Using and Customizing Perl

Follow this link for more information on using Perl.

Using and Customizing Python

Follow this link for more information on using Python.

Using and Customizing R Packages

You can install your own R packages which is similar to using virtualenv with Python

1. Make directory to store packages
   $ mkdir -p ~/R/library
2. Tell R where the directory is by creating an environment file:
   $ echo 'R_LIBS=~/R/library/' >> ~/.Renviron
3. For example to install and load the package "ggplot2":
   $ module load R
   $ R
   ...
   > install.packages("ggplot2")
   > library(ggplot2)
4. After this you'll only need the library command to load your custom package
5. For more information:
   http://www.r-bloggers.com/installing-r-packages/

Using Matlab

There are three ways to run Matlab

1. The command line version using modules.  This is the most common as you will typically submit a job using PBS.
2. Graphical mode using the Ocelote Desktop of OnDemand
3. Using the Matlab integration with Python in a Jupyter notebook. 

Here are the details for method 1.

MATLAB performs its own hardware discovery and it might try to access all the cores and the memory of the node even if the full node wasn't allocated. That will result in scheduler killing the job. To prevent that the full Ocelote node of 28 cores and 168GB of memory should be allocated to run a MATLAB job.

Like any other application, MATLAB has to be loaded as a module before you can use it. To see all the installed versions of the MATLAB use command module avail matlab.

The typical procedure for performing calculations on UA HPC systems is to run your program non-interactively on compute nodes. The easiest way to run MATLAB non-interactively is to use input/output redirection. This method uses Linux operators < and > to point MATLAB to the input file and tell where to write the output (see the example script). The other method is to invoke MATLAB from the PBS script and execute specified statement using -r option. For details please refer to the manual page of matlab command:

https://www.mathworks.com/help/matlab/ref/matlablinux.html

#!/bin/bash
#PBS -N job_name
#PBS -W group_list=group_name
#PBS -q standard
#PBS -l select=1:ncpus=28:mem=168gb:pcmem=6gb
#PBS -l walltime=01:00:00
#PBS -l cput=28:00:00

cd $PBS_O_WORKDIR

module load matlab

matlab -nodisplay -nosplash < script_name.m > output.txt

The options -nodisplay and -nosplash in the example prevent MATLAB from opening elements of GUI. To view the full list of options for matlab command load the MATLAB module and type matlab -h in Linux prompt, or use the link above to the manual page on MathWorks website."

Spark

Apache Spark is a fast and general-purpose cluster computing system.  However it has not been installed for support in a multi-node environment as yet.  That functionality is planned for the future.  It provides high-level APIs in Java, Scala, Python and R, and an optimized engine that supports general execution graphs. It also supports a rich set of higher-level tools including Spark SQL for SQL and structured data processing, MLlib for machine learning, GraphX for graph processing, and Spark Streaming.

There are some simple tests here.

Compilers

• El Gato  

  • The principles are similar for ElGato except that the intel and intel-mpi compilers are only available for the 2013 versions.

  • openmpi is available both for version 1.6.5 and version 1.8.1

  • El Gato has a separate web site with easy to follow instructions.

For AVX2 support, compile with the -xHOST option. Note that -xHOST alone does not enable aggressive optimization, so compilation with -O3 is also suggested. The -fast flag invokes -xHOST, but should be avoided since it also turns on interprocedural optimization (-ipo), which may cause problems in some instances.

For GNU compilers, AVX support is only available in version 4.6 or later.  For AVX support, compile with -mavx

Image Removed

Image Removed

Image Removed

Image Removed

Image Removed

Image Removed

Image Removed