Seti@Home optimized science apps and information
Optimized Seti@Home apps => Windows => GPU crunching => Topic started by: Zoran Kirsic on 14 Jan 2009, 07:12:18 pm
-
You can see spec of my computer under this link http://setiathome.berkeley.edu/show_host_detail.php?hostid=4234493
I have a 8600T with 180.84 ForceWare driver. even with Raistmer's_opt_package_V5a or Raistmer's_opt_package_V5b I have continues computing errors. As you can see this is not a VLAR problem.
You can see my results at http://setiathome.berkeley.edu/results.php?hostid=4234493. but here is one http://setiathome.berkeley.edu/forum_thread.php?id=51005&nowrap=true#853519:
or
Task ID 1122573998
Name 16no08ag.3415.23794.9.8.94_0
Workunit 395233994
Created 14 Jan 2009 19:38:37 UTC
Sent 14 Jan 2009 21:01:34 UTC
Received 14 Jan 2009 23:02:55 UTC
Server state Over
Outcome Client error
Client state Compute error
Exit status 1 (0x1)
Computer ID 4234493
Report deadline 7 Feb 2009 0:26:25 UTC
CPU time 52.0625
stderr out
<core_client_version>6.4.5</core_client_version>
<![CDATA[
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : GeForce 8600 GT
totalGlobalMem = 268107776
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1188000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 1
multiProcessorCount = 4
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 8600 GT is okay
SETI@home using CUDA accelerated device GeForce 8600 GT
Rise priority modification by Raistmer based on rev400 of SETI@home sources
VLAR autokill mod from Crunch3rPriority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 268107776 free GPU memory 224959232
setiathome_enhanced 6.02 Visual Studio/Microsoft C++
libboinc: 6.3.22
Work Unit Info:
...............
WU true angle range is : 0.433357
Optimal function choices:
-----------------------------------------------------
name
-----------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.00045 0.00000
v_ChirpData 0.01731 0.00000
v_Transpose4 0.01130 0.00000
FPU opt folding 0.00474 0.00000
Cuda error 'cudaMemcpy(&flags, dev_flag, sizeof(*dev_flag), cudaMemcpyDeviceToHost)' in file 'd:/BTR/seticuda/seti_boinc/client/cuda/cudaAcc_gaussfit.cu' in line 510 : unknown error.
</stderr_txt>
]]>
Validate state Invalid
Claimed credit 10.0294433356691
Granted credit 0
application version 6.07
http://setiathome.berkeley.edu/result.php?resultid=1122573998
Task ID 1122573994
Name 16no08ag.3415.23794.9.8.82_1
Workunit 395233982
Created 14 Jan 2009 19:38:37 UTC
Sent 14 Jan 2009 21:01:34 UTC
Received 14 Jan 2009 23:02:55 UTC
Server state Over
Outcome Client error
Client state Compute error
Exit status -1073741819 (0xffffffffc0000005)
Computer ID 4234493
Report deadline 7 Feb 2009 0:26:25 UTC
CPU time 51.28125
stderr out
<core_client_version>6.4.5</core_client_version>
<![CDATA[
<message>
- exit code -1073741819 (0xc0000005)
</message>
<stderr_txt>
setiathome_CUDA: Found 1 CUDA device(s):
Device 1 : GeForce 8600 GT
totalGlobalMem = 268107776
sharedMemPerBlock = 16384
regsPerBlock = 8192
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1188000
totalConstMem = 65536
major = 1
minor = 1
textureAlignment = 256
deviceOverlap = 1
multiProcessorCount = 4
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce 8600 GT is okay
SETI@home using CUDA accelerated device GeForce 8600 GT
Rise priority modification by Raistmer based on rev400 of SETI@home sources
VLAR autokill mod from Crunch3rPriority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 268107776 free GPU memory 224959232
setiathome_enhanced 6.02 Visual Studio/Microsoft C++
libboinc: 6.3.22
Work Unit Info:
...............
WU true angle range is : 0.433357
Optimal function choices:
-----------------------------------------------------
name
-----------------------------------------------------
v_BaseLineSmooth (no other)
v_GetPowerSpectrum 0.00046 0.00000
v_ChirpData 0.01682 0.00000
v_Transpose4 0.01139 0.00000
FPU opt folding 0.00480 0.00000
Cuda error 'cudaAcc_GetPowerSpectrum_kernel' in file 'd:/BTR/seticuda/seti_boinc/client/cuda/cudaAcc_PowerSpectrum.cu' in line 56 : unknown error.
</stderr_txt>
]]>
Validate state Invalid
Claimed credit 9.98275114663122
Granted credit 0
application version 6.07
http://setiathome.berkeley.edu/result.php?resultid=1122573994
Can someone suggest what I have to do or maybe is better to go back to CPU processing!?? Before I have tried in 6.03 app, but with same errors.
And every time exactly in 11 min and 2 sec, processing will stop and the message will appear that is a computing error.
[attachment deleted by admin]
-
....
And every time exactly in 11 min and 2 sec, processing will stop and the message will appear that is a computing error.
You don't happen to have you screensaver set to kick in after 10min ?
Did you install the latest drivers from nvidia, if so what version ?
-
I have no screensaver, and 180.84 version of driver!
-
I have no screensaver, and 180.84 version of driver!
Well.... try to go witj 181.20 .... not sure it helps though... Pretty possible it something very different...
-
maybe too much overclock
-
maybe too much overclock
And just ckeck driver again as here (http://setiathome.berkeley.edu/forum_thread.php?id=51275&nowrap=true#851540) shown
Sometimes the driver are not correctly installed. In your case it schould be version 180.84
-
today I installed 15.23_nforce and 181.20_geforce drivers and I have no problem. CUDA is now crunching normally. Here is a link to my First results http://setiathome.berkeley.edu/result.php?resultid=1122786826. I don't know how or why is working, but it's working. until now I have around 30 computing errors, and this my first 100%.