Talk:Advanced MPI scheduling

sbatch options affecting process placement

Most or all of these options should be touched upon in the discussion of process placement. The terminology, "node", "task", "code", "socket", "cpu", "thread", etc., needs to be explained too.

• -N, --nodes=
• -n, --ntasks=
• --ntasks-per-core=
• --ntasks-per-node=
• --ntasks-per-socket=
• --tasks-per-node=
• --threads-per-core=
• -c, --cpus-per-task=
• --mincpus=
• --cores-per-socket=
• --exclusive[=user|mcs]
• --spread-job
• --hint=[compute_bound|memory_bound|multithread|nomultithread]
• -m, --distribution=[arbitrary|<block|cyclic|plane]
• --mem_bind=

These affect how memory is allocated. Are there others?

• --mem= and --mem-per-cpu=

Ross Dickson (talk) 15:33, 5 April 2017 (UTC)