Received from Francis on Thu, Aug 04, 2011 at 06:07:40AM EDT:
> Hi everyone,
>
> I'm wondering how I can use CUDA C math functions (compiled by adding
> -use_fast_math to nvcc) in PyCUDA if I have a source module with a function
> such as ceilf( )? I think this could be the source of my program's errors.
>
> Best regards,
> ./francis
What errors are you observing? You should be able to call ceilf() and
friends directly in your kernels without any unusual settings.
L.G.
_______________________________________________
PyCUDA mailing list
[email protected]
http://lists.tiker.net/listinfo/pycuda
