NAMD: Difference between revisions

32 bytes added ,  4 years ago
no edit summary
No edit summary
No edit summary
Line 74: Line 74:
== Verbs jobs == <!--T:16-->
== Verbs jobs == <!--T:16-->
These provisional instructions will be refined further once this configuration can be fully tested on the new clusters.
These provisional instructions will be refined further once this configuration can be fully tested on the new clusters.
This example uses 64 processes in total on 2 nodes, each node running 32 processes, thus fully utilizing its 32 cores.  This script assumes full nodes are used, thus ntasks/nodes should be 32 (on Graham).  For best performance, NAMD jobs should use full nodes.
This example uses 64 processes in total on 2 nodes, each node running 32 processes, thus fully utilizing its 32 cores.  This script assumes full nodes are used, thus <code>ntasks-per-node</code> should be 32 (on Graham).  For best performance, NAMD jobs should use full nodes.


<!--T:17-->
<!--T:17-->
Line 177: Line 177:
== Verbs-GPU jobs == <!--T:20-->
== Verbs-GPU jobs == <!--T:20-->
These provisional instructions will be refined further once this configuration can be fully tested on the new clusters.
These provisional instructions will be refined further once this configuration can be fully tested on the new clusters.
This example uses 64 processes in total on 2 nodes, each node running 32 processes, thus fully utilizing its 32 cores.  Each node uses 2 GPUs, so job uses 4 GPUs in total. This script assumes full nodes are used, thus ntasks/nodes should be 32 (on Graham).  For best performance, NAMD jobs should use full nodes.
This example uses 64 processes in total on 2 nodes, each node running 32 processes, thus fully utilizing its 32 cores.  Each node uses 2 GPUs, so job uses 4 GPUs in total. This script assumes full nodes are used, thus <code>ntasks-per-node</code> should be 32 (on Graham).  For best performance, NAMD jobs should use full nodes.


<!--T:21-->
<!--T:21-->
rsnt_translations
56,430

edits