Added job scripts for JUWELS stage 2019a. Keras and Tensorflow are working...

Added job scripts for JUWELS stage 2019a. Keras and Tensorflow are working both independently and with Horovod. PyTorch code is generating dataset related errors that need to be investigated; possibly just a matter of updating the custom pre-downloaded-dataset handling code.

horovod/keras/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=2
+#SBATCH --ntasks=4
+#SBATCH --ntasks-per-node=4
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=HOROVOD_KERAS_MNIST
+#SBATCH --gres=gpu:4 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load MVAPICH2/2.3.1-GDR
+module load TensorFlow/1.13.1-GPU-Python-3.6.8
+module load Keras/2.2.4-GPU-Python-3.6.8
+module load Horovod/0.16.2-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py

horovod/pytorch/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=2
+#SBATCH --ntasks=4
+#SBATCH --ntasks-per-node=4
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=HOROVOD_PYTORCH_MNIST
+#SBATCH --gres=gpu:4 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load MVAPICH2/2.3.1-GDR
+module load PyTorch/1.1.0-GPU-Python-3.6.8
+module load torchvision/0.3.0-GPU-Python-3.6.8
+module load Horovod/0.16.2-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py

horovod/tensorflow/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=2
+#SBATCH --ntasks=4
+#SBATCH --ntasks-per-node=4
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=HOROVOD_TFLOW_MNIST
+#SBATCH --gres=gpu:4 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load MVAPICH2/2.3.1-GDR
+module load TensorFlow/1.13.1-GPU-Python-3.6.8
+module load Keras/2.2.4-GPU-Python-3.6.8
+module load Horovod/0.16.2-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py

keras/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=KERAS_MNIST
+#SBATCH --gres=gpu:1 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load TensorFlow/1.13.1-GPU-Python-3.6.8
+module load Keras/2.2.4-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py

pytorch/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=PYTORCH_MNIST
+#SBATCH --gres=gpu:1 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load PyTorch/1.1.0-GPU-Python-3.6.8
+module load torchvision/0.3.0-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py

tensorflow/submit_job_juwels_python3.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=TFLOW_MNIST
+#SBATCH --gres=gpu:1 --partition=develgpus
+#SBATCH --mail-type=ALL
+
+# Load the required modules
+module load GCC/8.3.0
+module load TensorFlow/1.13.1-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist.py