Page Comparison

#!/bin/bash --login
#SBATCH --account=pawsey12345-gpujob-name=distribute_tf
#SBATCH --partition=gpu
#SBATCH --exclusive
#SBATCH --nodes=2    module  load tensorflow/rocm5.6-tf2.12  #If additional python packages have been#2 installednodes in user'sthis ownexample virtual
environment
VENV_PATH=/software/projects/pawsey12345/matilda/myenv/bin/activate

#Clear definition#SBATCH --exclusive            #All resources of the python script containing the tensorflow training case
PYTHON_SCRIPT=/software/projects/pawsey12345/matilda/matilda-machinelearning/models/01_horovod_mnist.py

#Launch for execution indicating resources to the srun command
srun -N 2 -n 16 -c 8 --gres=gpu:8 bash -c "source $VENV_PATH && python3 $PYTHON_SCRIPT node are exclusive to this job
#                              #8 GPUs per node (16 "allocation packs" in total for the job)
#SBATCH --time=00:05:00
#SBATCH --account=pawsey12345-gpu #IMPORTANT: use your own project and the -gpu suffix

#----
#Loading needed modules:
module load tensorflow/<version>
echo -e "\n\n#------------------------#"
module list

#----
#Printing the status of the given allocation
echo -e "\n\n#------------------------#"
echo "Printing from scontrol:"
scontrol show job ${SLURM_JOBID}

#----
#If additional python packages have been installed in user's own virtual environment
VENV_PATH=/software/projects/pawsey12345/matilda/myenv/bin/activate

#----
#Clear definition of the python script containing the tensorflow training case
PYTHON_SCRIPT=/software/projects/pawsey12345/matilda/matilda-machinelearning/models/01_horovod_mnist.py

#----
#TensorFlow settings if needed:
#  The following two variables control the real number of threads in Tensorflow code:
export TF_NUM_INTEROP_THREADS=1    #Number of threads for independent operations
export TF_NUM_INTRAOP_THREADS=1    #Number of threads within individual operations 

#----
#Execution
#Note: srun needs the explicit indication full parameters for use of resources in the job step.
#      These are independent from the allocation parameters (which are not inherited by srun)
#      Each task needs access to all the 8 available GPUs in the node where it's running.
#      So, no optimal binding can be provided by the scheduler.
#      Therefore, "--gpus-per-task" and "--gpu-bind" are not used.
#      Optimal use of resources is now responsability of the code.
#      "-c 8" is used to force allocation of 1 task per CPU chiplet. Then, the REAL number of threads
#         for the code SHOULD be defined by the environment variables above.
echo -e "\n\n#------------------------#"
echo "Code execution:"
srun -N 2 -n 16 -c 8 --gres=gpu:8 bash -c "source $VENV_PATH &&  python3 $PYTHON_SCRIPT"

#----
#Printing information of finished job steps:
echo -e "\n\n#------------------------#"
echo "Printing information of finished jobs steps using sacct:"
sacct -j ${SLURM_JOBID} -o jobid%20,Start%20,elapsed%20

#----
#Done
echo -e "\n\n#------------------------#"
echo "Done"