Questions and Answers :
GPU applications :
display driver reset problem
Message board moderation
Author | Message |
---|---|
Joseph Stateson Send message Joined: 27 May 99 Posts: 309 Credit: 70,759,933 RAC: 3 |
This work unit caused it http://setiathome.berkeley.edu/result.php?resultid=1112701831 Once this happens it appears (not consistently) that subsequent WU's also fail. I saw this first on the beta seti cuda project. I switched to regular seti a few hours ago, but after just 1 good WU I got this one. I rebooted just to be safe and am back running gpugrid. I do not see this problem (the display driver reset) occurring in gpugrid. Vista 64, gfx280 180.84, BM 6.5.0 From event log Display driver nvlddmkm stopped responding and has successfully recovered. |
OzzFan Send message Joined: 9 Apr 02 Posts: 15691 Credit: 84,761,841 RAC: 28 |
Since you are using a beta version of BOINC, you may want to report this on the BOINC Developers list. |
Joseph Stateson Send message Joined: 27 May 99 Posts: 309 Credit: 70,759,933 RAC: 3 |
Discovered that when the driver gets reset, my VNC server loses its display. I can log in remotely, but cant see anything as the display is black. When I get back to work (or get home) the display is all fuzzy and pixelating. This was on Ultra VNC and YMMV for other VNC flavors. |
Byron S Goodgame Send message Joined: 16 Jan 06 Posts: 1145 Credit: 3,936,993 RAC: 0 |
The task example error you gave is a common one with CUDA and Very Low Angle Range or VLAR WU's "WU true angle range is : 0.012636". It's suggested that you abort these since it's not likely you'll be able to complete them. It's a bug in the CUDA app they're working on. There is a batch file you can create to spot them before they start so you can abort them. There's info on it in this message |
©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.