Advanced MPI scheduling: Difference between revisions

Advanced MPI scheduling (view source)

50 bytes removed , 5 years ago

no edit summary

rsnt_translations

56,420

edits

@@ Line 111: / Line 111: @@
 <!--T:30-->
-If you need more memory per node than the smallest node provides (e.g. more than 125 GiB at Graham) then you should not use <code>--mem=0</code>, but request the amount explicitly. Furthermore, some memory on each node is reserved for the operating system.  To find the largest amount your job can request and still qualify for a given node type, consult the "Available memory" column of the "Node types and characteristics" table on cluster description page:
+If you need more memory per node than the smallest node provides (e.g. more than 125 GiB at Graham) then you should not use <code>--mem=0</code>, but request the amount explicitly. Furthermore, some memory on each node is reserved for the operating system.  To find the largest amount your job can request and still qualify for a given node type, consult the "Available memory" column of the "Node characteristics" table on cluster description page:
-* [[Béluga/en#Node_types_and_characteristics|Béluga node types and characteristics]]
+* [[Béluga/en#Node_characteristics|Béluga node characteristics]]
 * [[Cedar#Node_characteristics|Cedar node characteristics]]
-* [[Graham#Node_types_and_characteristics|Graham node types and characteristics]]
+* [[Graham#Node_characteristics|Graham node characteristics]]
 ==== Few cores, single node ==== <!--T:6-->