how bessel function work?

Accelerated Computing CUDA CUDA Programming and Performance
21

Higher orders of jn() seem to work just fine. So you should be able to use your own wrapper function that incorporates the suggested workaround:

double my_jn (int order, double a)
{ 
   double res;
   if (order == 0) {
      res = j0 (a);
   } else if (order == 1) {
      res = j1 (a);
   } else {
      res = jn (order, a);
   }
   return res;
}
22

Thanks for reporting this. As a workaround, please use j0(x) instead of jn(0,x) as njuffa suggested earlier. Note that the same problem applies to jn(1,x); in CUDA 5.5 and earlier, you will need to use j1(x) instead.

We will correct these to be properly equivalent in a future release.

EDIT: Sorry for the duplication; I hadn’t seen the second page of followups before posting my reply.

23

Thanks a lot :)