2 files changed, 21 insertions, 9 deletions
diff --git a/Examples/batchScripts/batch_cori.sh b/Examples/batchScripts/batch_cori.sh
index bfadc6e0a..e6cd5e1ef 100644
--- a/Examples/batchScripts/batch_cori.sh
+++ b/Examples/batchScripts/batch_cori.sh
@@ -4,19 +4,30 @@
 #SBATCH -t 01:00:00
 #SBATCH -q regular
 #SBATCH -C knl
+#SBATCH -S 4
 #SBATCH -J <job name>
 #SBATCH -A <allocation ID>
 #SBATCH -e error.txt
 #SBATCH -o output.txt
 
-export OMP_NUM_THREADS=8
 export OMP_PLACES=threads
 export OMP_PROC_BIND=spread
 
-# Typically use OMP_NUM_THREADS=8 and 8 MPI ranks per node,
-# without hyperthreading (HT=1)
-srun --cpu_bind=cores -n 16 -c 32 <path/to/executable> <input file>
-# 4 OpenMP threads, 16 MPI ranks per node, HT=1
-# srun --cpu_bind=cores -n 32 -c 16 <path/to/executable> <inputs file>
-# 8 OpenMP threads, 16 MPI ranks per node, HT=2
-# srun --cpu_bind=cores -n 32 -c 16 <path/to/executable> <inputs file>
+# KNLs have 4 hyperthreads max
+export CORI_MAX_HYPETHREAD_LEVEL=4
+# We use 64 cores out of the 68 available on Cori KNL,
+# and leave 4 to the system (see "#SBATCH -S 4" above).
+export CORI_NCORES_PER_NODE=64
+
+# Typically use 8 MPI ranks per node without hyperthreading,
+# i.e., OMP_NUM_THREADS=8
+export WARPX_NMPI_PER_NODE=8
+export WARPX_HYPERTHREAD_LEVEL=1
+
+# Compute OMP_NUM_THREADS and the thread count (-c option)
+export CORI_NHYPERTHREADS_MAX=$(( ${CORI_MAX_HYPETHREAD_LEVEL} * ${CORI_NCORES_PER_NODE} ))
+export WARPX_NTHREADS_PER_NODE=$(( ${WARPX_HYPERTHREAD_LEVEL} * ${CORI_NCORES_PER_NODE} ))
+export OMP_NUM_THREADS=$(( ${WARPX_NTHREADS_PER_NODE} / ${WARPX_NMPI_PER_NODE} ))
+export WARPX_THREAD_COUNT=$(( ${CORI_NHYPERTHREADS_MAX} / ${WARPX_NMPI_PER_NODE} ))
+
+srun --cpu_bind=cores -n $(( ${SLURM_JOB_NUM_NODES} * ${WARPX_NMPI_PER_NODE} )) -c ${WARPX_THREAD_COUNT} <path/to/executable> <input file>
diff --git a/Examples/batchScripts/batch_summit.sh b/Examples/batchScripts/batch_summit.sh
index a2679510f..002660b91 100644
--- a/Examples/batchScripts/batch_summit.sh
+++ b/Examples/batchScripts/batch_summit.sh
@@ -12,4 +12,5 @@ module load cuda
 omp=1
 export OMP_NUM_THREADS=${omp}
 
-jsrun -n 2 -a 6 -g 6 -c 6 --bind=packed:${omp} <path/to/executable> <input file> > output.txt
+num_nodes=$(( $(printf '%s\n' ${LSB_HOSTS} | sort -u | wc -l) - 1 ))
+jsrun -n ${num_nodes} -a 6 -g 6 -c 6 --bind=packed:${omp} <path/to/executable> <input file> > output.txt