#!/bin/bash
#PBS -S /bin/bash
#PBS -N AF2
#PBS -o $PBS_JOBID.out
#PBS -e $PBS_JOBID.err

#Half node for a sequence < 1000 residues
#Full node otherwise and for the multimer version.
#PBS -l nodes=1:ppn=16
#PBS -l walltime=24:00:00
#PBS -A simlab_project
#PBS -q alphafold_1n

#script version 20.10.2022

### FOR EVERYTHING BELOW, I ADVISE YOU TO MODIFY THE USER-part ONLY ###
WORKDIR="/"
NUM_NODES=$(cat $PBS_NODEFILE|uniq|wc -l)
if [ ! -n "$PBS_O_HOME" ] || [ ! -n "$PBS_JOBID" ]; then
        echo "At least one variable is needed but not defined. Please touch your manager about."
        exit 1
else
        if [ $NUM_NODES -le 1 ]; then
                WORKDIR+="scratch/"
                export WORKDIR+=$(echo $PBS_O_HOME |sed 's#.*/\(home\|workdir\)/\(.*_team\)*.*#\2#g')"/$PBS_JOBID/"
                mkdir $WORKDIR
                rsync -ap $PBS_O_WORKDIR/ $WORKDIR/

                # if you need to check your job output during execution (example: each hour) you can uncomment the following line
                # /shared/scripts/ADMIN__auto-rsync.example 3600 &
        else
                export WORKDIR=$PBS_O_WORKDIR
        fi
fi

echo "your current dir is: $PBS_O_WORKDIR"
echo "your workdir is: $WORKDIR"
echo "number of nodes: $NUM_NODES"
echo "number of cores: "$(cat $PBS_NODEFILE|wc -l)
echo "your execution environment: "$(cat $PBS_NODEFILE|uniq|while read line; do printf "%s" "$line "; done)

cd $WORKDIR

# If you're using only one node, it's counterproductive to use IB network for your MPI process communications
if [ $NUM_NODES -eq 1 ]; then
        export PSM_DEVICES=self,shm
        export OMPI_MCA_mtl=^psm
        export OMPI_MCA_btl=shm,self
else
# Since we are using a single IB card per node which can initiate only up to a maximum of 16 PSM contexts
# we have to share PSM contexts between processes
# CIN is here the number of cores in node
        CIN=$(cat /proc/cpuinfo | grep -i processor | wc -l)
        if [ $(($CIN/16)) -ge 2 ]; then
                PPN=$(grep $HOSTNAME $PBS_NODEFILE|wc -l)
                if [ $CIN -eq 40 ]; then
                        export PSM_SHAREDCONTEXTS_MAX=$(($PPN/4))
                elif [ $CIN -eq 32 ]; then
                        export PSM_SHAREDCONTEXTS_MAX=$(($PPN/2))
                else
                        echo "This computing node is not supported by this script"
                fi
                echo "PSM_SHAREDCONTEXTS_MAX defined to $PSM_SHAREDCONTEXTS_MAX"
        else
                echo "no PSM_SHAREDCONTEXTS_MAX to define"
        fi
fi

function get_gpu-ids() {
        if [ $PBS_NUM_PPN -eq $(cat /proc/cpuinfo | grep -cE "^processor.*:") ]; then
                echo "0,1" && return
        fi

        if [ -e /dev/cpuset/torque/$PBS_JOBID/cpus ]; then
                FILE="/dev/cpuset/torque/$PBS_JOBID/cpus"
        elif [ -e /dev/cpuset/torque/$PBS_JOBID/cpuset.cpus ]; then
                FILE="/dev/cpuset/torque/$PBS_JOBID/cpuset.cpus"
        else
                FILE=""
        fi

        if [ -e $FILE ]; then
                if [ $(cat $FILE | sed -r 's/^([0-9]).*$/\1/') -eq 0 ]; then
                        echo "0" && return
                else
                        echo "1" && return
                fi
        else
                echo "0,1" && return
        fi
}

gpus=$(get_gpu-ids)


## USER Part
module load gcc/8.3.0
module load miniconda-py3/latest

conda activate alphafold

nb_cores=$(cat $PBS_NODEFILE|wc -l)

#Run
cd $WORKDIR/

AF2_path="/scratch-nv/software/alphafold/alphafold_repo"
AF2_db_path="/scratch-nv/software/alphafold/alphafold_db"

d1=`date +%s`
echo $(date)


# Use either one by uncommenting the command line.
# Just change the name of the fasta file.
#Monomer
#bash ${AF2_path}/run_alphafold.sh -n $nb_cores -a $gpus -d ${AF2_db_path} -o . -f myfasta.fasta -t 2021-12-01

#Multimer
#bash ${AF2_path}/run_alphafold.sh -n $nb_cores -a $gpus -d ${AF2_db_path} -o . -f sequences.fasta -t 2021-11-01 -m multimer



d2=$(date +%s)
echo $(date)

diff=$((($d2 - $d1)/60))
echo "Time spent (min) : ${diff}"

## DO NOT MODIFY THE PART OF SCRIPT: you will be accountable for any damage you cause
# At the term of your job, you need to get back all produced data synchronizing workdir folder with you starting job folder and delete the temporary one (workdir)
if [ $NUM_NODES -le 1 ]; then
        cd $PBS_O_WORKDIR
        rsync -ap $WORKDIR/ $PBS_O_WORKDIR/
        rm -rf $WORKDIR
fi
## END-DO