrun -i
+
−
  o PRINT JOB INFO:                    lstc_qrun [-s server]
+
−
  o PRINT LICENSE INFORMATION:          lstc_qrun [-s server] -r
+
−
  o PRINT VERBOSE LICENSE INFORMATION: lstc_qrun [-s server] -R
+
−
</pre>
+
  
−
To check the status of your job in the queue use the sqjobs command.  On x86_64 systems you can check whether any of your jobs are queued on the license server use <i>lstc_qrun</i>. Its possible that sqsub will start your job but it will sit idle until enough license are available on the license server and the lstc_qrun command will reveal this:
+
<source lang="bash">
 +
[roberpj@hnd19:~] export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
  
−
<source lang="bash">
 
 
[roberpj@hnd19:~] lstc_qrun
 
[roberpj@hnd19:~] lstc_qrun
 
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
 
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
Line 257: Line 512:
 
dscronin    6396@hnd15            MPPDYNA_971      Tue Apr  9 21:54    6
 
dscronin    6396@hnd15            MPPDYNA_971      Tue Apr  9 21:54    6
 
csharson    28890@saw175.saw.sharc MPPDYNA_971      Wed Apr 10 16:48    6
 
csharson    28890@saw175.saw.sharc MPPDYNA_971      Wed Apr 10 16:48    6
−
roberpj    11257
+
No programs queued
 
</source>
 
</source>
  
−
At the time of this writing UWO is running on a 4cpu demo license with details:
+
To show license file expiration details, append "-R" to the command:
  
 
<source lang="bash">
 
<source lang="bash">
 +
[roberpj@hnd19:~] export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
 +
 
[roberpj@hnd19:~] lstc_qrun -R
 
[roberpj@hnd19:~] lstc_qrun -R
 
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
 
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
Line 280: Line 537:
 
  dscronin    6396@hnd15              6
 
  dscronin    6396@hnd15              6
 
  csharson  28890@saw175.saw.sharcnet  6
 
  csharson  28890@saw175.saw.sharcnet  6
−
roberpj    11257@hnd15              8
 
 
                   LICENSE GROUP    58    966  1024 |    0
 
                   LICENSE GROUP    58    966  1024 |    0
  
Line 288: Line 544:
 
                   LICENSE GROUP    0  1024  1024 |    0
 
                   LICENSE GROUP    0  1024  1024 |    0
 
</source>
 
</source>
 +
 +
===Killling A Program===
 +
 +
The queue normally kills lsdyna jobs cleanly.  However its possible that licences for a job (which is no longer running in the queue and therefore no longer has any processes running on the cluster) will continue to be tied up according to the lstc_qrun command.  To kill such a program determine the pid@hostname from the lstc_qrun command then run the following kill command.  The following example demonstrates the procedure for username roberpj:
 +
 +
<pre>
 +
[roberpj@orc-login2:~]  lstc_qrun -R | grep roberpj
 +
roberpj    45312@orc329.orca.shar MPPDYNA          Wed Dec  5 15:50    12
 +
 +
[roberpj@orc-login2:~] lstc_qkill 45312@orc329.orca.sharcnet.ca
 +
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
 +
Program queued for termination
 +
 +
[roberpj@orc-login2:~]  lstc_qrun -R | grep roberpj
 +
[roberpj@orc-login2:~]
 +
</pre>
  
 
==Legacy Instructions==
 
==Legacy Instructions==
Line 314: Line 586:
  
 
=References=
 
=References=
−
 
−
o LSTC Release Notes<br>
 
−
http://www.dynasupport.com/search?Subject%3Alist=release%20note
 
  
 
o LSTC LS-DYNA Homepage<br>
 
o LSTC LS-DYNA Homepage<br>
Line 324: Line 593:
 
http://www.dynasupport.com/
 
http://www.dynasupport.com/
  
−
o LS-DYNA and d3VIEW Blog<br>
+
o LS-DYNA Release Notes<br>
−
http://blog2.d3view.com/a-few-words-on-memory-settings-in-ls-dyna/
+
http://www.dynasupport.com/release-notes
  
−
o Convert Words to GB (500000000w=3.73gb,800000000w=5.96gb )<br>
+
o LS-PrePost Online Documentation FAQ<br>
−
http://deviceanalytics.com/memcalc.php
+
http://www.lstc.com/lspp/content/faq.shtml
 +
 
 +
o LSTC Download/Install Overview Page<br>
 +
Provides links to binaries for LS-DYNA SMP/MPP, LS-OPT, LS-PREPOST, LS-TASC.<br>
 +
http://www.lstc.com/download
 +
 
 +
==Memory Links==
 +
 
 +
o Implicit: Memory notes<br>
 +
http://www.dynasupport.com/howtos/implicit/implicit-memory-notes
  
 
o LS-DYNA Support Environment variables<br>
 
o LS-DYNA Support Environment variables<br>
 
http://www.dynasupport.com/howtos/general/environment-variables
 
http://www.dynasupport.com/howtos/general/environment-variables
  
−
o http://www.dynasupport.com/release-notes
+
o LS-DYNA and d3VIEW Blog (a few words on memory settings)<br>
−
http://www.dynasupport.com/release-notes
+
http://blog2.d3view.com/a-few-words-on-memory-settings-in-ls-dyna/
 +
 
 +
o Convert Words to GB ie) memory=500MW (3.73GB)<br>
 +
http://deviceanalytics.com/memcalc.php

Latest revision as of 09:25, 6 June 2019

This page is will be deleted pending it's creation on the CC wiki.
LSDYNA
Description: Suite of programs for transient dynamic finite element program
SHARCNET Package information: see LSDYNA software page in web portal
Full list of SHARCNET supported software


Introduction

Before a research group can use LSDYNA on sharcnet, a license must be purchased directly from LSTC for the sharcnet license server. Alternately, if a research group resides at a institution that has sharcnet computing hardware (mac, uwo, guelph, waterloo) it maybe possible to use a pre-existing site license hosted on an accessible institutional license server. To access and use this software you must open a ticket and request to be added to the sharcnet lsdyna group.

Version Selection

Graham Cluster

License

Create and customize this file for your license server, where XXXXX should be replaced with your port number and Y with your server number: 

[roberpj@gra1:~] cat .licenses/ls-dyna.lic 
#LICENSE_TYPE: network
#LICENSE_SERVER: XXXXX@licenseY.uwo.sharcnet

Module

The modules are loaded automatically in the testomp.sh and testmpi.sh script shown below in the example section:

For single node smp jobs the available versions can be found by doing: 

[roberpj@gra-login2:~] module spider ls-dyna
       ls-dyna/7.1.2
       ls-dyna/7.1.3
       ls-dyna/8.1
       ls-dyna/9.1
       ls-dyna/9.2
       ls-dyna/10.0

To load any version do for example: 

module load ls-dyna/9.1

For multi node mpp jobs the available versions can be found by doing: 

[roberpj@gra-login2:~] module spider ls-dyna-mpi
       ls-dyna-mpi/7.1.2
       ls-dyna-mpi/7.1.3
       ls-dyna-mpi/8.1
       ls-dyna-mpi/9.1
       ls-dyna-mpi/9.2
       ls-dyna-mpi/10.0

To load the 7.1.X modules do the following: 

module load openmpi/1.6.5 ls-dyna-mpi/7.1.3

To load the 8.X or 9.X modules do: 

module load openmpi/1.8.8 ls-dyna-mpi/9.2

To load the 10.X modules do: 

module load openmpi/1.10.7 ls-dyna-mpi/10.0

Legacy Clusters

License

Once a license configuration is established, the research group will be given a 5 digit port number. The value should then be inserted into the appropriate departmental export statement before loading the module file as follows:

o UofT Mechanical Engineering Dept 

export LSTC_LICENSE_SERVER=Port@license1.uwo.sharcnet

o McGill Mechanical Engineering Department 

export LSTC_LICENSE_SERVER=Port@license2.uwo.sharcnet

o UW Mechanical and Mechatronics Engineering Dept 

export LSTC_LICENSE_SERVER=Port@license3.uwo.sharcnet

o Laurentian University Bharti School of Engineering 

export LSTC_LICENSE_SERVER=Port@license4.uwo.sharcnet

o Fictitious Example: 

export LSTC_LICENSE_SERVER=12345@license1.uwo.sharcnet

Module

The next step is load the desired sharcnet lsdyna module version. Check which modules are available by running the module avail command then load one the modules as shown: 

[roberpj@orc-login2:~] module avail lsdyna
------------------------------------ /opt/sharcnet/modules ------------------------------------
lsdyna/hyb/r711.88920     lsdyna/mpp/r711.88920     lsdyna/smp/r611.79036
lsdyna/mpp/ls971.r85718   lsdyna/mpp/r712.95028     lsdyna/smp/r711.88920
lsdyna/mpp/ls980B1.011113 lsdyna/mpp/r800.95359     lsdyna/smp/r712.95028
lsdyna/mpp/r611.79036     lsdyna/mpp/r901.109912    lsdyna/smp/r800.95359
lsdyna/mpp/r611.80542     lsdyna/smp/ls980B1.78258  lsdyna/smp/r901.109912

r9.0.1 versions

o For serial or threaded jobs: 

module load lsdyna/smp/r901.109912

o For mpi jobs: 

module unload intel openmpi lsdyna mkl
module load intel/15.0.3 openmpi/intel1503-std/1.8.7 lsdyna/mpp/r901.109912

r8.0.0 versions

o For serial or threaded jobs: 

module load lsdyna/smp/r800.95359

o For mpi jobs: 

module unload intel openmpi lsdyna mkl
module load intel/15.0.3 openmpi/intel1503-std/1.8.7 lsdyna/mpp/r800.95359

r7.1.2 versions

o For serial or threaded jobs: 

module load lsdyna/smp/r712.95028

o For mpi jobs: 

module unload intel openmpi lsdyna
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028

r7.1.1 versions

o For serial or threaded jobs: 

module load lsdyna/smp/r711.88920

o For mpi jobs: 

module load lsdyna/mpp/r711.88920

r6.1.1 versions

o For serial or threaded jobs: 

module load lsdyna/smp/r611.79036

o For mpi jobs: 

module unload intel openmpi lsdyna

module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.79036
or
module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.80542

where r611.80542 provides lsdyna_s only.

ls980 versions

o For serial or threaded jobs: 

module load lsdyna/smp/ls980B1.78258

o For mpi jobs: 

module unload intel openmpi lsdyna

module load intel/12.1.3 openmpi/intel/1.4.5 lsdyna/mpp/ls980B1.011113
or
module load intel/12.1.3 openmpi/intel/1.6.2 lsdyna/smp/ls980B1.78258

Note1) restart capability for ls980smpB1 and ls980mppB1 is not supported Note2) the module using legacy openmpi/intel/1.4.5 will run extremely slow

Job Submission

Graham Cluster

The submission scripts myompjob.sh and mympijob.sh for the airbag problem are shown in the Example Job section below, for both graham and orca. Please note that you should specify your own username if submitting to a def account (not roberpj). Alternatively you could specify your resource allocation account:

Sample threaded job submit script: 

sbatch myompjob.sh

Sample mpi job submit script: 

sbatch  mympijob.sh

Legacy Clusters

When loading a lsdyna sharcnet legacy module on the new orca or a sharcnet legacy system, the single or double precision solvers are specified with lsdyna_s or lsdyna_d respectively, as shown in the following sqsub commands:

1cpu SERIAL Job

sqsub -r 1h -q serial -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=1

4cpu SMP Job

sqsub -r 1h -q threaded -n 4 -o ofile.%J --mpp=1G lsdyna_s i=airbag.deploy.k ncpu=4

If using an explicit solver, one can specify a conservative initial memory setting on the command line as follows: 

export LSTC_MEMORY=auto
sqsub -r 1h -q threaded -n 4 -o ofile.%J --mpp=2G lsdyna_d i=airbag.deploy.k ncpu=4 memory=754414

where memory is the minimum number of 8 byte words shared by all processors in double precision, or, 4 byte words in single precision.

The initial value can be determined by starting a simulation interactively on the command line, and finding the output resembling: Memory required to begin solution  : 754414. The number of words can be specified as memory=260M instead of memory=260000000, for further details see https://www.d3view.com/2006/10/a-few-words-on-memory-settings-in-ls-dyna/.

8cpu MPI Job

sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k

The initial memory can also be specified for mpi jobs on the sqsub command line with "memory=" for the first master processor to decompose the problem and "memory2=" used on all processors including the master to solves the decomposed problem, where the values are specified as 4 bytes per word in single precision and 8 bytes per word in double precision. The number of words can be specified as memory=260M instead of memory=260000000 OR memory2=260M instead of memory2=260000000 for further details see https://www.d3view.com/2006/10/a-few-words-on-memory-settings-in-ls-dyna/. The initial values can be found by running simulation interactively on a orca compute node and checking the output for a line such as: Memory required to begin solution (memory= 464898 memory2= 158794 ) which could then be implemented for a job run in the queue by doing: 

export LSTC_MEMORY=auto
sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k memory=464898 memory2=158794

The specification of memory2 on sharcnet or compute canada clusters is not beneficial since the queue reserves the same memory per core for all nodes, such that the decomposition master node process cannot be allocated to have larger system memory. Therefore its sufficient to specify a single memory parameter by doing: 

export LSTC_MEMORY=auto 
sqsub -r 1h -q mpi -o ofile.%J -n 8 --mpp=2G lsdyna_d i=airbag.deploy.k memory=464898

where the LSTC_MEMORY variable will only allow the memory to grow for explicit simulations. The following slurm examples demonstrate how to prescribe the memory parameters exactly.

Example Job

Copy the airbag example to your account: 

rsync -av orca.computecanada.ca:/opt/sharcnet/lsdyna/r901.109912/examples r901.109912_examples
cd r901.109912_examples/examples/misc/airbag
gunzip airbag.deploy.k.gz

Graham (default modules)

Please note that graham does not have the sharcnet legacy modules installed on it.

Threaded Job

Sample submission script mysmpjob1.sh for 4 core single precision smp job using compute canada default cvmfs modules: 

#!/bin/bash
#SBATCH --account=def-roberpj-ab
#SBATCH --nodes=1                           # use one node
#SBATCH --cpus-per-task=4                   # number threads
#SBATCH --mem=4000M                         # total memory
#SBATCH --time=00:30:00                     # hrs:min:sec
#SBATCH --job-name=testsmp1                 # %x = jobname
#SBATCH --output=slurm-%x-%N-%j.out
echo "SLURM_CPUS_PER_TASK= "$SLURM_CPUS_PER_TASK
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
# ----------------------------------------------------------
# IMPORTANT:  to set license server do either:
# 1) export LSTC_LICENSE_SERVER=port@some.license.server
# 2) create  ~/.licenses/ls-dyna.lic as shown above
# ----------------------------------------------------------
module load ls-dyna/9.1
ls-dyna_s i=airbag.deploy.k ncpu=4 memory=1000M

where memory = 4000M / 4 (bytes/word) = 1000M words

Mpi Job

Sample submission script mympijob2.sh for 4 core double precision mpp job using compute canada default cvmfs modules: 

#!/bin/bash
#SBATCH --account=def-roberpj-ab
#SBATCH --ntasks=4                     # number of ranks
#SBATCH --mem-per-cpu=4000M            # memory per rank
#SBATCH --time=00:30:00                # hrs:min:sec
#SBATCH --job-name=testmpi2            # %x = jobname
#SBATCH --output=slurm-%x-%N-%j.out
# ----------------------------------------------------------
# IMPORTANT:  to set license server do either:
# 1) export LSTC_LICENSE_SERVER=port@some.license.server
# 2) create  ~/.licenses/ls-dyna.lic as shown above
# ----------------------------------------------------------
module load openmpi/1.8.8 ls-dyna-mpi/9.1
srun ls-dyna_d i=airbag.deploy.k memory=500M memory2=500M

where memory = 4000M / 8 (bytes/word) = 500M words

New Orca (legacy modules)

Please note, while new orca has most compute canada cvmfs modules available by default it does not have the graham the ls-dyna or ls-dyna-mpi modules installed. Therefore currently the only way to run lsdyna is by using the legacy sharcnet lsdyna modules as shown in the following two smp and mpi examples.

Threaded Job

Submission script mysmpjob3.sh to run 16 core single precision single node smp job with sharcnet legacy modules: 

#!/bin/bash
#SBATCH --account=def-roberpj-ab
#SBATCH --nodes=1                           # use one node
#SBATCH --cpus-per-task=16                  # number threads
#SBATCH --mem=4000M                         # total memory
#SBATCH --time=00:30:00                     # hrs:min:sec
#SBATCH --job-name=mysmpjob3-1node-16core    # jobname
#SBATCH --output=slurm-%x-%N-%j.out         # %x = jobname
echo "SLURM_CPUS_PER_TASK= "$SLURM_CPUS_PER_TASK
export OMP_NUM_THREADS=$SLURM_CPUS_PER_TASK
# ----------------------------------------------------------------
# IMPORTANT:  to set license server for legacy modules:
export LSTC_LICENSE_SERVER=31047@license3.sharcnet.ca
# since ~/.licenses/ls-dyna.lic does NOT work with legacy modules
# ----------------------------------------------------------------
module purge --force
export MODULEPATH=/opt/sharcnet/modules
module load lsdyna/smp/r712.95028
lsdyna_s i=airbag.deploy.k ncpu=$SLURM_CPUS_PER_TASK memory=500M

where memory = 4000M / 8 (bytes/word) = 500M words

MPI Job

To run the sharcnet legacy module lsdyna/mpp/r712.95028 efficiently over several compute nodes with many cores requires using orca's xeon nodes as shown in mympijob4.sh below. To run lsdyna on orca's opteron nodes with module lsdyna/mpp/r712.95028 requires using only one opteron node as shown in mympijob5.sh below. The other legacy sharcnet lsdyna mpp modules, as shown in the Availability Table lsdyna/mpp/ls971.r85718, lsdyna/mpp/ls980B1.011113, lsdyna/mpp/r611.79036, lsdyna/mpp/r611.80542, lsdyna/mpp/r711.88920, lsdyna/mpp/r800.95359 and lsdyna/mpp/r901.109912 have yet to be tested. If you want to use one but cannot get it working please open a ticket. Note that lines containing a space between "# and SBATCH" are comments. To activate such line(s) required removal of the space ie) "#SBATCH". Its recommended to use module ls-dyna-mpi on graham instead since the machine is far newer, faster and reliable.

Multi Node Slurm Script

[roberpj@orc-login2:~/samples/lsdyna/airbag] cat mympijob4.sh
#!/bin/bash
#SBATCH --account=def-roberpj-ab
#SBATCH --constraint=xeon
#SBATCH --ntasks=48
#SBATCH --mem-per-cpu=4000M
#SBATCH --time=00:30:00
#SBATCH --job-name=mympijob4-Xnodes-48cores-xeon  # jobname
#SBATCH --output=slurm-%x-%N-%j.out             # %x = jobname
# -------------------------------------------------------------
# To set license server when using legacy sharcnet modules:
export LSTC_LICENSE_SERVER=port@some.license.server
# since ~/.licenses/ls-dyna.lic does not work with legacy modules.
# -------------------------------------------------------------
module purge --force
export MODULEPATH=/opt/sharcnet/modules
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028
MACHINEFILE=`srun hostname -s | tr '\n' ':' | sed 's/:/,/g' | sed 's/.$//'`
mpirun --host $MACHINEFILE --mca plm_slurm_args '--cpu_bind=none' lsdyna_s i=airbag.deploy.k memory=250M memory2=250M

Single Node Slurm Script

[roberpj@orc-login2:~/samples/lsdyna/airbag] cat mympijob5.sh
#!/bin/bash
#SBATCH --account=def-roberpj-ab
#SBATCH --constraint=opteron
#SBATCH --nodes=1
# SBATCH --ntasks=24
# SBATCH --mem=0
#SBATCH --ntasks=16
#SBATCH --mem-per-cpu=1000M
#SBATCH --time=00:30:00
#SBATCH --job-name=mympijob5-1node-16cores-opteron  # jobname
#SBATCH --output=slurm-%x-%N-%j.out         # %x = jobname
# -------------------------------------------------------------
# To set license server when using legacy sharcnet modules:
export LSTC_LICENSE_SERVER=port@some.license.server
# since ~/.licenses/ls-dyna.lic does not work with legacy modules.
# -------------------------------------------------------------
module purge --force
export MODULEPATH=/opt/sharcnet/modules
module load intel/12.1.3 openmpi/intel/1.6.5 lsdyna/mpp/r712.95028
MACHINEFILE=`srun hostname -s | tr '\n' ':' | sed 's/:/,/g' | sed 's/.$//'`
mpirun --host $MACHINEFILE lsdyna_s i=airbag.deploy.k memory=250M memory2=250M

where memory = 1000M / 4 (bytes/word) = 250M words

Legacy Clusters

STEP1) The following shows sqsub submission of the airbag example to the mpi queue. Its recommended to first edit airbag.deploy.k and change endtim to 3.000E-00 so the job runs long enough to perform the restart in steps 2 and 3 below: 

cp -a /opt/sharcnet/lsdyna/r611.79036/examples /scratch/$USER/test-lsdyna
cd /scratch/$USER/test-lsdyna/misc/airbag
gunzip airbag.deploy.k.gz
cp airbag.deploy.k airbag.deploy.restart.k
nano deploy.restart.k (reduce plot file creation frequency)
   *DATABASE_BINARY_D3PLOT
   $       dt      lcdtdeploy.restart.k
   1.000E-01   <--- change from 5.000E-04 
export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
module unload intel openmpi lsdyna
module load intel/11.1.069 openmpi/intel/1.6.4 lsdyna/mpp/r611.79036
sqsub -r 10m -q mpi --mpp=2G -n 8 -o ofile.%J lsdyna_d i=airbag.deploy.k

STEP2) With the job still running, use the echo command as follows to create a file called "D3KIL" that will trigger generation of restart files at which point the file D3KIL itself will be erased. Do this once a day if data loss is critical to you OR once or twice just before the sqsub -r time limit is reached. Further information can be found here http://www.dynasupport.com/tutorial/ls-dyna-users-guide/sense-switch-control: 

echo "sw3" > D3KIL
sqkill job#

STEP3) Before the job can be restarted, the following two lines must be added to the airbag.deploy.restart.k file: 

*CHANGE_CURVE_DEFINITION
         1

STEP4) Now resubmit the job as follows using "r=" to specify the restart file: 

sqsub -r 1h -q mpi --mpp=2G -n 8 -o ofile.%J lsdyna_d i=airbag.deploy.restart.k r=d3dump01

General Notes

Graham Cluster

There are no special notes at the present time in regards to using lsdyna on graham.


Command Line Use

Following the upgrade of orca to the compute canada module stack, the orca development nodes were discontinued.
Therefore this section is no longer relevent and remain for historical purposes only.

Parallel lsdyna jobs can be run interactively on the command line (outside the queue) for short run testing purposes as follows:

o Orca Development Node MPP (mpi) Example 

ssh orca.sharcnet.ca  
ssh orc-dev1  (or dev2,3,4)
module unload intel openmpi lsdyna
module load intel/12.1.3 openmpi/intel/1.6.2 lsdyna/mpp/r711.88920
mpirun -np 8 lsdyna_d i=airbag.deploy.k

o Orca Development Node SMP (threaded) Example 

ssh orca.sharcnet.ca  
ssh orc-dev1  (or dev2,3,4)
module unload intel openmpi lsdyna
module load lsdyna/smp/r711.88920
lsdyna_d i=airbag.deploy.k ncpu=8

Memory Issues

A minumum of mpp=2G is recommended although the memory requirement of a job may suggest much less is required. For instance setting mpp=1G for the airbag test job above will result in the following error when running a job in the queue: 

--------------------------------------------------------------------------
An attempt to set processor affinity has failed - please check to
ensure that your system supports such functionality. If so, then
this is probably something that should be reported to the OMPI developers.
--------------------------------------------------------------------------

Another error message which can occur after a job runs for a while if mpp is chosen to small is: 

>>>>> Process 45 <<<<<
>>>>> Signal 11 : Segmentation Violation <<<<<

To get an idea of the amount of memory a job used run grep on the output file: 

[roberpj@orc-login1:~/samples/lsdyna/airbag]  cat  ofile.2063302.orc-admin2.orca.sharcnet | grep Memory
     |    Distributed Memory Parallel                  |
 Memory size from command line:      500000,       500000
 Memory for the head node
 Memory installed (MB)        :        32237
 Memory free (MB)             :        11259
 Memory required (MB)         :            0
 Memory required to process keyword     :       458120
 Memory required for decomposition      :       458120
 Memory required to begin solution (memory=      458120 memory2=      230721)
 Max. Memory reqd for implicit sol: max used               0
 Max. Memory reqd for implicit sol: incore                 0
 Max. Memory reqd for implicit sol: oocore                 0
 Memory required to complete solution (memory=      458120 memory2=      230721)

Version and Revision

Again run grep on the output file to extract the major and minor revision: 

[roberpj@orc-login1:~/samples/lsdyna/airbag]  cat  ofile.2063302.orc-admin2.orca.sharcnet | grep 'Revision\|Version'
     |  Version : mpp s R6.1.1    Date: 01/02/2013     |
     |  Revision: 78769           Time: 07:43:30       |
     |  SVN Version: 80542                             |

Check License Status

Running and Queued Programs

To get a summary of running and/or queued jobs use the lstc_qrun command as follows, where queued means the job has started running according to the sqsub command but its actually sitting waiting for license resources to come available. Once these are acquired the job will start running on the cluster and appear as a Running Program according to lstc_qrun ie) 

[roberpj@hnd19:~] export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
 
[roberpj@hnd19:~] lstc_qrun
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
                     Running Programs
    User             Host          Program              Started       # procs
-----------------------------------------------------------------------------
dgierczy    20277@saw61.saw.sharcn LS-DYNA_971      Mon Apr  8 17:44     1
dgierczy     8570@saw32.saw.sharcn LS-DYNA_971      Mon Apr  8 17:44     1
dscronin    25486@hnd6             MPPDYNA_971      Tue Apr  9 20:19     6
dscronin    14897@hnd18            MPPDYNA_971      Tue Apr  9 21:48     6
dscronin    14971@hnd18            MPPDYNA_971      Tue Apr  9 21:48     6
dscronin    15046@hnd18            MPPDYNA_971      Tue Apr  9 21:48     6
dscronin    31237@hnd16            MPPDYNA_971      Tue Apr  9 21:53     6
dscronin    31313@hnd16            MPPDYNA_971      Tue Apr  9 21:54     6
dscronin     6396@hnd15            MPPDYNA_971      Tue Apr  9 21:54     6
csharson    28890@saw175.saw.sharc MPPDYNA_971      Wed Apr 10 16:48     6
No programs queued

To show license file expiration details, append "-R" to the command: 

[roberpj@hnd19:~] export LSTC_LICENSE_SERVER=#####@license#.uwo.sharcnet
 
[roberpj@hnd19:~] lstc_qrun -R
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
**** LICENSE INFORMATION ****
PROGRAM          EXPIRATION CPUS  USED   FREE    MAX | QUEUE
---------------- ----------      ----- ------ ------ | -----
LS-DYNA_971      12/31/2013          -    966   1024 |     0
 dgierczy   20277@saw61.saw.sharcnet   1
 dgierczy    8570@saw32.saw.sharcnet   1
MPPDYNA_971      12/31/2013          -    966   1024 |     0
 dscronin   25486@hnd6               6
 dscronin   14897@hnd18              6
 dscronin   14971@hnd18              6
 dscronin   15046@hnd18              6
 dscronin   31237@hnd16              6
 dscronin   31313@hnd16              6
 dscronin    6396@hnd15              6
 csharson   28890@saw175.saw.sharcnet   6
                   LICENSE GROUP    58    966   1024 |     0
 
PROGRAM          EXPIRATION CPUS  USED   FREE    MAX | QUEUE
---------------- ----------      ----- ------ ------ | -----
LS-OPT           12/31/2013          0   1024   1024 |     0
                   LICENSE GROUP     0   1024   1024 |     0

Killling A Program

The queue normally kills lsdyna jobs cleanly. However its possible that licences for a job (which is no longer running in the queue and therefore no longer has any processes running on the cluster) will continue to be tied up according to the lstc_qrun command. To kill such a program determine the pid@hostname from the lstc_qrun command then run the following kill command. The following example demonstrates the procedure for username roberpj: 

[roberpj@orc-login2:~]  lstc_qrun -R | grep roberpj
roberpj    45312@orc329.orca.shar MPPDYNA          Wed Dec  5 15:50    12

[roberpj@orc-login2:~] lstc_qkill 45312@orc329.orca.sharcnet.ca
Defaulting to server 1 specified by LSTC_LICENSE_SERVER variable
Program queued for termination

[roberpj@orc-login2:~]  lstc_qrun -R | grep roberpj
[roberpj@orc-login2:~]

Legacy Instructions

The following binaries remain available on saw and orca for backward compatibility testing: 

[roberpj@orc-login2:~] cd /opt/sharcnet/local/lsdyna
[roberpj@orc129:/opt/sharcnet/local/lsdyna] ls ls971*
ls971_d_R3_1    ls971_d_R4_2_1  ls971_s_R3_1    ls971_s_R4_2_1  ls971_s_R5_1_1
ls971_d_R4_2_0  ls971_d_R5_0    ls971_s_R4_2_0  ls971_s_R5_0

There are currently no sharcnet modules for these versions, hence jobs should be submitted as follows: 

module load lsdyna
export PATH=/opt/sharcnet/local/lsdyna:$PATH
export LSTC_LICENSE_SERVER=XXXXX@license3.uwo.sharcnet
cp /opt/sharcnet/local/lsdyna/examples/airbag.deploy.k airbag.deploy.k
SERIAL JOB:  sqsub -q serial -r 1d -o ofile.%J ls971_d_R4_2_1 i=airbag.deploy.k
THREADED JOB:  sqsub -q threaded -n 4 -r 1d -o ofile.%J ls971_d_R4_2_1 ncpu=4 para=2 i=airbag.deploy.k

Note! the ls971_s_R3_1 and ls971_d_R3_1 binaries do not work, a fix is being looked for.

References

o LSTC LS-DYNA Homepage
http://www.lstc.com/products/ls-dyna

o LSTC LS-DYNA Support (Tutorials, HowTos, Faq, Manuals, Release Notes, News, Links)
http://www.dynasupport.com/

o LS-DYNA Release Notes
http://www.dynasupport.com/release-notes

o LS-PrePost Online Documentation FAQ
http://www.lstc.com/lspp/content/faq.shtml

o LSTC Download/Install Overview Page
Provides links to binaries for LS-DYNA SMP/MPP, LS-OPT, LS-PREPOST, LS-TASC.
http://www.lstc.com/download

Memory Links

o Implicit: Memory notes
http://www.dynasupport.com/howtos/implicit/implicit-memory-notes

o LS-DYNA Support Environment variables
http://www.dynasupport.com/howtos/general/environment-variables

o LS-DYNA and d3VIEW Blog (a few words on memory settings)
http://blog2.d3view.com/a-few-words-on-memory-settings-in-ls-dyna/

o Convert Words to GB ie) memory=500MW (3.73GB)
http://deviceanalytics.com/memcalc.php

Retrieved from "https://sharcnet.ca/help/index.php?title=LSDYNA&oldid=17951"