Panic Mode on the Server Status?
Message boards :
Number crunching :
Panic Mode on the Server Status?
Message board moderation
| Author | Message |
|---|---|
 Send message Joined: 26 Feb 14 Posts: 211 Credit: 4,496,324,562 RAC: 0 Level  Scientific publications    
|
Looks like we crunched all there was to crunch. Seeing no new work units unsent. It's a wait and see now.... Z |
|
Send message Joined: 21 Mar 16 Posts: 513 Credit: 4,673,458,277 RAC: 0 Level Scientific publications 
|
Since computers are getting faster and faster, maybe the university needs to hire some more PhDs :) |
|
Send message Joined: 5 Jan 09 Posts: 670 Credit: 2,498,095,550 RAC: 0 Level  Scientific publications 
|
Flops/sec are about the same as they have been for over a year during periods when there are a constant supply of WU's. |
|
Send message Joined: 28 Jul 12 Posts: 819 Credit: 1,591,285,971 RAC: 0 Level  Scientific publications
|
Since computers are getting faster and faster, maybe the university needs to hire some more PhDs :) Graduate students in this field are probably rare. And they have to plan their work before crunching, and write up their thesis afterwards. So there is not a constant supply of work from a relatively small group. But at least one of their graduates is now at Stanford. I will let you find him on the Folding project. |
|
Send message Joined: 9 Dec 08 Posts: 1006 Credit: 5,068,599 RAC: 0 Level  Scientific publications |
Just to chit-chat and provide some context: one problem with creating workunits (for new projects) is that the process is very error-prone. A misplaced keystroke may mean that days or weeks of time and computing time are lost. This invites defensiveness. (By the way, it's not different with supercomputers - just slightly faster turnaround). Also, consider that any amount of computing time implies a much larger amount of "human time" for follow-up and analysis (which itself has a degree of unpredictability, being this research). These skills are not learned in a month... |
|
Send message Joined: 26 Feb 14 Posts: 211 Credit: 4,496,324,562 RAC: 0 Level Scientific publications
|
It’s all good. Crunch them if they are available, if not I have backup projects with low caches. I try to keep the computers busy, you know the mischief they can get into if I leave them unsupervised for any length of time lol. 😂😂😂 |
|
Send message Joined: 11 Dec 11 Posts: 21 Credit: 145,887,858 RAC: 0 Level  Scientific publications 
|
Don´t know if it´s normal, i just return to crunch GPUgrid yesterday, but in the midle of the night i get the abandoned msg in 9 WU (some allmost crunched, running normal for about 6 hrs). Two examples... http://www.gpugrid.net/result.php?resultid=16643300 http://www.gpugrid.net/result.php?resultid=16643008 I need to do something? Just to be sure is not an error on my side. 
|
|
Send message Joined: 26 Feb 14 Posts: 211 Credit: 4,496,324,562 RAC: 0 Level Scientific publications
|
Probably they find an error in the work units and ordered them cancelled. I wouldn't worry to much about them. |
©2025 Universitat Pompeu Fabra