16ja12ab.20567.20407.438086664202.12.0

Noticed this WU resulted in an error on my GPU running Lunatics.
Processed OK on a system running stock on the CPU.
Resulted in an error on a GPU running CUDA50 on stock.


Result that completed without error,

<core_client_version>7.4.36</core_client_version>
<![CDATA[
<stderr_txt>
setiathome_v7 7.00 DevC++/MinGW/g++ 4.5.2
libboinc: 7.1.0

Work Unit Info:
...............
WU true angle range is : 260.202393
Optimal function choices:
--------------------------------------------------------
name timing error
--------------------------------------------------------
v_BaseLineSmooth (no other)
v_avxGetPowerSpectrum 0.000044 0.00000
avx_ChirpData_a 0.002533 0.00000
v_avxTranspose4x16ntw 0.000642 0.00000
BH SSE folding 0.000333 0.00000
SETI@Home Informational message -9 result_overflow
NOTE: The number of results detected equals the storage space allocated.

Flopcounter: 3770522828.539515

Spike count: 29
Autocorr count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
08:27:42 (3676): called boinc_finish



On the CUDA devices

<core_client_version>7.0.64</core_client_version>
<![CDATA[
<message>
too many boinc_temporary_exit()s
</message>
<stderr_txt>



Followed with this, repeated about 36-38 times.

Priority of process set to BELOW_NORMAL (default) successfully
Priority of worker thread set successfully

setiathome enhanced x41zc, Cuda 5.00

Detected setiathome_enhanced_v7 task. Autocorrelations enabled, size 128k elements.
Work Unit Info:
...............
WU true angle range is : 260.202393

Kepler GPU current clockRate = 1163 MHz

re-using dev_GaussFitResults array for dev_AutoCorrIn, 4194304 bytes
re-using dev_GaussFitResults+524288x8 array for dev_AutoCorrOut, 4194304 bytes
Thread call stack limit is: 1k
Error on call (cudaMemcpy(TripletResults, dev_TripletResults, 2 * grid.x * block.x * grid.y * block.y * sizeof(*dev_TripletResults), cudaMemcpyDeviceToHost)), file c:/[Projects]/__Sources/sah_v7_opt/Xbranch/client/cuda/cudaAcc_pulsefind.cu, line 318: invalid argument
Exiting
cudaAcc_free() called...
cudaAcc_free() running...
cudaAcc_free() PulseFind freed...
cudaAcc_free() Gaussfit freed...
cudaAcc_free() AutoCorrelation freed...
cudaAcc_free() DONE.
Cuda sync'd & freed.
Preemptively acknowledging a safe temporary exit->
Exit Status: 0
boinc_exit(): requesting safe worker shutdown ->
boinc_exit(): received safe worker shutdown acknowledge ->
Cuda threadsafe ExitProcess() initiated, rval 0
setiathome_CUDA: Found 2 CUDA device(s):
Device 1: GeForce GTX 750 Ti, 2048 MiB, regsPerBlock 65536
computeCap 5.0, multiProcs 5
pciBusID = 2, pciSlotID = 0
Device 2: GeForce GTX 750 Ti, 2048 MiB, regsPerBlock 65536
computeCap 5.0, multiProcs 5
pciBusID = 1, pciSlotID = 0
In cudaAcc_initializeDevice(): Boinc passed DevPref 1
setiathome_CUDA: CUDA Device 1 specified, checking...
Device 1: GeForce GTX 750 Ti is okay
SETI@home using CUDA accelerated device GeForce GTX 750 Ti
pulsefind: blocks per SM 4 (Fermi or newer default)
pulsefind: periods per launch 100 (default)

---

Grant
Darwin NT

A problem Wu causing an application problem, two Cuda hosts report the same problem,

the Wu itself and it's download url:

http://setiathome.berkeley.edu/workunit.php?wuid=1795270232

http://setiathome.berkeley.edu/sah/download_fanout/287/16ja12ab.20567.20407.438086664202.12.0

setiathome enhanced x41zc, Cuda 5.00

Detected setiathome_enhanced_v7 task. Autocorrelations enabled, size 128k elements.
Work Unit Info:
...............
WU true angle range is : 260.202393
re-using dev_GaussFitResults array for dev_AutoCorrIn, 4194304 bytes
re-using dev_GaussFitResults+524288x8 array for dev_AutoCorrOut, 4194304 bytes
Thread call stack limit is: 1k
Error on call (cudaMemcpy(TripletResults, dev_TripletResults, 2 * grid.x * block.x * grid.y * block.y * sizeof(*dev_TripletResults), cudaMemcpyDeviceToHost)), file c:/[Projects]/__Sources/sah_v7_opt/Xbranch/client/cuda/cudaAcc_pulsefind.cu, line 318: invalid argument
Exiting
cudaAcc_free() called...
cudaAcc_free() running...
cudaAcc_free() PulseFind freed...
cudaAcc_free() Gaussfit freed...
cudaAcc_free() AutoCorrelation freed...
cudaAcc_free() DONE.
Cuda sync'd & freed.
Preemptively acknowledging a safe temporary exit->
Exit Status: 0
boinc_exit(): requesting safe worker shutdown ->
boinc_exit(): received safe worker shutdown acknowledge ->
Cuda threadsafe ExitProcess() initiated, rval 0

Claggy

It's a known problem, I've reported it in the CA thread, and attached the Wu.

Claggy

It's a known problem, I've reported it in the CA thread, and attached the Wu.

Claggy

Thanks for that.

---

Grant
Darwin NT