[slurm-users] Performance with hybrid setup

vicentesmith vicentesmith at protonmail.com
Sun Mar 13 18:42:30 UTC 2022

I'm performing some tests (CPU-only systems) in order to compare MPI versus hybrid setup. The system is running OpenMPIv4.1.2 so that a job submission reads:
mpirun -np 48 foo.exe
mpirun -np 6 foo.exe
In our system, the latter runs slightly faster (about 5 to 10%) but any performance gain/loss will depend on the system & app.
In the same system and for the same app, the first SLURM script reads:
#SBATCH --job-name=***
#SBATCH --output=*
#SBATCH --ntasks=48
mpirun foo.exe
This script runs fine. Then, and for the hybrid job, the script reads:
#SBATCH --job-name=***hybrid
#SBATCH --output=***
#SBATCH --ntasks=6
#SBATCH --cpus-per-task=8
mpirun foo.exe
However, this runs much slower and it seems to slow down even more as it moves forward. Something is obviously not clicking correctly for the latter case. My only explanation is that the threads are not forked out correctly (by this I mean that the 8 threads are not assigned to the cores sharing the same L3). OpenMPI is supposed to choose the path of least resistance but I was wondering if I might need to recompile OpenMPI with some extra flags or modify the SLURM script somehow.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.schedmd.com/pipermail/slurm-users/attachments/20220313/33f13e48/attachment.htm>

More information about the slurm-users mailing list