CUDA Tasks Ending with -9 result

Author	Message
Sponge Send message Joined: 16 May 99 Posts: 3 Credit: 452,476 RAC: 0	Message 971372 - Posted: 18 Feb 2010, 22:14:39 UTC Most of my CUDA WU's are ending with "SETI@Home Informational message -9 result_overflow NOTE: The number of results detected exceeds the storage space allocated." Combined Count = 31. WU takes < 120 sec to run. Vid info as follows: setiathome_CUDA: Found 1 CUDA device(s): Device 1 : GeForce GTX 260 totalGlobalMem = 939524096 sharedMemPerBlock = 16384 regsPerBlock = 16384 warpSize = 32 memPitch = 262144 maxThreadsPerBlock = 512 clockRate = 1242000 totalConstMem = 65536 major = 1 minor = 3 textureAlignment = 256 deviceOverlap = 1 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 setiathome_enhanced 6.09 Visual Studio/Microsoft C++ libboinc: 6.3.22 Is there an issue with the NVidia driver? MS C++?? or Seti CUDA?? Albert (Sponge) ID: 971372 ·

skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60	Message 971454 - Posted: 19 Feb 2010, 2:04:40 UTC - in response to Message 971372. you may have just hit a noisy patch of WU's Check your Wingmen, see if they are getting the -9 error as well. this error is typically from Noisy WU's or GPU's that are running to hot. In a rich man's house there is no place to spit but his face. Diogenes Of Sinope ID: 971454 ·

Sponge Send message Joined: 16 May 99 Posts: 3 Credit: 452,476 RAC: 0	Message 971847 - Posted: 19 Feb 2010, 20:01:40 UTC Most of the results were inconclusive. Wingmen did not report a -9. NVIDIA was set at factory default (Cooling = 40%) I have up'd that to 80% and when we get some access to new WU's; I will update this thread. Albert (Sponge) ID: 971847 ·

Jack Shaftoe Send message Joined: 19 Aug 04 Posts: 44 Credit: 2,343,242 RAC: 0	Message 977383 - Posted: 11 Mar 2010, 17:51:06 UTC - in response to Message 971847. Having similar problems. I set it to run GPU only when idle - which means it doesn't run all day while I work. Overnight it runs, about 50% pass, 50% fail. http://setiathome.berkeley.edu/results.php?userid=7918567&offset=0&show_names=0&state=5 Someone mentions heat being an issue, so I've upped fan from stock level of 40 to 65. Will see if that helps. If anyone else uses an EVGA card, their latest Precision is kinda nice. Shows % GPU useage and I can see SETI using 68-72% of my GPU. ID: 977383 ·

Jack Shaftoe Send message Joined: 19 Aug 04 Posts: 44 Credit: 2,343,242 RAC: 0	Message 977756 - Posted: 12 Mar 2010, 17:15:14 UTC - in response to Message 977383. Darn, same result last night. Wonder what is going on... ID: 977756 ·

skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60	Message 977775 - Posted: 12 Mar 2010, 17:36:23 UTC - in response to Message 977756. Check GPUz for high temperatures. If that isnt the case then try a reboot. In a rich man's house there is no place to spit but his face. Diogenes Of Sinope ID: 977775 ·

Gundolf Jahn Send message Joined: 19 Sep 00 Posts: 3184 Credit: 446,358 RAC: 0	Message 977785 - Posted: 12 Mar 2010, 17:54:01 UTC - in response to Message 977756. What are the errors you see? If -6, it's just the VLAR-kill. GruÃŸ, Gundolf Computer sind nicht alles im Leben. (Kleiner Scherz) SETI@home classic workunits 3,758 SETI@home classic CPU time 66,520 hours ID: 977785 ·

skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60	Message 977788 - Posted: 12 Mar 2010, 17:57:12 UTC - in response to Message 977785. he had a whole batch of -9 overflows In a rich man's house there is no place to spit but his face. Diogenes Of Sinope ID: 977788 ·

©2026 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.

CUDA Tasks Ending with -9 result_overflow