Differences

This shows you the differences between two versions of the page.

--- cluster:189 [2020/01/11 17:57]
hmeij07
+++ cluster:189 [2020/01/11 18:07]
hmeij07 [Funding Policy]
@@ Line 37: / Line 37: @@
 A gpu hour of usage is 3x the cpu hourly rate.\\
-user base stats, annual meeting, spring reading week
+We currently have about 1,450 physical cpu cores, 60 gpus, 520 gb of gpu memory and 8,560 gb cpu memory provided by about 120 compute nodes and login nodes. Scratch spaces are provide local to compute nodes (2-5 tb) or over the network via NFS (55 tb). Home directories are under quota (10 tb) but these will disappear in the future with the TrueNAS/ZFS appliance (190 tb, 475 tb effective assuming a compression rate of 2.5x). a guide can be found here [[cluster:82|Brief Description]] and the software is located here [[cluster:73|CD-HIT]]
-hpcc stats cpu cores, gpus, mem, hdd (rough) link to guide
-latest deployment: nvidia gpu cloud on premise (docker containers) link
-Script preempts nodes every 2 hours.

DokuWiki