Strange "error while computing" problem

Questions and Answers : GPU applications : Strange "error while computing" problem
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile Magnus
Avatar

Send message
Joined: 9 Aug 05
Posts: 12
Credit: 5,004,781
RAC: 0
Sweden
Message 896656 - Posted: 18 May 2009, 21:22:52 UTC
Last modified: 18 May 2009, 21:23:32 UTC

I´ve been running a machine dedicated for SETI alone, for a while. In the beginning, everything was fine. But then I started to get "error while computing" on the wu made by my 8800GT´s. I started to suspect them to be faulty, and replaced them with a coulple of 8800GTS-cards I´ve been running with no faults in my server. And the "errors" are still there. Any ideas?
Hardware look like this:
Foxconn Destroyer motherboard
AMD 940 Phenom II
Corsair XMS2 6400 Dominator 2x2Gb
2x8800GTS or 2x8800GT
Corsair 620W
Everything stuffed into a Lian PC-V2000.
No strange temperatures, and no faults in Prime95. No overclocking.
Freshly installed Win XP.
ID: 896656 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 896679 - Posted: 18 May 2009, 22:06:37 UTC - in response to Message 896656.  
Last modified: 18 May 2009, 22:12:31 UTC

That would be this one?

There I found
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 'c:/sw/gpgpu/seti/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 49 : initialization error.
setiathome_CUDA: CUDA runtime ERROR in plan FFT. Falling back to HOST CPU processing...
followed by
Unhandled Exception Detected...

- Unhandled Exception Record -
Reason: Breakpoint Encountered (0x80000003) at address 0x7C90120E

Engaging BOINC Windows Runtime Debugger...

Whatever that means ;-)

Gruß,
Gundolf
[edit]Even the task without error was computed on the CPU:
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : Device Emulation (CPU)
totalGlobalMem = -1
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 1
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1350000
totalConstMem = 65536
major = 9999
minor = 9999
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 16
setiathome_CUDA: device 1 is emulation device and should not be used, supports 9999.9999
setiathome_CUDA: CUDA Device 2 specified, checking...
Device cannot be used
SETI@home NOT using CUDA, falling back on host CPU processing
bad driver version? [/edit]
ID: 896679 · Report as offensive
Profile popandbob
Volunteer tester

Send message
Joined: 19 Mar 05
Posts: 551
Credit: 4,673,015
RAC: 0
Canada
Message 896729 - Posted: 18 May 2009, 23:51:32 UTC

Somewhere down the line something is preventing CUDA from running and it is falling back to the CPU

The breakpoint encountered happened when the task was terminated via abort or an improper shutdown.



Do you Good Search for Seti@Home? http://www.goodsearch.com/?charityid=888957
Or Good Shop? http://www.goodshop.com/?charityid=888957
ID: 896729 · Report as offensive
Profile Magnus
Avatar

Send message
Joined: 9 Aug 05
Posts: 12
Credit: 5,004,781
RAC: 0
Sweden
Message 896883 - Posted: 19 May 2009, 7:15:19 UTC - in response to Message 896729.  

Any idea what causes it?
ID: 896883 · Report as offensive
Profile Gundolf Jahn

Send message
Joined: 19 Sep 00
Posts: 3184
Credit: 446,358
RAC: 0
Germany
Message 896892 - Posted: 19 May 2009, 7:55:55 UTC - in response to Message 896883.  

Any idea what causes it?

Excerpt from my earlier post:
major = 9999 
minor = 9999 
...
setiathome_CUDA: device 1 is emulation device and should not be used, supports 9999.9999
setiathome_CUDA: CUDA Device 2 specified, checking...
Device cannot be used
SETI@home NOT using CUDA, falling back on host CPU processing
bad driver version?
ID: 896892 · Report as offensive
Profile Byron S Goodgame
Volunteer tester
Avatar

Send message
Joined: 16 Jan 06
Posts: 1145
Credit: 3,936,993
RAC: 0
United States
Message 896897 - Posted: 19 May 2009, 8:33:31 UTC - in response to Message 896883.  

Any idea what causes it?

Hi

Do you have a load on both video cards, either by connecting a second monitor or by using a dummy plug? If so did you also extend the destop to the second "display" in display settings on your desktop?
ID: 896897 · Report as offensive
Profile Magnus
Avatar

Send message
Joined: 9 Aug 05
Posts: 12
Credit: 5,004,781
RAC: 0
Sweden
Message 896924 - Posted: 19 May 2009, 11:56:43 UTC - in response to Message 896897.  

Do I need to? I havn´t it connected to any screen at all, at the moment.

ID: 896924 · Report as offensive
Profile Byron S Goodgame
Volunteer tester
Avatar

Send message
Joined: 16 Jan 06
Posts: 1145
Credit: 3,936,993
RAC: 0
United States
Message 897060 - Posted: 20 May 2009, 0:17:39 UTC - in response to Message 896924.  
Last modified: 20 May 2009, 0:26:15 UTC

Do I need to? I havn´t it connected to any screen at all, at the moment.


According to what I've seen posted in the threads here, if you want to run tasks on both cards, you would need to, though I'm not sure it would fix the current error you're having, it might be worth trying.
ID: 897060 · Report as offensive

Questions and Answers : GPU applications : Strange "error while computing" problem


 
©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.