Can anyone guide me as to where to go and how to enable the use of doubles in visual studio for kernels in CUDA. In a previous post a guy said i should compile with -arch sm_13 but I have no clue where to put this line. Im still a n00b with this programming in CUDA. I have a GTX 260 so it does support doubles.
I’m guessing you’re using Visual Studio and starting from an SDK sample. Right-click on the main .cu file in VS. It’ll be the one that doesn’t have a tiny red sign on it. Then in the custom build step you’ll see “nvcc” being called with various command line options. Put it there.
Thanx alot dude. much appreciated