#!/bin/bash
#PBS -q EarlyAppAccess
#PBS -l select=2
#PBS -l walltime=01:00:00
#PBS -A LatticeQCD_aesp_CNDA

export TZ='/usr/share/zoneinfo/US/Central'
export OMP_PROC_BIND=spread
export OMP_NUM_THREADS=3
unset OMP_PLACES

cd $PBS_O_WORKDIR

NNODES=`wc -l < $PBS_NODEFILE`
NRANKS=12         # Number of MPI ranks per node
NDEPTH=4          # Number of hardware threads per rank, spacing between MPI ranks on a node
NTHREADS=$OMP_NUM_THREADS # Number of OMP threads per rank, given to OMP_NUM_THREADS

NTOTRANKS=$(( NNODES * NRANKS ))

CMD="mpiexec -np 2 -ppn 1  -envall ./gpu_tile_compact.sh ./halo_mpi --mpi 2.1.1.1"
$CMD