Announcements

2 Jan 2017

DAS-5/VU has been extended with 4 TitanX-Pascal GPUs. Check DAS-5 special nodes for an overview of all DAS-5 special nodes.

9 Nov 2016

CUDA 8 is now available on all DAS-5 sites with GPU nodes. Check the DAS-5 GPU page for usage info.

May, 2016

IEEE Computer publishes paper about 20 years of Distributed ASCI Supercomputer. See the DAS Achievements page.

28 Sep 2015

DAS-5/VU has been extended with 16 GTX TitanX GPUs.

6 Aug 2015

DAS-5/UvA has been extended with 4 GTX TitanX GPUs: two on both node205 and node206.

6 Jul 2015

DAS-5 is fully operational!

DAS-5 Usage Policy


Each DAS-5 cluster consists of a headnode (file/compile server) and a number of compute nodes. The headnode is called fsX (X is 0, 1, 2, 3, 4 or 5 according to the cluster base); the worker nodes are named nodeX[0-9][0-9].

The DAS-5 must be used in the following way:

  • Program development (editing, compiling) is done on the headnodes, i.e., the file/compile servers.
  • Program execution MUST be done on the compute nodes, NEVER on a headnode. The headnodes are usually heavily loaded just carrying out the tasks they are intended for. User programs that run on a headnode harm all other users of that DAS-5 cluster! This rule also holds for sequential runs of parallel programs.
  • Running of jobs on the worker nodes MUST be done via the DAS-5 cluster scheduling system SLURM, which offers sufficient abstraction and flexibility for nearly all needs. A full documentation set is available.
  • The user interface of the original DAS scheduler prun has also been ported to the DAS-5 scheduler. For many users this will be the most convenient way to start jobs on one of the clusters.
  • The default run time for jobs scheduled on DAS-5 is 15 minutes, which is also the maximum during working hours, from 08:00 to 20:00. We do not want people to monopolize the clusters for a longer time, since that makes interactively running short jobs on a large number of nodes practically impossible. Also, to get a reasonable spread of the load on DAS-5, preferably use the cluster at your own site, unless it is overloaded and another one happens to be free.
  • DAS-5 is specifically NOT a cluster for doing production work. It is meant for people doing experimental research on parallel and distributed programming. Only during the night and in the weekend, when DAS-5 is regularly idle, it is allowed to run long jobs. In all other cases, you will first have to ask permission in advance from das-sysadm@cs.vu.nl to make sure you are not causing too much trouble for other users.

NOTE: Users who do not obey these usage rules, risk blocking of their account!


See also: DAS-5 User Accounts and DAS-5 Job Execution.