multiple errors when using cuda and svm

I have to paralelize a svm aplication, basically I have a vector and I must call the svm kernell in each element in a paralell way. So in my cuda kernell y have a call to the svm routine.
But cuda don’t support calling external functions from a kernel function.

Any idea or help to make it possible? I already try using http://mklab.iti.gr/project/GPU-LIBSVM but when I tried to compile it following the instructions it says the same error “calling a host function from a device function is not allowed”

Hola, hablas español? …yo también estoy trabajando con svm en cuda y quiero saber si existen librerías para utilizar svm’s en cuda, lo que tu estabas haciendo es programar la svm en cuda?

Hi, I don’t understand english very well, I would like to work with svm’s and cuda, you can help me in my works?