Skip to content
Snippets Groups Projects
Commit 5dcd0a4f authored by Lukáš Krupčík's avatar Lukáš Krupčík
Browse files

add

parent 9a0dfe83
No related branches found
Tags
4 merge requests!368Update prace.md to document the change from qprace to qprod as the default...,!367Update prace.md to document the change from qprace to qprod as the default...,!366Update prace.md to document the change from qprace to qprod as the default...,!323extended-acls-storage-section
Pipeline #
Showing
with 52 additions and 76 deletions
...@@ -63,7 +63,7 @@ echo Machines$hl ...@@ -63,7 +63,7 @@ echo Machines$hl
Header of the pbs file (above) is common and description can be find Header of the pbs file (above) is common and description can be find
on [this on [this
site](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution). site](../../resource-allocation-and-job-execution/job-submission-and-execution.html).
SVS FEM recommends to utilize sources by keywordsnodes, ppn. These SVS FEM recommends to utilize sources by keywordsnodes, ppn. These
keywords allows to address directly the number of nodes (computers) and keywords allows to address directly the number of nodes (computers) and
cores (ppn) which will be utilized in the job. Also the rest of code cores (ppn) which will be utilized in the job. Also the rest of code
...@@ -81,10 +81,6 @@ Licensed products are the followingaa_r ...@@ -81,10 +81,6 @@ Licensed products are the followingaa_r
Multiphysics)-**Commercial.** Multiphysics)-**Commercial.**
[<span id="result_box" class="short_text"><span class="hps">More</span> [<span id="result_box" class="short_text"><span class="hps">More</span>
<span class="hps">about licensing</span> <span <span class="hps">about licensing</span> <span
class="hps">here</span></span>](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/licensing) class="hps">here</span></span>](licensing.html)
...@@ -51,7 +51,7 @@ NCORES=`wc -l $PBS_NODEFILE |awk '{print $1}'` ...@@ -51,7 +51,7 @@ NCORES=`wc -l $PBS_NODEFILE |awk '{print $1}'`
Header of the pbs file (above) is common and description can be find Header of the pbs file (above) is common and description can be find
on [this on [this
site](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution). site](../../resource-allocation-and-job-execution/job-submission-and-execution.html).
[SVS FEM](http://www.svsfem.cz) recommends to utilize [SVS FEM](http://www.svsfem.cz) recommends to utilize
sources by keywordsnodes, ppn. These keywords allows to address sources by keywordsnodes, ppn. These keywords allows to address
directly the number of nodes (computers) and cores (ppn) which will be directly the number of nodes (computers) and cores (ppn) which will be
...@@ -221,11 +221,11 @@ utility should be run ...@@ -221,11 +221,11 @@ utility should be run
ANSLIC_ADMIN Utility will be run ANSLIC_ADMIN Utility will be run
![](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/Fluent_Licence_1.jpg) ![](Fluent_Licence_1.jpg)
![](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/Fluent_Licence_2.jpg) ![](Fluent_Licence_2.jpg)
![](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/Fluent_Licence_3.jpg) ![](Fluent_Licence_3.jpg)
...@@ -234,8 +234,4 @@ list. ...@@ -234,8 +234,4 @@ list.
![](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/Fluent_Licence_4.jpg) ![](Fluent_Licence_4.jpg)
...@@ -70,7 +70,7 @@ echo Machines$hl ...@@ -70,7 +70,7 @@ echo Machines$hl
<span>Header of the pbs file (above) is common and description can be <span>Header of the pbs file (above) is common and description can be
find on </span>[this find on </span>[this
site](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution)<span>. site](../../resource-allocation-and-job-execution/job-submission-and-execution.html)<span>.
[SVS FEM](http://www.svsfem.cz) recommends to utilize [SVS FEM](http://www.svsfem.cz) recommends to utilize
sources by keywordsnodes, ppn. These keywords allows to address sources by keywordsnodes, ppn. These keywords allows to address
directly the number of nodes (computers) and cores (ppn) which will be directly the number of nodes (computers) and cores (ppn) which will be
...@@ -83,7 +83,3 @@ file has to be specified. Input file has to be defined by common LS-DYNA ...@@ -83,7 +83,3 @@ file has to be specified. Input file has to be defined by common LS-DYNA
.**k** file which is attached to the ansys solver via parameter i= .**k** file which is attached to the ansys solver via parameter i=
<span><span> </span></span> <span><span> </span></span>
...@@ -59,7 +59,7 @@ echo Machines$hl ...@@ -59,7 +59,7 @@ echo Machines$hl
Header of the pbs file (above) is common and description can be find on Header of the pbs file (above) is common and description can be find on
[this [this
site](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution). site](../../resource-allocation-and-job-execution/job-submission-and-execution.html).
[SVS FEM](http://www.svsfem.cz) recommends to utilize [SVS FEM](http://www.svsfem.cz) recommends to utilize
sources by keywordsnodes, ppn. These keywords allows to address sources by keywordsnodes, ppn. These keywords allows to address
directly the number of nodes (computers) and cores (ppn) which will be directly the number of nodes (computers) and cores (ppn) which will be
...@@ -77,9 +77,5 @@ Multiphysics)-**Commercial**, aa_r_dy (ANSYS **Academic** ...@@ -77,9 +77,5 @@ Multiphysics)-**Commercial**, aa_r_dy (ANSYS **Academic**
AUTODYN)<span> AUTODYN)<span>
[<span id="result_box" class="short_text"><span class="hps">More</span> [<span id="result_box" class="short_text"><span class="hps">More</span>
<span class="hps">about licensing</span> <span <span class="hps">about licensing</span> <span
class="hps">here</span></span>](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/licensing) class="hps">here</span></span>](licensing.html)
</span> </span>
...@@ -16,7 +16,7 @@ of license is realized on command line respectively directly in user's ...@@ -16,7 +16,7 @@ of license is realized on command line respectively directly in user's
pbs file (see individual products). [<span id="result_box" pbs file (see individual products). [<span id="result_box"
class="short_text"><span class="hps">More</span> <span class="hps">about class="short_text"><span class="hps">More</span> <span class="hps">about
licensing</span> <span licensing</span> <span
class="hps">here</span></span>](https://docs.it4i.cz/anselm-cluster-documentation/software/ansys/licensing) class="hps">here</span></span>](licensing.html)
To load the latest version of any ANSYS product (Mechanical, Fluent, To load the latest version of any ANSYS product (Mechanical, Fluent,
CFX, MAPDL,...) load the module: CFX, MAPDL,...) load the module:
...@@ -30,7 +30,3 @@ If user needs to work in interactive regime we recommend to configure ...@@ -30,7 +30,3 @@ If user needs to work in interactive regime we recommend to configure
the RSM service on the client machine which allows to forward the the RSM service on the client machine which allows to forward the
solution to the Anselm directly from the client's Workbench project solution to the Anselm directly from the client's Workbench project
(see ANSYS RSM service). (see ANSYS RSM service).
...@@ -51,7 +51,7 @@ module load lsdyna ...@@ -51,7 +51,7 @@ module load lsdyna
Header of the pbs file (above) is common and description can be find Header of the pbs file (above) is common and description can be find
on [this on [this
site](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution). site](../../resource-allocation-and-job-execution/job-submission-and-execution.html).
[SVS FEM](http://www.svsfem.cz) recommends to utilize [SVS FEM](http://www.svsfem.cz) recommends to utilize
sources by keywordsnodes, ppn. These keywords allows to address sources by keywordsnodes, ppn. These keywords allows to address
directly the number of nodes (computers) and cores (ppn) which will be directly the number of nodes (computers) and cores (ppn) which will be
...@@ -62,7 +62,3 @@ Working directory has to be created before sending pbs job into the ...@@ -62,7 +62,3 @@ Working directory has to be created before sending pbs job into the
queue. Input file should be in working directory or full path to input queue. Input file should be in working directory or full path to input
file has to be specified. Input file has to be defined by common LS-DYNA file has to be specified. Input file has to be defined by common LS-DYNA
**.k** file which is attached to the LS-DYNA solver via parameter i= **.k** file which is attached to the LS-DYNA solver via parameter i=
...@@ -2,3 +2,4 @@ ...@@ -2,3 +2,4 @@
...@@ -61,9 +61,9 @@ parallelization only. This can be achieved by passing option <span ...@@ -61,9 +61,9 @@ parallelization only. This can be achieved by passing option <span
class="monospace">mpiprocs=16:ompthreads=1</span> to PBS. class="monospace">mpiprocs=16:ompthreads=1</span> to PBS.
You are advised to use the -d option to point to a directory in [SCRATCH You are advised to use the -d option to point to a directory in [SCRATCH
filesystem](https://docs.it4i.cz/anselm-cluster-documentation/storage-1/storage). filesystem](../../storage.html). Molpro can produce a
Molpro can produce a large amount of temporary data during its run, and large amount of temporary data during its run, and it is important that
it is important that these are placed in the fast scratch filesystem. these are placed in the fast scratch filesystem.
### Example jobscript ### Example jobscript
...@@ -89,3 +89,4 @@ it is important that these are placed in the fast scratch filesystem. ...@@ -89,3 +89,4 @@ it is important that these are placed in the fast scratch filesystem.
rm -rf /scratch/$USER/$PBS_JOBID rm -rf /scratch/$USER/$PBS_JOBID
...@@ -58,9 +58,10 @@ in the input file set the following directives : ...@@ -58,9 +58,10 @@ in the input file set the following directives :
- <span>MEMORY controls the amount of memory NWChem will use</span> - <span>MEMORY controls the amount of memory NWChem will use</span>
- <span>SCRATCH_DIR set this to a directory in [SCRATCH - <span>SCRATCH_DIR set this to a directory in [SCRATCH
filesystem](https://docs.it4i.cz/anselm-cluster-documentation/storage-1/storage#scratch) (or filesystem](../../storage.html#scratch) (or run the
run the calculation completely in a scratch directory). For certain calculation completely in a scratch directory). For certain
calculations, it might be advisable to reduce I/O by forcing calculations, it might be advisable to reduce I/O by forcing
"direct" mode, eg. "scf direct"</span> "direct" mode, eg. "scf direct"</span>
...@@ -25,8 +25,7 @@ Intel Compilers ...@@ -25,8 +25,7 @@ Intel Compilers
For information about the usage of Intel Compilers and other Intel For information about the usage of Intel Compilers and other Intel
products, please read the [Intel Parallel products, please read the [Intel Parallel
studio](https://docs.it4i.cz/anselm-cluster-documentation/software/intel-suite) studio](intel-suite.html) page.
page.
GNU C/C++ and Fortran Compilers GNU C/C++ and Fortran Compilers
------------------------------- -------------------------------
...@@ -155,14 +154,13 @@ Java ...@@ -155,14 +154,13 @@ Java
---- ----
For information how to use Java (runtime and/or compiler), please read For information how to use Java (runtime and/or compiler), please read
the [Java the [Java page](java.html).
page](https://docs.it4i.cz/anselm-cluster-documentation/software/java).
nVidia CUDA nVidia CUDA
----------- -----------
For information how to work with nVidia CUDA, please read the [nVidia For information how to work with nVidia CUDA, please read the [nVidia
CUDA CUDA page](nvidia-cuda.html).
page](https://docs.it4i.cz/anselm-cluster-documentation/software/nvidia-cuda).
...@@ -86,7 +86,7 @@ $ module avail comsol ...@@ -86,7 +86,7 @@ $ module avail comsol
it is recommend to use COMSOL on the compute nodes via PBS Pro it is recommend to use COMSOL on the compute nodes via PBS Pro
scheduler. In order run the COMSOL Desktop GUI on Windows is recommended scheduler. In order run the COMSOL Desktop GUI on Windows is recommended
to use the [Virtual Network Computing to use the [Virtual Network Computing
(VNC)](resolveuid/11e53ad0d2fd4c5187537f4baeedff33).</span></span> (VNC)](https://docs.it4i.cz/anselm-cluster-documentation/software/comsol/resolveuid/11e53ad0d2fd4c5187537f4baeedff33).</span></span>
``` ```
$ xhost + $ xhost +
...@@ -150,9 +150,9 @@ COMSOL release. On Anselm 1 commercial ...@@ -150,9 +150,9 @@ COMSOL release. On Anselm 1 commercial
and the 5 educational and the 5 educational
(</span></span><span><span>**EDU**</span></span><span><span>) licenses (</span></span><span><span>**EDU**</span></span><span><span>) licenses
of LiveLink for MATLAB (please see the [ISV of LiveLink for MATLAB (please see the [ISV
Licenses](https://docs.it4i.cz/anselm-cluster-documentation/software/isv_licenses)) Licenses](isv_licenses.html)) are available. Following
are available. Following example shows how to start COMSOL model from example shows how to start COMSOL model from MATLAB via LiveLink in the
MATLAB via LiveLink in the interactive mode.</span></span> interactive mode.</span></span>
``` ```
$ xhost + $ xhost +
...@@ -205,3 +205,4 @@ path to input file has to be specified. The Matlab command option (-r ...@@ -205,3 +205,4 @@ path to input file has to be specified. The Matlab command option (-r
”mphstart”) created a connection with a COMSOL server using the default ”mphstart”) created a connection with a COMSOL server using the default
port number. port number.
...@@ -86,7 +86,7 @@ $ module avail comsol ...@@ -86,7 +86,7 @@ $ module avail comsol
it is recommend to use COMSOL on the compute nodes via PBS Pro it is recommend to use COMSOL on the compute nodes via PBS Pro
scheduler. In order run the COMSOL Desktop GUI on Windows is recommended scheduler. In order run the COMSOL Desktop GUI on Windows is recommended
to use the [Virtual Network Computing to use the [Virtual Network Computing
(VNC)](resolveuid/11e53ad0d2fd4c5187537f4baeedff33).</span></span> (VNC)](https://docs.it4i.cz/anselm-cluster-documentation/software/comsol/resolveuid/11e53ad0d2fd4c5187537f4baeedff33).</span></span>
``` ```
$ xhost + $ xhost +
...@@ -150,9 +150,9 @@ COMSOL release. On Anselm 1 commercial ...@@ -150,9 +150,9 @@ COMSOL release. On Anselm 1 commercial
and the 5 educational and the 5 educational
(</span></span><span><span>**EDU**</span></span><span><span>) licenses (</span></span><span><span>**EDU**</span></span><span><span>) licenses
of LiveLink for MATLAB (please see the [ISV of LiveLink for MATLAB (please see the [ISV
Licenses](https://docs.it4i.cz/anselm-cluster-documentation/software/isv_licenses)) Licenses](../isv_licenses.html)) are available.
are available. Following example shows how to start COMSOL model from Following example shows how to start COMSOL model from MATLAB via
MATLAB via LiveLink in the interactive mode.</span></span> LiveLink in the interactive mode.</span></span>
``` ```
$ xhost + $ xhost +
...@@ -205,3 +205,4 @@ path to input file has to be specified. The Matlab command option (-r ...@@ -205,3 +205,4 @@ path to input file has to be specified. The Matlab command option (-r
”mphstart”) created a connection with a COMSOL server using the default ”mphstart”) created a connection with a COMSOL server using the default
port number. port number.
...@@ -20,15 +20,14 @@ The intel debugger version 13.0 is available, via module intel. The ...@@ -20,15 +20,14 @@ The intel debugger version 13.0 is available, via module intel. The
debugger works for applications compiled with C and C++ compiler and the debugger works for applications compiled with C and C++ compiler and the
ifort fortran 77/90/95 compiler. The debugger provides java GUI ifort fortran 77/90/95 compiler. The debugger provides java GUI
environment. Use [X environment. Use [X
display](resolveuid/11e53ad0d2fd4c5187537f4baeedff33) display](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/resolveuid/11e53ad0d2fd4c5187537f4baeedff33)
for running the GUI. for running the GUI.
$ module load intel $ module load intel
$ idb $ idb
Read more at the [Intel Read more at the [Intel
Debugger](https://docs.it4i.cz/anselm-cluster-documentation/software/intel-suite/intel-debugger) Debugger](intel-suite/intel-debugger.html) page.
page.
Allinea Forge (DDT/MAP) Allinea Forge (DDT/MAP)
----------------------- -----------------------
...@@ -45,8 +44,7 @@ implementation. ...@@ -45,8 +44,7 @@ implementation.
$ forge $ forge
Read more at the [Allinea Read more at the [Allinea
DDT](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/allinea-ddt) DDT](debuggers/allinea-ddt.html) page.
page.
Allinea Performance Reports Allinea Performance Reports
--------------------------- ---------------------------
...@@ -62,7 +60,7 @@ help you improve the efficiency of your runs. Our license is limited to ...@@ -62,7 +60,7 @@ help you improve the efficiency of your runs. Our license is limited to
$ perf-report mpirun -n 64 ./my_application argument01 argument02 $ perf-report mpirun -n 64 ./my_application argument01 argument02
Read more at the [Allinea Performance Read more at the [Allinea Performance
Reports](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/allinea-performance-reports) Reports](debuggers/allinea-performance-reports.html)
page. page.
RougeWave Totalview RougeWave Totalview
...@@ -77,8 +75,7 @@ great complexity. ...@@ -77,8 +75,7 @@ great complexity.
$ module load totalview $ module load totalview
$ totalview $ totalview
Read more at the Read more at the [Totalview](debuggers/total-view.html)
[Totalview](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/total-view)
page. page.
Vampir trace analyzer Vampir trace analyzer
...@@ -90,8 +87,4 @@ Vampir is a GUI trace analyzer for traces in OTF format. ...@@ -90,8 +87,4 @@ Vampir is a GUI trace analyzer for traces in OTF format.
$ vampir $ vampir
Read more at Read more at
the [Vampir](https://docs.it4i.cz/salomon/software/debuggers/vampir) page. the [Vampir](../../salomon/software/debuggers/vampir.html) page.
...@@ -79,7 +79,7 @@ forwarding</span> enabled. This could mean using the -X in the ssh  ...@@ -79,7 +79,7 @@ forwarding</span> enabled. This could mean using the -X in the ssh 
Other options is to access login node using VNC. Please see the detailed Other options is to access login node using VNC. Please see the detailed
information on how to [use graphic user interface on information on how to [use graphic user interface on
Anselm](resolveuid/11e53ad0d2fd4c5187537f4baeedff33)<span Anselm](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/resolveuid/11e53ad0d2fd4c5187537f4baeedff33)<span
class="internal-link"></span>. class="internal-link"></span>.
From the login node an interactive session **with X windows forwarding** From the login node an interactive session **with X windows forwarding**
...@@ -99,8 +99,7 @@ Command line arguments to a program can be entered to the</span> ...@@ -99,8 +99,7 @@ Command line arguments to a program can be entered to the</span>
"Arguments<span class="Apple-converted-space">" </span><span "Arguments<span class="Apple-converted-space">" </span><span
style="text-alignstart; ">box.</span> style="text-alignstart; ">box.</span>
![](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/ddt1.png){.image-inline ![](ddt1.png)
width="451" height="513"}
To start the debugging directly without the submission window, user can To start the debugging directly without the submission window, user can
specify the debugging and execution parameters from the command line. specify the debugging and execution parameters from the command line.
...@@ -131,3 +130,4 @@ Debugging with Allinea DDT, Workshop conducted at LLNL by Allinea on May ...@@ -131,3 +130,4 @@ Debugging with Allinea DDT, Workshop conducted at LLNL by Allinea on May
...@@ -37,8 +37,7 @@ Usage ...@@ -37,8 +37,7 @@ Usage
Use the the perf-report wrapper on your (MPI) program. Use the the perf-report wrapper on your (MPI) program.
Instead of [running your MPI program the usual Instead of [running your MPI program the usual
way](https://docs.it4i.cz/anselm-cluster-documentation/software/mpi-1), way](../mpi-1.html), use the the perf report wrapper:
use the the perf report wrapper:
$ perf-report mpirun ./mympiprog.x $ perf-report mpirun ./mympiprog.x
...@@ -46,7 +45,7 @@ The mpi program will run as usual. The perf-report creates two ...@@ -46,7 +45,7 @@ The mpi program will run as usual. The perf-report creates two
additional files, in *.txt and *.html format, containing the additional files, in *.txt and *.html format, containing the
performance report. Note that [demanding MPI codes should be run within performance report. Note that [demanding MPI codes should be run within
the queue the queue
system](https://docs.it4i.cz/anselm-cluster-documentation/resource-allocation-and-job-execution/job-submission-and-execution). system](../../resource-allocation-and-job-execution/job-submission-and-execution.html).
Example Example
------- -------
...@@ -71,9 +70,9 @@ Now lets profile the code: ...@@ -71,9 +70,9 @@ Now lets profile the code:
$ perf-report mpirun ./mympiprog.x $ perf-report mpirun ./mympiprog.x
Performance report files Performance report files
[mympiprog_32p*.txt](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/mympiprog_32p_2014-10-15_16-56.txt) [mympiprog_32p*.txt](mympiprog_32p_2014-10-15_16-56.txt)
and and
[mympiprog_32p*.html](https://docs.it4i.cz/anselm-cluster-documentation/software/debuggers/mympiprog_32p_2014-10-15_16-56.html) [mympiprog_32p*.html](mympiprog_32p_2014-10-15_16-56.html)
were created. We can see that the code is very efficient on MPI and is were created. We can see that the code is very efficient on MPI and is
CPU bounded. CPU bounded.
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment