GeForce 8800 GX2 and CUDA

Questions and Answers : GPU applications : GeForce 8800 GX2 and CUDA
Message board moderation

To post messages, you must log in.

AuthorMessage
Mel

Send message
Joined: 30 Jun 06
Posts: 6
Credit: 932,098
RAC: 0
United States
Message 964811 - Posted: 20 Jan 2010, 20:11:51 UTC

I'm getting a large number of computation errors using CUDA on my video card. Upon further inspection GPU 0 runs fine, but GPU one is causing all the errors. When I watched it though it's not really a computation error, more like GPU 1 is not getting to work at all and it times out at 25 seconds +-2.
Anyone know how to correct this? My GPUs both run fine for everything else.

System Information
Win XP Pro V2002 Service Pack 3
Video Driver Version: 195.62
Bios GPU 0: 62.92.39.00.10
Bios GPU 1: 62.92.39.00.09
BOINC: 6.10.18
CUDA23 V 6.09
ID: 964811 · Report as offensive
Mel

Send message
Joined: 30 Jun 06
Posts: 6
Credit: 932,098
RAC: 0
United States
Message 965625 - Posted: 24 Jan 2010, 5:44:32 UTC

An update. I've noticed that it's not just my card with this error. Here is the dump from one of the work units. All units that display this error have the same dump. This seems to happen with all breeds of 9800 cards. I wonder if other people encountering this problem have 2 or more GTs working in parallel.

<core_client_version>6.10.18</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
setiathome_CUDA: Found 2 CUDA device(s):
Device 1 : GeForce 9800 GX2
totalGlobalMem = 536543232
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1500000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 1
multiProcessorCount = 16
Device 2 : GeForce 9800 GX2
totalGlobalMem = 536543232
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1500000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 1
multiProcessorCount = 16
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 9800 GX2 is okay
SETI@home using CUDA accelerated device GeForce 9800 GX2
setiathome_enhanced 6.09 Visual Studio/Microsoft C++
libboinc: 6.3.22

Work Unit Info:
...............
WU true angle range is : 0.381387
Optimal function choices:
-----------------------------------------------------
name
-----------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.00049 0.00000
v_ChirpData 0.01742 0.00000
v_Transpose4 0.01069 0.00000
FPU opt folding 0.00331 0.00000
CUFFT error in file 'c:/sw/gpgpu/seti/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 62.

</stderr_txt>
]]>

ID: 965625 · Report as offensive
Mel

Send message
Joined: 30 Jun 06
Posts: 6
Credit: 932,098
RAC: 0
United States
Message 967375 - Posted: 31 Jan 2010, 23:32:57 UTC - in response to Message 964811.  

Oddly enough this error has stopped occuring. Nothing has changed. Not even the version number of Seti. I will post a new thread if it happens again.
ID: 967375 · Report as offensive

Questions and Answers : GPU applications : GeForce 8800 GX2 and CUDA


 
©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.