This lesson is still being designed and assembled (Pre-Alpha version)

DeapSECURE module 6: Parallel and High-Performance Computing: Setup

Setting Up Files

Hands-on Files on Turing

Hands-on files are located on Turing on this subdirectory:

/scratch-lustre/DeapSECURE/module-par/Exercises

Copy the entire directory tree to your ~/CItraining/module-par:

$ mkdir -p ~/CItraining/par

$ cd ~/CItraining/par

$ cp -pr /scratch-lustre/DeapSECURE/module-par/Exercises/. .

(Don’t forget the last period!)

Obtaining Compute Resource

In this workshop we will experiment with different configurations for process placement. We will need to get a set of compute cores all from the same node for one configuration, and also cores from different compute nodes.

To request four cores from the same node do:

salloc -n 4 -N 1

To request CPU cores from different nodes do:

salloc -n 4 --ntasks-per-node=1

Setting Up Environment

Modules needed for today’s experiments are:

module use /scratch-lustre/DeapSECURE/lmod
module load DeapSECURE
module load icc/18 impi/18
module load python/3.6
module load mpi4py

We created a shell command file named parallel-prog-env in your hands-on directory to ease reloading of these modules later on. To take advantage of this, please issue this command in the same directory as before:

$ source parallel-prog-env

Do this only once per shell session, right after you obtain a compute core.

Thank you for your participation in the DeapSECURE workshops! We hope that these workshops have enriched your knowledge on the computational capabilities that you can use for cybersecurity work.

Please share your thoughts in the feedback: