Advanced MPI scheduling: Difference between revisions

Advanced MPI scheduling (view source)

2 bytes added , 1 year ago

no edit summary

rsnt_translations

56,430

edits

@@ Line 169: / Line 169: @@
   --mem=96G
   srun --cpus-per-task=$SLURM_CPUS_PER_TASK application.exe
-This job is the same size as the last one: 16 tasks (that is, 16 MPI processes), each with 4 threads. The difference here is that we are sure of getting exactly 2 whole nodes. Recall that <code>--mem</code> requests memory <i>per node</i>, so we use it instead of <code>--mem-per-cpu</code> for the reason described earlier.
+This job is the same size as the last one: 16 tasks (that is, 16 MPI processes), each with 4 threads. The difference here is that we are sure of getting exactly 2 whole nodes. Remember that <code>--mem</code> requests memory <i>per node</i>, so we use it instead of <code>--mem-per-cpu</code> for the reason described earlier.
 === Why srun instead of mpiexec or mpirun? === <!--T:10-->