run parallel distributed in cluster
Hi all,
I want run my fluent case in a cluster using several nodes and processors (I'm using Torque as manager in the cluster). The PBS journal is: #PBS -N LSVOFaxi #PBS -m ae #PBS -M user@domain.com #PBS -l nodes=2:pn=4 (the face are two point, I don't know why appears it) FLUENT_PATH=/cluster/apps/ansys_inc/v140/fluent/bin cd ${PBS_O_WORKDIR} $FLUENT_PATH/fluent 2ddp -g -ssh -pinfiniband -t8 -cnf=/home/Documents/LSVOFaxi/fluenthostsn2p4 -i LSVOFaxi.txt > LSVOFaxi.log The hosts file (fluenthostsn2p4) is: r1i0n2 r1i0n2 r1i0n2 r1i0n2 r1i0n15 r1i0n15 r1i0n15 r1i0n15 <white line> But this not worked. I think that the error is in the following line command, but I don't know: $FLUENT_PATH/fluent 2ddp -g -ssh -pinfiniband -t8 -cnf=/home/Documents/LSVOFaxi/fluenthostsn2p4 -i LSVOFaxi.txt > LSVOFaxi.log If anyone know solve it, please help me. Thank you. ----------------------------------------------------------------------- When I ran parallel local, with 1 node and 4 processors, using the following PBS journal, this worked. #PBS -N LSVOFaxi #PBS -m ae #PBS -M user@domain.com #PBS -l nodes=1:ppn=4 (the face are two point, I don't know why appears it) FLUENT_PATH=/cluster/apps/ansys_inc/v140/fluent/bin cd ${PBS_O_WORKDIR} $FLUENT_PATH/fluent 2ddp -g -t4 < LSVOFaxi.txt > LSVOFaxi.log |
All times are GMT -4. The time now is 06:18. |