Update Cades authored by Doak, Peter W.'s avatar Doak, Peter W.
......@@ -39,27 +39,26 @@ bash $ ssh or-condo-login.ornl.gov
```
The [env/cades-cnms](env-cades-cnms) gives you some standard environment variables and puts the CNMS modules in your `$MODULEPATH`
### Check current qos=std usage with
### Check current qos=std condo with
```shell-session
[you@or-condo-login02 ~]$ showq -w acct=cnms
```
### Check current qos=std class=high_mem condo with
```shell-session
[you@or-condo-login02 ~]$ showq -w "acct=cnms,class=high_mem"
```
## Environment
**32+ core Haswell/Broadwell Based**
| type | memory |feature code |
| ----------------- | ------------ | ------------|
| Haswell 2x16 | 125G | hw32, std |
| Broadwell 2x18 | 125G | bw36, std |
| High mem (bw36) | 251G | high_mem |
|GPU haswell | 251G |k80_hw32, gpu,std |
|GPU Broadwell | 251G |k80_bw36, gpu,std |
## Environment
**32-36 core Haswell/Broadwell Based**
Most plentiful node is Haswell 2x16, i.e. hw32
We have two guaranteed blocks of compute:
1 . 1216 on -q batch (includes both hw32 and bw36)
2 . 1200~ on -q high_mem (these are all bw36)
* unless stated modules are optimized for hw32.
* unless stated modules are optimized for hw32 but run just as well on bw36
* use of no feature code results in std
* mixes of node types can cause crashes
* high_mem and gpu nodes are now on separate queues. Neglect the feature code and use the correct queue
** MOAB Torque Cluster **
......
......