Shaheen III#
If you are familiar with HPC clusters and need a quick reference on the specifics of how to interact with KSL computational resources, you will find the relevant information here in a concise form. For details, please explore the other sections of the documentation starting from System Architecture.
Login#
To login you need to ssh
into the login node.
A ssh
client should be installed on your workstation/laptop.
For users with MacOS and Linux operating system, please open the Terminal
application paste command below replacing your username for Shaheen III.
For Windows users, you will need a application with ssh
client installed within it. Please follow instruction in this video tutorial . When logging in to Shaheen III, please replace the hostname with shaheen.hpc.kaust.edu.sa when following the steps prescribed in the tutorial.
Logging into Shaheen III#
Shaheen III has a total of 5 login nodes. login1
is reserved for system administration, and login2
to login5
are available for users to login to Shaheen III.
Note
In near future the hostname is going to change to more intuitive one as was the case with Shaheen II (shaheen.hpc.kaust.edu.sa
). This is expected to happen after the Shaheen II is decommissioned.
The following is an example of logging in on Shaheen III through hostname login2
:
ssh -X username@login2.hpc.kaust.edu.sa
Submitting your first Jobscripts#
All KSL systems use SLURM for scheduling jobs for batch processing.
Shaheen III example jobscripts#
On Shaheen III the example jobscripts below need to be submitted from /scratch/$USER
directory.
This is imperative because /home
directory is not mounted on compute nodes. Also /project
directory is read-only on compute node.
Note
Compute nodes in workq
on Shaheen III are allocated in exclusive mode. For a detailed description of available partitions please refer to Shaheen III.
The following is a sample jobscript cpu_shaheen3.slurm
to print hostnames of one AMD Genoa compute nodes of Shaheen III in workq
.
#!/bin/bash
#SBATCH --time=00:10:00
#SBATCH --partition=workq
#SBATCH --nodes=1
#SBATCH --ntasks=192
#SBATCH --hint=nomultithread
srun -n ${SLURM_NTASKS} --hint=nomultithread /bin/hostname
The above jobscript can now be submitted using the sbatch
command.
sbatch cpu_shaheen3.slurm
KSL has written a convenient utility called Jobscript Generator. Use this template to create a jobscript and copy-paste it in a file in your SSH terminal on Shaheen III or Ibex login nodes.
If you get an error in regarding account specification, please email with the your username and error and the jobscript.