The information above is a notebook launched on zeus.pawsey.org.au. Ensure that you look at your output to select the correct machine.

#!/bin/bash -l
# This example is for GPUs on Setonix
# Allocate slurm resources, edit as necessary
#SBATCH --account=[your-project-name]
# Here we request the appropriate GPU partition on a system
#SBATCH --partition=gpu
# Be aware that the request for GPU resources may change in later versions of slurm
#SBATCH --nodes=1
#SBATCH --gpus-per-node=1
#SBATCH --time=02:00:00
#SBATCH --job-name=jupyter_notebook
#SBATCH --export=NONE

# Set our working directory
# This is the directory we'll mount to /home/jovyan in the container
# Should be in a writable path with some space, like /scratch
jupyterDir="${MYSCRATCH}/jupyter-dir"

# Set the image and tag we want to use
image="docker://jupyter/datascience-notebook:latest"

# You should not need to edit the lines below

# Prepare the working directory
mkdir -p ${jupyterDir}
cd ${jupyterDir}

# Get the image filename
imagename=${image##*/}
imagename=${imagename/:/_}.sif

# Get the hostname
# We'll set up an SSH tunnel to connect to the Juypter notebook server
host=$(hostname)

# Set the port for the SSH tunnel
# This part of the script uses a loop to search for available ports on the node;
# this will allow multiple instances of GUI servers to be run from the same host node
port="8888"
pfound="0"
while [ $port -lt 65535 ] ; do
  check=$( ss -tuna | awk '{print $4}' | grep ":$port *" )
  if [ "$check" == "" ] ; then
    pfound="1"
    break
  fi
  : $((++port))
done
if [ $pfound -eq 0 ] ; then
  echo "No available communication port found to establish the SSH tunnel."
  echo "Try again later. Exiting."
  exit
fi

# Load Singularity
module load singularity/3.11.4-nompi

# Load ROCm and set environment variable for Singularity
module load rocm/5.2.3
export SINGULARITYENV_CUDA_HOME=$CUDA_HOME

# Pull our image in a folder
singularity pull $imagename $image

echo "*****************************************************"
echo "Setup - from your laptop do:"
echo "ssh -N -f -L ${port}:${host}:${port} $USER@$PAWSEY_CLUSTER.pawsey.org.au"
echo "*****"
echo "The launch directory is: $jupyterDir"
echo "*****************************************************"
echo ""
echo "*****************************************************"
echo "Terminate - from your laptop do:"
echo "kill \$( ps x | grep 'ssh.*-L *${port}:${host}:${port}' | awk '{print \$1}' )"
echo "*****************************************************"
echo ""
 
# Launch our container
# and mount our working directory to /home/jovyan in the container
# and bind the run time directory to our home directory
singularity exec --nv -C \
  -B ${jupyterDir}:/home/joyvan \
  -B ${jupyterDir}:$HOME \
  ${imagename} \
  jupyter notebook \
  --no-browser \
  --port=${port} --ip=0.0.0.0 \
  --notebook-dir=${jupyterDir}

# key GPU library
from numba import cuda
import numpy as np

# define some kernels
@cuda.jit
def add_kernel(x, y, out):
    idx = cuda.grid(1)
    out[idx] = x[idx] + y[idx]

n = 4096
x = np.arange(n).astype(np.int32) # [0...4095] on the host
y = np.ones_like(x)               # [1...1] on the host
out = np.zeros_like(x)

# cuda commands to copy memory to the device 
d_x = cuda.to_device(x)
d_y = cuda.to_device(y)
d_out = cuda.to_device(out)

# run kernel
threads_per_block = 128
blocks_per_grid = 32
add_kernel[blocks_per_grid, threads_per_block](d_x, d_y, d_out)
cuda.synchronize()

# output result 
print(d_out.copy_to_host()) # Should be [1...4096]