Initial Setup (flory)

In High-Performance computing (HPC) there are several compiler and message passing systems for users to choose. Selecting a combination of compiler and message passing systems for a particular computational job is an involved process that depends upon the intricacies of the calculation and the specifications of the HPC system. This initial setup tutorial will guide the user in setting up a new account to use the most common combination of compiler and message passing system: GNU Compiler Collection, and Open MPI.

Set Defaults

Most of the scripts and programs are located in the

{{HPC-Base-Dir}}

Parameter unnamed not defined. For correct usage see template's documention.

path and it's sub-directories. For the curious, to see what is currently in

{{HPC-Base-Dir}}

Parameter unnamed not defined. For correct usage see template's documention.

/bin

, use the ls command. You should see something like this:

user $ls

{{HPC-Base-Dir}}

Parameter unnamed not defined. For correct usage see template's documention.

/bin

lmp-config  pw.x-config  qe-config  qpeek  selector-compiler  selector-mpi

The selector-compiler and selector-mpi scripts will be used for setting up a new account.

GNU Compiler Collection

To setup the GNU Compiler Collection for the currently running environment:

user $source

{{HPC-Base-Dir}}

Parameter unnamed not defined. For correct usage see template's documention.

/bin/selector-compiler -g

Setup GNU compiler and libraries.

Open MPI

To setup Open MPI that has been compiled with the GNU compiler for the currently running environment:

user $source

{{HPC-Base-Dir}}

Parameter unnamed not defined. For correct usage see template's documention.

/bin/selector-mpi -o

Set MPI to Open MPI with GNU compiler.

Note
The settings so far affect only the currently running shell and will be lost when logging back in at a later date. To make changes persistent across logins, see the next section.

Make Changes Persistent and Global

Before a job can be successfully submitted to the cluster it is required to have:

• Persistent settings across logins
• Same settings on all nodes of cluster

To make the compiler and message passing system settings persistent across logins and all nodes we need to edit the .bashrc file in the home directory. The directions below will be for using the nano editor, but you are free to use whatever text editor you are most comfortable with.

Use the following to start editing the file:

user $nano -w ${HOME}/.bashrc

If this is your first time editing the .bashrc file, it should look something like this:

FILE ${HOME}/.bashrc

# .bashrc

# Source global definitions
if [ -f /etc/bashrc ]; then
	. /etc/bashrc
fi

# User specific aliases and functions

We need to add the two commands we typed earlier (here and here) to the bottom of this file. It should look like this:

FILE ${HOME}/.bashrc(after editing)

# .bashrc

# Source global definitions
if [ -f /etc/bashrc ]; then
	. /etc/bashrc
fi

# User specific aliases and functions
source /home/bgo/shared/bin/selector-compiler -g -q
source /home/bgo/shared/bin/selector-mpi -o -q

You'll notice that the two commands are slightly different than what we used before; they both have a -q added. The -q tells the commands to be 'quiet' and not show any output. You can omit the -q from each command if you'd like to be reminded of what compiler and message passing system is set during each login.

To save the changes, use Ctrl+O, then hit Enter to accept the file name. Use Ctrl+X to exit nano.

Now every time you login, the GNU compiler and Open MPI compiled with the GNU compiler will be the default.