nvidia-cuda-tutorial
nvidia-cuda-tutorial copied to clipboard
Add section on preventing widening integer indices
The section on the widening on integer indices produced in a loop over a range seems to accidentally be missing - it should be just before the "Limiting register usage" section in session 2.
This section should explain the use of a while loop and explicit incrementing to generate indices that remain as int32 instead of being prone to widening to 64 bits as is the case with range.