Message boards :
Number crunching :
GTX 295
Message board moderation
Author | Message |
---|---|
Tim Send message Joined: 19 May 99 Posts: 211 Credit: 278,575,259 RAC: 0 |
Hello to all.. Today I install one more GTX 295 to my rig with id 5867601. At the very beginning the card is sending computation errors, so i removed it from the system for now. Any ideas why is that? All gpus are stock timings, EVGA, no dust in it. |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14649 Credit: 200,643,578 RAC: 874 |
With (at that time) five CUDA compute resources in a single host, you probably ran out of a key resource - I'm guessing kernel mode CPU memory, from what I've read from the developers. The errors start with Cuda error 'cudaMemcpy(&flags, dev_find_pulse_flag, sizeof(*dev_find_pulse_flag), cudaMemcpyDeviceToHost)' in file 'c:/[Projects]/X_CudaMB/client/cuda/cudaAcc_pulsefind.cu' in line 1614 : unspecified launch failure. on the sample I checked. This is a highly technical area - I suggest you PM jason_gee, who wrote the app you're using. |
SupeRNovA Send message Joined: 25 Oct 04 Posts: 131 Credit: 12,741,814 RAC: 0 |
you mean you install one more 285 card ? not 295 ? |
Tim Send message Joined: 19 May 99 Posts: 211 Credit: 278,575,259 RAC: 0 |
you mean you install one more 285 card ? not 295 ? I install one more GTX 295. |
SupeRNovA Send message Joined: 25 Oct 04 Posts: 131 Credit: 12,741,814 RAC: 0 |
in your id stays they are 4 x 285 that is why i ask |
Tim Send message Joined: 19 May 99 Posts: 211 Credit: 278,575,259 RAC: 0 |
in your id stays they are 4 x 285 I am using 2 285's and 1 295. I removed the spare 295 as fault. |
Sutaru Tsureku Send message Joined: 6 Apr 07 Posts: 7105 Credit: 147,663,825 RAC: 5 |
in your id stays they are 4 x 285 BOINC don't report the grafic cards correct (or it's wrong displayed in the online overview (server software)). Tim have as GPU#0 and #1 a GTX285 each. GPU#2 and #3 is a GTX295. It's displayed [4] GTX285. But this mean, this is the first grafic card (GPU#0) and all other counted/added GPU chips. It's a pity that the grafic cards are not shown as: [2] GTX285 [1] GTX295 (IMHO, this would be the best) or chips: [2] GTX285 [2] GTX295 Maybe someone could/should contact the DEVs (or admins).. - Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. - |
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4 |
in your id stays they are 4 x 285 If you look at the stderr.txt output from one of Tim's GPU results you see: <core_client_version>6.10.60</core_client_version> <![CDATA[ <stderr_txt> setiathome_CUDA: Found 4 CUDA device(s): Device 1: GeForce GTX 285, 1023 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 30 clockRate = 1476000 Device 2: GeForce GTX 285, 1023 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 30 clockRate = 1476000 Device 3: GeForce GTX 295, 895 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 30 clockRate = 1242000 Device 4: GeForce GTX 295, 895 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 30 clockRate = 1242000 In cudaAcc_initializeDevice(): Boinc passed DevPref 2 setiathome_CUDA: CUDA Device 2 specified, checking... Device 2: GeForce GTX 285 is okay SETI@home using CUDA accelerated device GeForce GTX 285 Priority of process raised successfully Priority of worker thread raised successfully Cuda Active: Plenty of total Global VRAM (>300MiB). All early cuFft plans postponed, to parallel with first chirp. ) _ _ _)_ o _ _ (__ (_( ) ) (_( (_ ( (_ ( not bad for a human... _) Multibeam x38g Preview, Cuda 3.20 Legacy setiathome_enhanced V6 mode. Work Unit Info: ............... WU true angle range is : 0.432804 Flopcounter: 33073003624989.656000 Spike count: 4 Pulse count: 0 Triplet count: 0 Gaussian count: 0 Worker preemptively acknowledging a normal exit.-> called boinc_finish boinc_exit(): requesting safe worker shutdown -> boinc_exit(): received safe worker shutdown acknowledge -> </stderr_txt> Claggy |
©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.