Message boards :
Number crunching :
curious about invalid AP
Message board moderation
Author | Message |
---|---|
David S Send message Joined: 4 Oct 99 Posts: 18352 Credit: 27,761,924 RAC: 12 |
http://setiathome.berkeley.edu/workunit.php?wuid=1479019117 is now out to its 5th host. I'm the _1 and I think my output is valid, 1 single pulse. The _2 came up with 30/30 (I take it this is the AP equivalent to a -9 on an MB task; does it have a similar cause?). But what really got me curious are the _0 and the _3. They both ran it as cal_ati (as is the _4 now in progress) and both got "too many exits." Specifically, the _0 has 98 iterations of Running on device number: 0 Priority of worker thread raised successfully Priority of process adjusted successfully, below normal priority class used 1 CAL GPUs found BOINC assigns device 0 Build features: Non-graphics FFTW USE_INCREASED_PRECISION USE_SSE x86 CPUID: AMD Athlon(tm) II X2 260 Processor Cache: L1=64K L2=1024K CPU features: FPU TSC PAE CMPXCHG8B APIC SYSENTER MTRR CMOV/CCMP MMX FXSAVE/FXRSTOR SSE SSE2 HT SSE3 SSE4A ### Restart at 0.00 percent. state.fold_buf_size_short=65536; state.fold_buf_size_long=262144 ERROR: some exception inside short FFA, probably video-driver restart, restarting app... The _3 has the same thing (but I didn't count how many times). Does this indicate some sort of problem with the cal_ati app, at least on certain types of AP WUs? (Sorry if this has been covered in another thread. I looked for one.) David Sitting on my butt while others boldly go, Waiting for a message from a small furry creature from Alpha Centauri. |
Ulrich Metzner Send message Joined: 3 Jul 02 Posts: 1256 Credit: 13,565,513 RAC: 13 |
This simply means it is getting warmer/spring/summer in the northern hemisphere and the people should stop brutally overclocking their GPUs or better cool them down to healthy values. I see the same on Nvidia hardware as well... :/ Aloha, Uli |
TBar Send message Joined: 22 May 99 Posts: 5204 Credit: 840,779,836 RAC: 2,768 |
driver: 1.4.1734 If you look back to a few days after the cal_ati App was released, almost a year ago, you will see where I reported the App Doesn't Work with Driver 1.4.1734. It's way back there. This thread is more recent, Problems with GPU computing on Mobility Radeon HD 3650 The Legacy Driver works fine with the Regular AstroPulse App. It's the CAL_ATI App that has the problems. Most of them end up as this one... I suppose that driver might work on some machines running the CAL App, but, I haven't seen any. |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Not to keep bashing ATI or anything... but I have noticed recently that there seem to be a lot more errors from ATI cards than there have been for the past few months. Maybe warmer weather.. maybe a new driver update. Not really sure what it is. Just on the first page of tasks for my main cruncher.. 1463876660 - error while computing - ati_opencl_100 1479857816 - error while computing - opencl_ati_100 1481314966 - error while computing - cal_ati 1481316282 - error while computing - cal_ati 1479309276 - error while computing - cal_ati It is easier to find such WUs in batches of re-sends. Most re-sends that I get are just "validation inconclusive" and need a third result for a confirmation, and pretty much over the past few months.. all three end up getting credit. Rarely does one get marked as invalid. So.. I don't know what's to blame for the sudden influx of ATI errors lately. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
©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.