yade-users team mailing list archive

Thread
Date

[Question #699235]: Settings HPC Slurm

To: yade-users@xxxxxxxxxxxxxxxxxxx
From: Luis Barbosa <question699235@xxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 27 Oct 2021 05:30:57 -0000
Reply-to: question699235@xxxxxxxxxxxxxxxxxxxxx
Sender: noreply@xxxxxxxxxxxxx

New question #699235 on Yade:
https://answers.launchpad.net/yade/+question/699235

Dear all,

I am using Slurm to run Yade in a cluster. From this scrip (below) no more than 7 cores are used in parallel:
#!/bin/bash -x
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=80
#SBATCH --partition=compute
#SBATCH --job-name=DEM_PFV
#SBATCH --time=10:00:00

singularity run /beegfs/common/singularity/yade/yade_debian_bookwarm_1.0.sif yade -j70 jobname.py


I am searching for instructions to see if I can change -nodes>1 or anything else to increase the number of parallel cores during simulation.


The simulation I am running is this example [1] but with a bigger domain.
[1] https://gitlab.com/yade-dev/trunk/-/blob/master/examples/FluidCouplingPFV/drainage-2PFV-Yuan_and_Chareyre_2017.py


I am completely new in this matter so any info would be helpful.
Kind regards,
Luis

-- 
You received this question notification because your team yade-users is
an answer contact for Yade.