Added/updated job scripts for data-distributed training.

horovod_data_distributed/submit_job_jureca.sh

+#!/usr/bin/env bash
+
+# Slurm job configuration
+#SBATCH --nodes=2
+#SBATCH --ntasks=8
+#SBATCH --ntasks-per-node=4
+#SBATCH --output=output_%j.out
+#SBATCH --error=error_%j.er
+#SBATCH --time=00:10:00
+#SBATCH --job-name=HVD_DATA_DIST
+#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 Horovod/0.16.2-GPU-Python-3.6.8
+
+# Run the program
+srun python -u mnist_data_distributed.py

horovod_data_distributed/submit_job_juron.sh

+#!/usr/bin/env bash
+
+#BSUB -q normal
+#BSUB -W 10
+#BSUB -n 8
+#BSUB -R "span[ptile=4]"
+#BSUB -gpu "num=4"
+#BSUB -e "error.%J.er"
+#BSUB -o "output_%J.out"
+#BSUB -J HVD_DATA_DIST
+
+# Load the required modules
+module load python/3.6.1
+module load tensorflow/1.12.0-gcc_5.4.0-cuda_10.0.130
+module load horovod/0.15.2
+
+# Run the program
+mpirun -bind-to none \
+        -map-by slot \
+        -x NCCL_DEBUG=INFO \
+        -x LD_LIBRARY_PATH \
+        -x PATH \
+        -mca pml ob1 \
+        -mca btl ^openib \
+        python -u mnist_data_distributed.py

horovod_data_distributed/submit_job_juwels.sh

@@ -17,8 +17,5 @@ module load MVAPICH2/2.3.1-GDR
 module load TensorFlow/1.13.1-GPU-Python-3.6.8
 module load Horovod/0.16.2-GPU-Python-3.6.8
 
-# Source the virtual environment
-source activate venv_dl_hpc4ns/bin/activate
-
 # Run the program
 srun python -u mnist_data_distributed.py