Hi

I have seen two WU's that falls back to cpu mode even if it's not a VLAR..

Check output below..

setiathome_CUDA: CUDA Device 5 specified, checking...
   Device 5: GeForce GTX 295 is okay
SETI@home using CUDA accelerated device GeForce GTX 295
Rise priority modification by Raistmer based on rev400 of SETI@home sources
VLAR autokill mod from Crunch3rPriority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 939261952	 free GPU memory 78420224
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 
'd:/BTR/seticuda/seti_boinc/client/cuda/cudaAcc_fft.cu' in line 49 : out of memory.
setiathome_CUDA: CUDA runtime ERROR in plan FFT. Falling back to HOST CPU processing...
setiathome_enhanced 6.02 Visual Studio/Microsoft C++
libboinc: 6.3.22

Work Unit Info:
...............
WU true angle range is :  1.418024
Optimal function choices:
-----------------------------------------------------
name                
-----------------------------------------------------
              v_BaseLineSmooth (no other)
            v_GetPowerSpectrum 0.00015 0.00000 
                   v_ChirpData 0.01623 0.00000 
                  v_Transpose4 0.00845 0.00000 
               FPU opt folding 0.00206 0.00000 

Flopcounter: 5863109275331.002900

Spike count:    0
Pulse count:    0
Triplet count:  0
Gaussian count: 0
called boinc_finish

</stderr_txt>
]]>

Wonder how comes that it states no memory available when there are 770Mb of free gpu memory?!

Kind Regards Vyper

---

_________________________________________________________________________
Addicted to SETI crunching!
Founder of GPU Users Group

Wonder how comes that it states no memory available when there are 770Mb of free gpu memory?!

And you know that for a fact, cos you have something check how much memory is actually being used, or is that your guess as Seti should use some 200MB of the 895MB that the card has? And that's 200MB+ per task, per GPU, so 2 GPUs = 400MB+ ...

Two tasks getting stuck eats up over 400MB of memory, leaving you with approx. 490MB for the next two tasks, which may want to start at the start of memory, find it blocked by other tasks and end up crashing.

Just reboot the computer to clear the VRAM.

---

Total GPU memory 939261952 free GPU memory 78420224

He may be running with this info but that looks like only 78 mb of free memory

---

In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope

Sorry my bad.. Didn't notice that it occupied whole ram?!

72 mb free gpuram..

Must check that particular gpuboard so it doesn't overheat or anything causing corruptions..

Thanks for noticing..

Kind regards Vyper

---

_________________________________________________________________________
Addicted to SETI crunching!
Founder of GPU Users Group

I had to run the numbers twice. I thought I had missed a digit as well

---

In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope

@ -= Vyper =-

Which Raistmer version you let run?


@ all

I had also some Out Of Memory errors..
But I guess with the system RAM.

http://setiathome.berkeley.edu/result.php?resultid=1211721515

http://setiathome.berkeley.edu/result.php?resultid=1206226503


I have 2 x 1 GB sticks installed.
Maybe it have something to do with the settings in Windows?

Message 876871

I have the settings to:
'Background services' and 'System cache'.

[Average RAM usage: ~ 600 - 700 MB]

---