IT-Bereich des Instituts für Chemie hpc:hpc_tubit:clust_conf https://it.chem.tu-berlin.de/wiki/ 2026-04-28T14:19:14+00:00 IT-Bereich des Instituts für Chemie https://it.chem.tu-berlin.de/wiki/ https://it.chem.tu-berlin.de/wiki/lib/tpl/arctic/images/favicon.ico text/html 2019-07-23T16:53:20+00:00 Anonymous (anonymous@undisclosed.example.com) Further Cluster Information and Links https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:docu&rev=1563893600&do=diff Further Cluster Information and Links * Official Cluster Wiki: HCP Homepage * ISIS learning course (including discussion forum and cluster annoumcements): ISIS HPC Course * [Talk] held by Sebastian Kraus at 10/31/2018 during group seminar of Quantum Chemistry group date of revision: 06-24-2019 © kraus text/html 2020-04-25T14:59:43+00:00 Anonymous (anonymous@undisclosed.example.com) Login https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:login&rev=1587819583&do=diff Login <html> Works only within the TU intranet or VPN: </html> * <html> ssh -2 -e none -p 22 &lt;TU_Account_Name&gt;@gateway.hpc.tu-berlin.de (130.149.243.190) </html> date of revision: 04-25-2020 © kraus text/html 2019-07-23T16:19:02+00:00 Anonymous (anonymous@undisclosed.example.com) Available computing partitions https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:partitions&rev=1563891542&do=diff Available computing partitions <html> Preliminary Remark: The SLURM scheduler obeys fair-share rules and applies scoring to each user account. Actually, depending on the amount of resources (wall clock and CPU time, main memory usage, generic resources) allocated by a user within the last seven days, the scheduler calculates the priority of the jobs being scheduled. text/html 2019-06-24T12:47:39+00:00 Anonymous (anonymous@undisclosed.example.com) Cluster configuration and usage guidelines https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:start&rev=1561373259&do=diff Cluster configuration and usage guidelines clust_conf index text/html 2019-06-24T12:07:49+00:00 Anonymous (anonymous@undisclosed.example.com) Storage design/architecture https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:storage&rev=1561370869&do=diff Storage design/architecture BeeGFS * <html> <em>Whole file system tree (user/software/scratch) resides on a single BeeGFS (backed by three storage pools).</em> </html> * <html> <em>Only nodes gpu[001-021] of gpu partition offer ext3 formatted 880GiB local scratch (on SSD drive) mounted at /tmp. </em> text/html 2019-06-24T12:46:36+00:00 Anonymous (anonymous@undisclosed.example.com) Usage guidelines https://it.chem.tu-berlin.de/wiki/doku.php?id=hpc:hpc_tubit:clust_conf:usage&rev=1561373196&do=diff Usage guidelines * <html> <em>Fast local SSD disk scratch available with gpu nodes (gpu[001-021]) (mounted at /tmp).</em> </html> * <html> <em>With exclusive jobs on large SMP nodes, temporary files could just be placed into /dev/shm/&lt;path/to/your/folder&gt;