#!/bin/bash                                                                                                                                                                                         
#SBATCH --nodes=1                    # Number of nodes
#SBATCH --ntasks-per-node=4          # Number of tasks per node
#SBATCH --gres=gpu:4                 # Allocate GPUs
#SBATCH --cpus-per-task=10           # Number of cores for each task (important to get all memory)
#SBATCH --hint=nomultithread         # Disable hyperthreading
#SBATCH --time=00:10:00              # Expected job duration (HH:MM:SS)
#SBATCH --job-name=qmcpack_multi_gpu # Jobname 
#SBATCH --output=%x.o%j              # Output file %x is the jobname, %j the jobid
#SBATCH --error=%x.o%j               # Error file
#SBATCH --time=10:00:00              # Expected runtime HH:MM:SS (max 100h for V100, 20h for A100)
##
## Please, refer to comments below for
## more information about these 4 last options.
##SBATCH --account=<account>@v100   # To specify gpu accounting: <account> = echo $IDRPROJ
##SBATCH --partition=<partition>    # To specify partition (see IDRIS web site for more info)
##SBATCH --qos=qos_gpu-dev          # Uncomment for job requiring less than 2 hours
##SBATCH --qos=qos_gpu-t4           # Uncomment for job requiring more than 20 hours (up to 16 GPU, V100 only)

 
# Cleans out the modules loaded in interactive and inherited by default
module purge

# Load needed modules
module load gcc/8.3.0
module load cuda/10.1.1
module load qmcpack/3.7.0-mpi-cuda

# echo commands
set -x

cd ${SLURM_SUBMIT_DIR}/dmc
   
# Execute code with the right binding. 1GPU per task
srun /gpfslocalsup/pub/idrtools/bind_gpu.sh qmcpack C2CP250_dmc_x2.in.xml