Can this be fixed?


log in

Advanced search

Questions and Answers : GPU applications : Can this be fixed?

Author Message
Default
Avatar
Send message
Joined: 23 Aug 08
Posts: 50
Credit: 2,222,384
RAC: 0
United States
Message 889161 - Posted: 28 Apr 2009, 13:42:59 UTC

I have two GTX 260's. One of them finishes tasks in about three minutes while the other takes about ten minutes. The results are always invalid or inconclusive for the one that finishes quickly. I have tried different versions of BOINC, drivers, even operating systems to no avail. Here's a look at the stderr_txt:



Name 01fe09ab.888.10297.11.8.101_0
Workunit 437519149
Created 28 Apr 2009 4:44:24 UTC
Sent 28 Apr 2009 7:20:55 UTC
Received 28 Apr 2009 11:53:53 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 4899468
Report deadline 21 May 2009 2:58:06 UTC
CPU time 56.07813
stderr out <core_client_version>6.6.20</core_client_version>
<![CDATA[
<stderr_txt>
setiathome_CUDA: Found 2 CUDA device(s):
Device 1 : GeForce GTX 260
totalGlobalMem = 939524096
sharedMemPerBlock = 16384
regsPerBlock = 16384
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1408000
totalConstMem = 65536
major = 1
minor = 3
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 27
Device 2 : GeForce GTX 260
totalGlobalMem = 939524096
sharedMemPerBlock = 16384
regsPerBlock = 16384
warpSize = 32
memPitch = 262144
maxThreadsPerBlock = 512
clockRate = 1408000
totalConstMem = 65536
major = 1
minor = 3
textureAlignment = 256
deviceOverlap = 0
multiProcessorCount = 27
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce GTX 260 is okay
SETI@home using CUDA accelerated device GeForce GTX 260
V10 modification by Raistmer
Priority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 939524096 free GPU memory 874577920
setiathome_enhanced 6.02 Visual Studio/Microsoft C++

Build features: Non-graphics VLAR autokill enabled FFTW x86
CPUID: Intel(R) Core(TM) i7 CPU 920 @ 2.67GHz

Cache: L1=64K L2=256K

CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3
libboinc: 6.4.5

Work Unit Info:
...............
WU true angle range is : 0.448125
SETI@Home Informational message -9 result_overflow
NOTE: The number of results detected exceeds the storage space allocated.

Flopcounter: 4639272426356.874000

Spike count: 0
Pulse count: 31
Triplet count: 0
Gaussian count: 0

Wall-clock time elapsed since last restart: 164.6 seconds
called boinc_finish

</stderr_txt>
]]>

Validate state Checked, but no consensus yet
Claimed credit 12.0040950762725
Granted credit 0
application version 6.08

I should mention that the cards run very cool (55C) and are not dirty. Is this card bad or is something wrong with my setup? Why just one card?
____________

Profile Hammeh
Volunteer tester
Avatar
Send message
Joined: 21 May 01
Posts: 135
Credit: 1,143,316
RAC: 0
United Kingdom
Message 889189 - Posted: 28 Apr 2009, 14:59:57 UTC

This appears to be happening because the results being returned by your card, give different results to other computers running the same Work Unit.
____________

Profile popandbob
Volunteer tester
Send message
Joined: 19 Mar 05
Posts: 535
Credit: 1,896,421
RAC: 0
Canada
Message 889245 - Posted: 28 Apr 2009, 20:53:55 UTC

Are you OCing? If so try reducing it... If its factory OC'ed then again try reducing it.
Also check the temps... GPU's are more likely to produce errors at over 80c.


Bob
____________


Do you Good Search for Seti@Home? http://www.goodsearch.com/?charityid=888957
Or Good Shop? http://www.goodshop.com/?charityid=888957

Default
Avatar
Send message
Joined: 23 Aug 08
Posts: 50
Credit: 2,222,384
RAC: 0
United States
Message 889258 - Posted: 28 Apr 2009, 21:41:39 UTC - in response to Message 889245.

Tried turning the clocks down ridiculously low, core, shader and memory. Problem still manifests no matter what the settings. Replaced thermal tape on heatsinks with Artic Silver paste, set fan speed to 100 percent, runs at 50C. I'm at a loss. I have noticed that while crunching, it runs slightly slower than my other card when observing the percentage complete. I'm guessing it must be a dud as far as CUDA is concerned.
____________

Profile popandbob
Volunteer tester
Send message
Joined: 19 Mar 05
Posts: 535
Credit: 1,896,421
RAC: 0
Canada
Message 889274 - Posted: 28 Apr 2009, 23:02:10 UTC

Well I'd suggest RMAing it.
If its having problems with cuda it will most likely have problems with other things as well.
Bob
____________


Do you Good Search for Seti@Home? http://www.goodsearch.com/?charityid=888957
Or Good Shop? http://www.goodshop.com/?charityid=888957

Questions and Answers : GPU applications : Can this be fixed?

Copyright © 2014 University of California