Message boards :
Number crunching :
Again -9 errors on GTX560Ti with optimized app.!
Message board moderation
Author | Message |
---|---|
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
Looking at results from my ATI host, I spotted this WU, <stderr_txt> setiathome_CUDA: Found 1 CUDA device(s): Device 1: GeForce GTX 560 Ti, 1023 MiB, regsPerBlock 32768 computeCap 2.1, multiProcs 8 clockRate = 1800000 setiathome_CUDA: CUDA Device 1 specified, checking... Device 1: GeForce GTX 560 Ti is okay SETI@home using CUDA accelerated device GeForce GTX 560 Ti Priority of process raised successfully Priority of worker thread raised successfully size 8 fft, is a freaky powerspectrum size 16 fft, is a cufft plan size 32 fft, is a cufft plan size 64 fft, is a cufft plan size 128 fft, is a cufft plan size 256 fft, is a freaky powerspectrum size 512 fft, is a freaky powerspectrum size 1024 fft, is a freaky powerspectrum size 2048 fft, is a cufft plan size 4096 fft, is a cufft plan size 8192 fft, is a cufft plan size 16384 fft, is a cufft plan size 32768 fft, is a cufft plan size 65536 fft, is a cufft plan size 131072 fft, is a cufft plan ) _ _ _)_ o _ _ (__ (_( ) ) (_( (_ ( (_ ( not bad for a human... _) Multibeam x32f Preview, Cuda 3.0 Work Unit Info: ............... WU true angle range is : 0.422232 SETI@Home Informational message -9 result_overflow NOTE: The number of results detected exceeds the storage space allocated. Flopcounter: 108133946757.611310 Spike count: 30 Pulse count: 0 Triplet count: 0 Gaussian count: 0 called boinc_finish </stderr_txt> ]]> Host 4335051, has made 172 errors, also -12 (0xfffffffffffffff4) and more errors, like Cuda error 'cufftExecC2C' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 102 : unspecified launch failure. Cuda error 'cudaAcc_GetPowerSpectrum_kernel' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_PowerSpectrum.cu' in line 56 : unspecified launch failure. Cuda error 'cudaAcc_GetPowerSpectrum_kernel' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_PowerSpectrum.cu' in line 56 : unspecified launch failure. Cuda error 'cudaAcc_summax32_kernel' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_summax.cu' in line 147 : unspecified launch failure. Cuda error 'cudaAcc_summax32_kernel' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_summax.cu' in line 147 : unspecified launch failure. Cuda error 'cudaMemcpy(PowerSpectrumSumMax, dev_PowerSpectrumSumMax, cudaAcc_NumDataPoints / fftlen * sizeof(*dev_PowerSpectrumSumMax), cudaMemcpyDeviceToHost)' in file 'd:/[Projects]/Berkeley/seti_cuda/seti_boinc/client/cuda/cudaAcc_summax.cu' in line 160 : unspecified launch failure. -1073741819 (0xffffffffc0000005), plus 462 invalids, well enough to send him a PM?! Hope someone will take a second look, although this is quite obvious. |
tbret Send message Joined: 28 May 99 Posts: 3380 Credit: 296,162,071 RAC: 40 |
It is hard to know what is going-on with Marc's computers with 560ti cards in them. Both are throwing-off invalid work. Just last night I discovered that one of my 560ti cards likes to throw invalid results after I run a specific application. My guess is that the application is causing the video driver to malfunction, so now I know to exit BOINC before starting the program and reboot before restarting BOINC. (if anyone cares - it's Roxio Creator 2011 Pro / Videowave) |
skildude Send message Joined: 4 Oct 00 Posts: 9541 Credit: 50,759,529 RAC: 60 |
Speculation. He's running the Lunatics CUDA app and not the Fermi app. In a rich man's house there is no place to spit but his face. Diogenes Of Sinope |
arkayn Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0 |
|
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
Well, looks like this isn't a FERMI app. can't remember them having AUTOKILL. resultid=2121977719. But, I could be wrong and appreciate, if someone else would comment on this one! Host 4202271. If I do Video-Editting jobs, I do turn off BOINC, as this is asking for trouble, IMHO. Although, BOINC and the CUDA or OpenCL app.'s, run at a lower priority, unless the cmd-line setting -HP, is used and shouldn't cause trouble??? I'm not sure about this. |
arkayn Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0 |
Well, looks like this isn't a FERMI app. can't remember them having AUTOKILL. That is definitely v12, not compatible. |
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
It is hard to know what is going-on with Marc's computers with 560ti cards in them. Both are throwing-off invalid work. I know the program, even used it, never caused trouble. The same goes for Pinnacle Studio 11. Something different or changed in GTX560Ti cards, what caused them to malfunction, but I haven't a clue as to what it can be. @ Arkayn, glad you recognized the v6, as I wasn't sure, IIRC, it's about a year ago, one should really pay more attention, when running 3rd party app.'s?! And I do hope, people who have trouble with 560Ti's or are running v6 on FERMI GPU, visit these forums and rase questions so it can be solved, it's such a waste of electicity, causes unnecessary faults, etc. etc. |
tbret Send message Joined: 28 May 99 Posts: 3380 Credit: 296,162,071 RAC: 40 |
Don't want to leave you with the wrong impression. I did suspend BOINC, but when I was done and BOINC came out of suspense it started giving errors. That did not happen with a GTX 460 BUT, I've updated to the newest driver since the 460 was in that computer. So the next time I did a little editing I shut BOINC down completely, and when I restarted it after I was done, it started making errors again. I rebooted and it has been working fine since. Something's hanging the new driver (is my guess). |
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
|
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
You made a double post, can't you just edit and then delete everything, or Or YOU simply could have red-x'd the post to inform the mods of the duplicate. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
You made a double post, can't you just edit and then delete everything, or Thanks Mark, never used it, a double post or something added in a second post, you can just simply delete the post, whitin an hour. Is that SETI@home, bound? I've editted post, made on Einstein@home, over 2 hours or even longer. [ADDED] I can edit or add something and the 3rd edit, I can delete, the whole post, which I'll now will try................. [ADDED] Well, you are right, if you delete everything, you have an 'empty post' which you can only 'post' , upload. But you get a screen, fill in your text I once cleared a post by using the Tab, you'll end up on 2 buttons, example OK and only a few words were written, also the first post! We are slowly drifting away from the Thread Title, Errors on 560Ti GPU and an incompatible case, a FERMI (GTX470) uses the v6 app. ;-) |
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
You made a double post, can't you just edit and then delete everything, or I know here in the Seti forums, 1 hour is the limit to edit a post. And I am not sure you can actually delete your own posts anymore.... At one time, you could delete the content and the post would delete itself. But the feature was being abused, and I think it was taken off the table. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Fred J. Verster Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 |
YES, I just tried it, but ONLY the FIRST post! I've never seen such a continuous and high throuput, or RAC Mark, impressive! Ten times the amount I do on SETI, but I do also other Projects, your mileage may vary, also, as they say. ;-) Although electricity is still cheaper, or better, less expensive, compaired to Europe, €0,45 per KWh, The Netherlands. In Europe, a lot of things are getting more expensive, computer hardware is only getting cheaper and better! You must have quite a high usage, with 4 rigs they use ~1400Watt, monitors not included, have 2 22'' [10:6] LCD SCREENS (1920 x 1280) and 1 CRT 15'' 1024 x 768, My first flatscreen (PACKARD BELL) has worked 5 years, it was already noticeble less bright, then half the screen was striped, a reBOOT, made clear that it didn't work at all and hooked up the CRT. Hmmm, Shall we return to the Thread Title................:) I noticed the high clock-speed, of the GTX560Ti 1.8GHz, my 470 is at 1.21GHz and GTX480 runs at 1.47GHz. temp is 78C. Rigs all fed with (cold)outside air and warm the room, in the process. And nVidias do run hot, well AMD/ATI also, but my 4850 gets 98C(doen't use it a.t.m.) The 2 ATI 5870 GPUs don't run past 72C . |
Spectrum Send message Joined: 14 Jun 99 Posts: 468 Credit: 53,129,336 RAC: 0 |
Strange as it is the one comp that I have with a singe 560Ti is running fine with the once in a blue moon ivalid result or error yet my other rig with the 2 vanilla 560's seems to be pumping out 20 to 25 invalid results a month or less depending on how long they stay on the server and all of the cards are running at out of the box speeds, still trying to figure out where the problem is! |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13736 Credit: 208,696,464 RAC: 304 |
Rails are stable? Sufficient cooling? Grant Darwin NT |
tbret Send message Joined: 28 May 99 Posts: 3380 Credit: 296,162,071 RAC: 40 |
Just did. Didn't see the double until now, but now I've added this post to tell you that so I've accomplished very little unless I also red x this one. |
Spectrum Send message Joined: 14 Jun 99 Posts: 468 Credit: 53,129,336 RAC: 0 |
CPU @ 67C GPU's @ 68-70C going to change out the TX750 Corsair PSU For a Cooler Master Silent ProM later on tonight and fit a H60 Corsair water cooler to the PSU, bummed that I couldn't get another Antec Kuhler620, put one in my older machine and got a temp drop of 20C and so quiet too! going to add a couple of 120mm fans to the case to improve airflow too and see what happens :) |
jason_gee Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 |
While you're there, reseat the cards in the PCIe slots :) Jason "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. |
Spectrum Send message Joined: 14 Jun 99 Posts: 468 Credit: 53,129,336 RAC: 0 |
Well all done (including reseating the cards) lets see what happens when the pendings clear ! |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13736 Credit: 208,696,464 RAC: 304 |
CPU @ 67C GPU's @ 68-70C going to change out the TX750 Corsair PSU For a Cooler Master Silent ProM later on tonight and fit a H60 Corsair water cooler to the PSU, bummed that I couldn't get another Antec Kuhler620, put one in my older machine and got a temp drop of 20C and so quiet too! going to add a couple of 120mm fans to the case to improve airflow too and see what happens :) Temperatures are OK & a 750W PSU should be up to it- i'd expect the actual load to be around 600W at most. I've got an i7 2600 with a GTX460 & it's pulling around 300W. Grant Darwin NT |
©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.