User Tools

Site Tools


cluster:208

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
cluster:208 [2022/05/26 17:23]
hmeij07 [Feedback]
cluster:208 [2022/05/26 19:57]
hmeij07 [gpu testing]
Line 385: Line 385:
 ===== gpu testing ===== ===== gpu testing =====
  
-  * n33 only, free of jobs, 4 gpus, 16 cores, 16 threads, 32 cpus +  * n33 only, 4 gpus, 16 cores, 16 threads, 32 cpus 
- +  * submit one at a time, observe   
-  * submit one at a time, observe where pmemd.cuda ends up +  * part=test, n 1, B 1:1:1, cuda_visible=0, no node specified 
 +  * "resources" reason at 17th submit, used up 16 cores and 16 threads 
 +  * all on same gpu 
 +  * part=test, n 1, B 1:1:1, cuda_visible not set, no node specified 
 +  * "resources" reason at 17th submit too, same reason 
 +  * all gpus used? nope, all on the same one 0 
 +  * redoing above with a  ''export CUDA_VISIBLE_DEVICES=`shuf -i 0-3 -n 1`'' 
 +  * even distribution across all gpus, 17th submit reason too
   *    * 
 ===== Changes ===== ===== Changes =====
cluster/208.txt · Last modified: 2022/11/02 17:28 by hmeij07