Same error on multiple machine with same workunit?

Author	Message
bupjae Send message Joined: 10 Mar 02 Posts: 1 Credit: 1,919,961 RAC: 0	Message 1179063 - Posted: 18 Dec 2011, 13:42:57 UTC Last modified: 18 Dec 2011, 13:43:08 UTC
Some of my workunits reported error, so I want to examine what happened. According to result of this unit, I think there might be something wrong with cuda application, but I'm not sure. Is anyone have same result like this? Could it be a result of some program bug?
ID: 1179063 ·

perryjay Send message Joined: 20 Aug 02 Posts: 3359 Credit: 9,659,000 RAC: 10,251	Message 1179088 - Posted: 18 Dec 2011, 17:24:00 UTC - in response to Message 1179063.
In this case, it is the one running stock and getting what looks like a good result that is actually wrong. He is running Debian with the old 6.4.5 BOINC client. The rest of the wingmen found too many triplets and the WU will probably run through a couple more people before reporting too many errors and be wiped. ____________ PROUD MEMBER OF Team Starfire World BOINC
ID: 1179088 ·

BilBg Send message Joined: 27 May 07 Posts: 2023 Credit: 3,035,480 RAC: 6,231	Message 1179434 - Posted: 20 Dec 2011, 0:37:01 UTC - in response to Message 1179063. Last modified: 20 Dec 2011, 0:53:19 UTC
The Linux CPU SETI@home Enhanced v6.03 (stock) validated OK against Windows 7 GPU NVIDIA GeForce GTX 260 (optimized) SETI@home Enhanced Anonymous platform (NVIDIA GPU) - Lunatics Multibeam x38g Preview, Cuda 3.20 ( It's known that stock CUDA apps (they are older) are more prone to "-12 error": SETI@home error -12 Unknown error cudaAcc_find_triplets erroneously found a triplet twice in find_triplets_kernel than the Lunatics optimized CUDA apps (actively developed, newer, faster) ) Stderr output <core_client_version>6.4.5</core_client_version> <![CDATA[ <stderr_txt> setiathome_enhanced 6.03 Revision: 306 g++ (Debian 4.3.1-6) 4.3.1 libboinc: BOINC 6.3.8 Work Unit Info: ............... WU true angle range is : 2.724785 Optimal function choices: ----------------------------------------------------- name ----------------------------------------------------- v_BaseLineSmooth (no other) v_vGetPowerSpectrumUnrolled 0.00045 0.00000 v_ChirpData 0.01915 0.00000 v_vTranspose4x8ntw 0.01132 0.00000 BH SSE folding 0.00141 0.00000 Flopcounter: 10432754946380.425781 Spike count: 4 Pulse count: 0 Triplet count: 7 Gaussian count: 0 called boinc_finish </stderr_txt> ]]> Stderr output <core_client_version>6.12.34</core_client_version> <![CDATA[ <stderr_txt> setiathome_CUDA: Found 2 CUDA device(s): Device 1: GeForce GTX 260, 842 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 27 clockRate = 1350000 Device 2: GeForce GTX 260, 842 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 27 clockRate = 1350000 In cudaAcc_initializeDevice(): Boinc passed DevPref 2 setiathome_CUDA: CUDA Device 2 specified, checking... Device 2: GeForce GTX 260 is okay SETI@home using CUDA accelerated device GeForce GTX 260 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 : 2.724785 Flopcounter: 10432115851830.561000 Spike count: 4 Pulse count: 0 Triplet count: 7 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> ]]> ____________ - ALF - "Find out what you don't do well ..... then don't do it!" :)
ID: 1179434 ·

The Linux CPU SETI@home Enhanced v6.03 (stock) validated OK against
Windows 7 GPU NVIDIA GeForce GTX 260 (optimized) SETI@home Enhanced Anonymous platform (NVIDIA GPU) - Lunatics Multibeam x38g Preview, Cuda 3.20

( It's known that stock CUDA apps (they are older) are more prone to "-12 error":
SETI@home error -12 Unknown error
cudaAcc_find_triplets erroneously found a triplet twice in find_triplets_kernel

than the Lunatics optimized CUDA apps (actively developed, newer, faster)
)

Stderr output <core_client_version>6.4.5</core_client_version> <![CDATA[ <stderr_txt> setiathome_enhanced 6.03 Revision: 306 g++ (Debian 4.3.1-6) 4.3.1 libboinc: BOINC 6.3.8 Work Unit Info: ............... WU true angle range is : 2.724785 Optimal function choices: ----------------------------------------------------- name ----------------------------------------------------- v_BaseLineSmooth (no other) v_vGetPowerSpectrumUnrolled 0.00045 0.00000 v_ChirpData 0.01915 0.00000 v_vTranspose4x8ntw 0.01132 0.00000 BH SSE folding 0.00141 0.00000 Flopcounter: 10432754946380.425781 Spike count: 4 Pulse count: 0 Triplet count: 7 Gaussian count: 0 called boinc_finish </stderr_txt> ]]> Stderr output <core_client_version>6.12.34</core_client_version> <![CDATA[ <stderr_txt> setiathome_CUDA: Found 2 CUDA device(s): Device 1: GeForce GTX 260, 842 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 27 clockRate = 1350000 Device 2: GeForce GTX 260, 842 MiB, regsPerBlock 16384 computeCap 1.3, multiProcs 27 clockRate = 1350000 In cudaAcc_initializeDevice(): Boinc passed DevPref 2 setiathome_CUDA: CUDA Device 2 specified, checking... Device 2: GeForce GTX 260 is okay SETI@home using CUDA accelerated device GeForce GTX 260 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 : 2.724785 Flopcounter: 10432115851830.561000 Spike count: 4 Pulse count: 0 Triplet count: 7 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> ]]>