Hi guys :)
I’m really sorry for the very basic question but I cannot find a straight answer on any of the online resources I have checked.
I am writing some code in cuda that ‘ping pongs’ on two sets of data, reading from one and writing to the other.
What I need to know is does the following piece of code actually work on DEVICE pointers in cuda. This is memory that has already been allocated on the device. I call the below in a method at the start of each frame.
cData* temp = d_data; d_data= d_dataOld; d_dataOld= temp;
If not can you suggest alternatives to simply changing which pointers I send to the kernels - I prefer to avoid that method in order to keep the code easy to read!