Problem with running code with double precision values Double precision gives wrong result

I am trying to run code with double precision on CUDA, but get wrong result. nvcc compiles the code correctly but while executing it on GPU there seems to be some problem.
The code for single precision works fine.
I am using Fedora 10 (Linux version on 64 bit AMD with Tesla c1060 GPU.
Feel free to discuss your views about this. Any help will be greatly appreciated.

Do you have a device that’s compute capability 1.3?

Are you compiling for doubles?

Thanks for the reply. I’ll try it out. I am compiling my code for the double.