Questions and Answers :
GPU applications :
Tasks hanging on CUDA 6.08
Message board moderation
Previous · 1 · 2 · 3 · Next
Author | Message |
---|---|
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Another one: http://setiathome.berkeley.edu/result.php?resultid=1141507523 Suspended / restarted. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 25.273% http://setiathome.berkeley.edu/result.php?resultid=1143832003 You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 18.697% http://setiathome.berkeley.edu/result.php?resultid=1145583721 You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
I think I found a clue. I just downloaded a ton of MB workunits and my GPU is happily crunching away on this task: http://setiathome.berkeley.edu/result.php?resultid=1149399409 It froze at about 6% but I noticed something this time. It froze exactly at the same time as BOINC switched tasks from one of my AP workunits to a Milkyway@home workunit. Perhaps there is a bug in which the Seti CUDA client hangs when the CPU client switches from one task to another? You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung as soon as it started. http://setiathome.berkeley.edu/result.php?resultid=1149404140 It seems again to have hung as another task was resumed. Here is a copy of the log: 2/4/2009 12:24:30 PM|SETI@home|Computation for task 05ja09ac.7312.72.7.8.76_1 finished 2/4/2009 12:24:30 PM|SETI@home|Starting 06dc08af.5377.5391.14.8.115_1 2/4/2009 12:24:30 PM|SETI@home|Starting task 06dc08af.5377.5391.14.8.115_1 using setiathome_enhanced version 608 2/4/2009 12:24:34 PM|Einstein@Home|Restarting task h1_0765.25_S5R4__1101_S5R5a_0 using einstein_S5R5 version 301 2/4/2009 12:24:34 PM|SETI@home|Started upload of 05ja09ac.7312.72.7.8.76_1_0 2/4/2009 12:24:38 PM|SETI@home|Finished upload of 05ja09ac.7312.72.7.8.76_1_0 -------------------------------------------------------------------------------- Task 06dc08af.5377.5391.14.8.115_1 is the one that hung. Note how as soon as it started, the Einstein task restarted, and that's when the Seti task hung. Restarting BOINC resumed the task. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 24.298%. http://setiathome.berkeley.edu/result.php?resultid=1149416814 Task restarted and running fine now. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 19.714%. http://setiathome.berkeley.edu/result.php?resultid=1149464863 Paused / resumed and now working fine. You will be assimilated...bunghole! |
john deneer Send message Joined: 16 Nov 06 Posts: 331 Credit: 20,996,606 RAC: 0 |
I don't know whether this is similar behaviour as reported here, but I guess the title of the thread applies to my 'problem' as well .... I'm running Raistmer's 'team' version 8 on a stock q6600 and 2 gt8800's (of which only the first is used). Boinc 6.4.5 with the cc_config.xml fix for 5 cpu's, 180.48 drivers (probably not the newest, but they seem to work okay) on 32-bit Windows XP Professional sp3. Usually everything is fine, and I haven't seen the behaviour where a cuda wu gets stuck somewhere in the middle of crunching. What I do see, however, is wu's getting stuck in the initial phase after approx. 1 second of cpu time. Suspending and resuming doesn't help (when I do that Boinc starts a fifth task on the cpu :-) and I have to resort to aborting the unit. Is there a way to avoid this? Or is the only way to run the 'hanging wu killer script' that was described some time ago? Might the 'old' driver version have something to do with it? I'm hesitant to just go ahead with a driver update, I have had some nasty experiences with that in the past and when everything seems to work I usually shy away from unnecessary driver updates :-) Regards, John. |
Gundolf Jahn Send message Joined: 19 Sep 00 Posts: 3184 Credit: 446,358 RAC: 0 |
...Suspending and resuming doesn't help (when I do that Boinc starts a fifth task on the cpu :-) and I have to resort to aborting the unit... What about stopping and restarting the BOINC client? Perhaps that would help avoid aborting of the task (just guessing here:-). Gruß, Gundolf Computer sind nicht alles im Leben. (Kleiner Scherz) SETI@home classic workunits 3,758 SETI@home classic CPU time 66,520 hours |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 0% immediately after starting: http://setiathome.berkeley.edu/result.php?resultid=1149460741 Had to restart BOINC to resume the task. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 13.514%. http://setiathome.berkeley.edu/result.php?resultid=1149464378 Suspended and resumed task, working fine now. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at %2.085. I had previously suspended the Seti project so I could play a 3d game without CUDA interfering. The task hung the instant I resumed the project. http://setiathome.berkeley.edu/result.php?resultid=1151109241 Suspended / resumed and task is now working fine. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 2.746%. http://setiathome.berkeley.edu/result.php?resultid=1149469519 Suspended / resumed the task, working fine now. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung immediately after it started at 0%. http://setiathome.berkeley.edu/result.php?resultid=1151108968 Suspending and resuming the task failed. Had to restart BOINC manager to get it running again. Edit - Task froze a second time at 13.956%. This time, suspending and resuming the task worked. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 1.631%. http://setiathome.berkeley.edu/result.php?resultid=1149464862 Suspended / resumed task. Working fine now. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 3.14%. http://setiathome.berkeley.edu/result.php?resultid=1151120754 Paused the task and resumed successfully. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 6.623% http://setiathome.berkeley.edu/result.php?resultid=1151120769 Paused the task and resumed successfully. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 3.778% http://setiathome.berkeley.edu/result.php?resultid=1152505374 Paused / resumed the task successfully. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 30.817% http://setiathome.berkeley.edu/result.php?resultid=1152505378 Paused and resumed the task successfully. You will be assimilated...bunghole! |
Borgholio Send message Joined: 2 Aug 99 Posts: 654 Credit: 18,623,738 RAC: 45 |
Task hung at 40.901% http://setiathome.berkeley.edu/result.php?resultid=1163190910 Paused and resumed the task fine. You will be assimilated...bunghole! |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.