Optimized CUDA Issues & '-12 Unknown error'

Author	Message
samuel7 Volunteer tester Send message Joined: 2 Jan 00 Posts: 47 Credit: 2,194,240 RAC: 0	Message 936677 - Posted: 29 Sep 2009, 14:03:53 UTC - in response to Message 932814. Last modified: 29 Sep 2009, 14:05:38 UTC Checked out the resends in my task list and found this on a wingmate: http://setiathome.berkeley.edu/result.php?resultid=1373879479 SETI@home error -12 Unknown error cudaAcc_find_triplets doesn't support more than MAX_TRIPLETS_ABOVE_THRESHOLD numBinsAboveThreshold in find_triplets_kernel My GPU with V12 will get to it late Wednesday UTC. If wanted, I can save wu/result files. I also had a -12 'found a triplet twice' error in which the wingmate that reported signals in stderr didn't find a triplet at all. WU 505853255 I'll copy the record here as it is purged in a few hours: http://setiathome.berkeley.edu/result.php?resultid=1366699602 Spike count: 28 Pulse count: 0 Triplet count: 0 Gaussian count: 3 ID: 936677 ·

skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60	Message 962883 - Posted: 12 Jan 2010, 13:09:45 UTC - in response to Message 936677. Samuel this result could have easily sent a -9 error as well. its a noisy WU and you have more than 30 results this happens all the time In a rich man's house there is no place to spit but his face. Diogenes Of Sinope ID: 962883 ·

Raistmer Volunteer developer Volunteer tester Send message Joined: 16 Jun 01 Posts: 6325 Credit: 106,370,077 RAC: 121	Message 962897 - Posted: 13 Jan 2010, 0:01:09 UTC This error fixed in some extent in last (still dev and pre-alpha) builds and root of this error now known. I suggest mods to unstick this thread to keep number of stickies resonable small. ID: 962897 ·

©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.