CUDA at 50%

[SoNic]

I have installed recently the unified appications on a new PC and CUDA units are always at 50% (1 CPU). On another C2D, it was  at that level just a few seconds at beginning and end.
Mu computer is this one:
http://setiathome.berkeley.edu/show_host_detail.php?hostid=5064535

Anybody has ideas why?

[SoNic]

What is this? Not enough memory?

setiathome_CUDA: CUDA Device 1 specified, checking...
   Device 1: Quadro FX 570 is okay
SETI@home using CUDA accelerated device Quadro FX 570
V12 modification by Raistmer
Priority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 268107776    free GPU memory 211175424
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 'd:/BoincSeti_Prog/sinbad_repositories/LunaticsUnited/SETI_CUDA_MB_exp/client/cuda/cudaAcc_fft.cu' in line 101 : feature is not yet implemented.
setiathome_CUDA: CUDA runtime ERROR in plan FFT. Falling back to HOST CPU processing...
Restarted at 1.37 percent.
After app init: total GPU memory 268107776    free GPU memory 211175424

[Josef W. Segur]

What is this? Not enough memory?

setiathome_CUDA: CUDA Device 1 specified, checking...
   Device 1: Quadro FX 570 is okay
SETI@home using CUDA accelerated device Quadro FX 570
V12 modification by Raistmer
Priority of worker thread rised successfully
Priority of process adjusted successfully
Total GPU memory 268107776    free GPU memory 211175424
...

Yep, needs nearly 220 MiB free GPU memory even though the application only allocates 89 MiB. Some others with 256 MB cards have found ways to reduce what's used for Windows, but it's a tight squeeze.
                                                                               Joe

[Raistmer]

What is this? Not enough memory?

setiathome_CUDA: CUDA Device 1 specified, checking...
Cuda error 'cufftPlan1d(&fft_analysis_plans[FftNum], FftLen, CUFFT_C2C, NumDataPoints / FftLen)' in file 'd:/BoincSeti_Prog/sinbad_repositories/LunaticsUnited/SETI_CUDA_MB_exp/client/cuda/cudaAcc_fft.cu' in line 101 : feature is not yet implemented.

I seen such error when used incorrect drivers. Update them, new CUFFT requires new drivers.