Difference between revisions of "Cluster:Compute nodes"

From Collective Computational Unit
Jump to navigation Jump to search
m (List of compute nodes)
m (List of compute nodes)
Line 17: Line 17:
 
| exc-cb, inf
 
| exc-cb, inf
 
| nVidia DGX-2
 
| nVidia DGX-2
| 16 x V100
+
| 16 x V100 @ 32 GB
 
|-
 
|-
 
! scope="row"| Glasya
 
! scope="row"| Glasya
Line 24: Line 24:
 
| trr161
 
| trr161
 
| Dual Xeon Rack
 
| Dual Xeon Rack
| 4 x Titan RTX
+
| 4 x Titan RTX @ 24 GB
 
|-
 
|-
 
! scope="row"| Demogorgon (in prep)
 
! scope="row"| Demogorgon (in prep)
Line 31: Line 31:
 
| cvia
 
| cvia
 
| Core i9 Desktop
 
| Core i9 Desktop
| 4 x GTX 1080 Ti
+
| 4 x GTX 1080 Ti @ 12 GB
 
|-
 
|-
 
! scope="row"| Lilith (in prep)
 
! scope="row"| Lilith (in prep)
Line 38: Line 38:
 
| cvia
 
| cvia
 
| Core i9 Desktop
 
| Core i9 Desktop
| 4 x Titan Xp
+
| 4 x Titan Xp @ 12 GB
 
|-
 
|-
 
! scope="row"| Asmodeus (in prep)
 
! scope="row"| Asmodeus (in prep)
Line 45: Line 45:
 
| cvia
 
| cvia
 
| Core i9 Desktop
 
| Core i9 Desktop
| 4 x Titan Xp
+
| 4 x Titan Xp @ 12 GB
 
|-
 
|-
 
|}
 
|}

Revision as of 20:24, 23 June 2019

List of compute nodes

The following compute nodes are currently part of the cluster:

CCU name INF name IP Access Platform GPUs
Vecna ccu-node1 134.34.226.230 exc-cb, inf nVidia DGX-2 16 x V100 @ 32 GB
Glasya ccu-node2 134.34.226.30 trr161 Dual Xeon Rack 4 x Titan RTX @ 24 GB
Demogorgon (in prep) ccu-node3 134.34.226.tba cvia Core i9 Desktop 4 x GTX 1080 Ti @ 12 GB
Lilith (in prep) ccu-node4 134.34.226.tba cvia Core i9 Desktop 4 x Titan Xp @ 12 GB
Asmodeus (in prep) ccu-node5 134.34.226.tba cvia Core i9 Desktop 4 x Titan Xp @ 12 GB


The CCU name is the internal name used in the Kubernetes cluster, as well as the configured hostname of the node. The INF name is the name within the network of the CS department, which means you can refer to the node as "inf-name.inf.uni-konstanz.de" in your browser (it is planned that "ccu-name.ccu.uni-konstanz.de" becomes an alias, but is not configured yet). Alternatively, you can refer to the node by its IP from the outside world.

In the column "Access" you can find which Kubernetes user groups can access this node.

Group Desciption
exc-cb Centre for the Advanced Study of Collective Behaviour
trr161 SFB Transregio 161 "Quantitative Methods for Visual Computing"
inf Department of Computer Science
cvia Computer Vision and Image Analysis Group