Quick Start Guide

Step 1: Connect to the Cluster

Option A: Web browser — Go to https://servood.hpc.ncsu.edu (Open OnDemand) and log in with your Unity credentials.

Option B: Terminal — Open a terminal and run:

ssh YOUR_UNITY_ID@login.hpc.ncsu.edu

Enter your password and complete Duo authentication. See detailed login instructions.

Step 2: Navigate to Your Scratch Directory

cd /share/$(groups | awk '{print $1}')
mkdir -p $USER
cd $USER

Your scratch directory (/share/group_name/user_name) is where you run jobs and store working data. See storage documentation for details.

Step 3: Create a Batch Script

Create a file called test_job.sh:

#!/bin/bash
#SBATCH --job-name=test
#SBATCH --output=test.out.%j
#SBATCH --error=test.err.%j
#SBATCH --ntasks=1
#SBATCH --time=00:10:00

echo "Hello from $(hostname)"
echo "Job ID: $SLURM_JOB_ID"
echo "Working directory: $(pwd)"
date

Copy-paste the above into a file, or use: nano test_job.sh

Step 4: Submit the Job

sbatch test_job.sh

Slurm will respond with: Submitted batch job 123456

Step 5: Monitor Your Job

squeue -u $USER

You'll see your job listed with state PD (pending) or R (running).

Step 6: Check the Results

When the job completes, check the output file:

cat test.out.*

What's Next?

For a more comprehensive overview of the cluster, see Understanding the Cluster or the full Getting Started guide.