CUDA in SLI = Computation Errors?

Author	Message
BilBg Send message Joined: 27 May 07 Posts: 2093 Credit: 3,272,842 RAC: 8,238	Message 982692 - Posted: 23 Mar 2010, 6:15:11 UTC - in response to Message 982690. Last modified: 23 Mar 2010, 6:36:15 UTC
Remove the email address from the post (you have 1 hour to do that) or you will receive spam. If you want email notification - edit community prefs & subscribe to thread. Not "every" WU gives errors - some are "Completed and validated": http://setiathome.berkeley.edu/results.php?hostid=5326815&offset=0&show_names=0&state=3 Give us more info - how many GPUs, what type, which of them are in SLI _____________________________ setiathome_CUDA: Found 2 CUDA device(s): Device 1 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 Device 2 : GeForce 8200 totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1200000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 0 multiProcessorCount = 1 _____________________________ setiathome_CUDA: Found 3 CUDA device(s): Device 1 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 Device 2 : nForce 980a/780a SLI totalGlobalMem = 268435456 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1200000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 0 multiProcessorCount = 1 Device 3 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 _____________________________ GeForce 9800 GT GeForce 8200 nForce 980a/780a SLI ??? ____________ - ALF - "Find out what you don't do well ..... then don't do it!" :)
ID: 982692 ·

The Weasel Send message Joined: 6 Jun 99 Posts: 126 Credit: 46,547,108 RAC: 22,167	Message 982943 - Posted: 24 Mar 2010, 2:57:33 UTC
I just built a new system and was in the same situation as u, I disabled sli and all is good right now. But im not sure if this is going to help u or not as the system i am working on is windows 7, but without disabling sli, it would process one or two work units without any problem, then i would get a slug of computation errors, hope this helps u ____________
ID: 982943 ·

ayork37 Volunteer tester Send message Joined: 25 Sep 03 Posts: 5 Credit: 514,723 RAC: 0	Message 991150 - Posted: 22 Apr 2010, 18:05:14 UTC - in response to Message 982943.
I'm having problems with my 8800GTX cards in SLI. After I turned this on and SETI did some work my machine would become unstable. For now I've turned SETI off. Is SETI /w SLI considered to be stable? ____________
ID: 991150 ·

Remove the email address from the post (you have 1 hour to do that) or you will receive spam.

If you want email notification - edit community prefs & subscribe to thread.

Not "every" WU gives errors - some are "Completed and validated":
http://setiathome.berkeley.edu/results.php?hostid=5326815&offset=0&show_names=0&state=3

Give us more info - how many GPUs, what type, which of them are in SLI

_____________________________ setiathome_CUDA: Found 2 CUDA device(s): Device 1 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 Device 2 : GeForce 8200 totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1200000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 0 multiProcessorCount = 1 _____________________________ setiathome_CUDA: Found 3 CUDA device(s): Device 1 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 Device 2 : nForce 980a/780a SLI totalGlobalMem = 268435456 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1200000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 0 multiProcessorCount = 1 Device 3 : GeForce 9800 GT totalGlobalMem = 536870912 sharedMemPerBlock = 16384 regsPerBlock = 8192 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1500000 totalConstMem = 65536 major = 1 minor = 1 textureAlignment = 256 deviceOverlap = 1 multiProcessorCount = 14 _____________________________