Add example job scripts

gpaw/README.md

@@ -96,7 +96,7 @@ Input file: [benchmark/carbon-nanotube/input.py](benchmark/silicon-cluster/input
 No special command line options or environment variables are needed to run the
 benchmarks on most systems. One can simply say e.g.
 ```
-mpirun -np 256 gpaw-python input.py
+srun gpaw-python input.py
 ```
 
 #### Special case: KNC
@@ -119,5 +119,4 @@ GPAW_PPN=12 GPAW_OFFLOAD=1 mpirun -np 256 -bootstrap slurm \
 #### Examples
 
 Example [job scripts](scripts/) (`scripts/job-*.sh`) are provided for
-different systems together with related machine specifications
-(`scripts/specs.*`) that may offer a helpful starting point.
+different PRACE systems that may offer a helpful starting point.

gpaw/scripts/job-davide.sh

+#!/bin/bash
+#SBATCH -J 4x4
+#SBATCH -p dvd_usr_prod
+#SBATCH --nodes=4
+#SBATCH --ntasks-per-node=4
+#SBATCH --cpus-per-task=4
+#SBATCH --time=00:30:00
+#SBATCH --account=<PROJECT_ID>
+#SBATCH --gres=gpu:tesla:4
+#SBATCH --exclusive
+
+cd $SLURM_SUBMIT_DIR
+
+source $CINECA_SCRATCH/lib/gpaw-cuda/load.sh
+
+srun gpaw-python input.py
+

gpaw/scripts/job-juwels.sh

+#!/bin/bash -x
+#SBATCH -J 4x48
+#SBATCH --account=<PROJECT_ID>
+#SBATCH --nodes=4
+#SBATCH --ntasks-per-node=48
+#SBATCH --time=00:30:00
+#SBATCH --partition=batch
+
+source $HOME/lib/gpaw-1.1.0/load.sh
+
+srun gpaw-python input.py
+

gpaw/scripts/job-marenostrum.sh

+#!/bin/bash -x
+#SBATCH -J 4x48
+#SBATCH --nodes=4
+#SBATCH --ntasks-per-node=48
+#SBATCH --time=00:30:00
+#SBATCH --qos=prace
+
+source $HOME/project/lib/gpaw-1.1.0/load.sh
+
+srun gpaw-python input.py
+

gpaw/scripts/job-piz-daint.sh

+#!/bin/bash -l
+#SBATCH -J 4x1
+#SBATCH --nodes=4
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=12
+#SBATCH --time=00:30:00
+#SBATCH --partition=normal
+#SBATCH --constraint=gpu
+#SBATCH --gres=gpu:1
+
+export OMP_NUM_THREADS=1
+export CRAY_CUDA_MPS=1
+export MPICH_NO_GPU_DIRECT=1
+
+source $SCRATCH/lib/gpaw-cuda/load.sh
+
+srun gpaw-python input.py
+