Message boards :
Number crunching :
Shortened WU's
Message board moderation
| Author | Message |
|---|---|
Bender10Send message Joined: 3 Dec 07 Posts: 167 Credit: 8,368,897 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]()
|
I just noticed a couple of WU's that ran in ~3.5 hours on my 9800. 13-IBUCH_smd_pYIpYV_1906-3-10-RND6244_0 http://www.gpugrid.net/result.php?resultid=863428 22-IBUCH_smd_pYIpYV_1906-7-10-RND0998_2 http://www.gpugrid.net/result.php?resultid=866933 Where did these come from..? Consciousness: That annoying time between naps...... Experience is a wonderful thing: it enables you to recognize a mistake every time you repeat it. |
K1atOdessaSend message Joined: 25 Feb 08 Posts: 249 Credit: 444,646,963 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
I've seen one of these so far as well. Looks like the credit is consistent with the larger WU's. I think I'd prefer smaller WU's for my slower cards, so I don't have to worry about something breaking 95% and 15 hours in. With fast cards, though, I can see this requiring more connections to the server as the tasks will only take a hour or so. Could cause issues even for short server outages. |
|
Send message Joined: 17 Aug 08 Posts: 2705 Credit: 1,311,122,549 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Is the upload file size reduced proportionally? If yes then I suppose the server could take some more beating (=more requests but comparable traffic). MrS Scanning for our furry friends since Jan 2002 |
|
Send message Joined: 10 Apr 08 Posts: 254 Credit: 16,836,000 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
It's normal. All these WUs having *smd* on them are normally shorter...but heavier than "usual" *IBUCH*s The reason is because for these type of simulations we generate an additional heavy file such as in most of (if not all) *KASHIF* WUs. If I keep the *smd* shorter the heavy file won't grew too much as it depends on the simulation length (~computing time). cheers, ignasi |
Bender10Send message Joined: 3 Dec 07 Posts: 167 Credit: 8,368,897 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]()
|
|
|
Send message Joined: 16 May 08 Posts: 5 Credit: 68,721,860 RAC: 0 Level ![]() Scientific publications ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]() ![]()
|
any chance of shrinking the download size? my isp has hard enough time keeping my cards full now. |
©2025 Universitat Pompeu Fabra