|
| file | builtins.cuh |
| | Templated, uniformly-named C++ functions wrapping single PTX instructions (in a dedicated builtins namespace).
|
| |
| file | common.cuh |
| | Type-generic wrappers for CUDA atomic operations.
|
| |
| file | constexpr_math.cuh |
| | mathematical functions (mostly very-simple ones) implemented using compile-time-executable code.
|
| |
| file | grid_info.cuh |
| | Information regarding the current kernel's launch grid and the calling thread's positions within it.
|
| |
| file | math.cuh |
| | Templatized mathematical function definitions for integer and floating-point types.
|
| |
| file | miscellany.cuh |
| | Miscellaneous functions provided by cuda-kat which are not a good fit in any other header.
|
| |
| file | non-builtins.cuh |
| | Templated, uniformly-named C++ functions wrapping what should have been single PTX - but aren't (in a dedicated non_builtins namespace).
|
| |
| file | ptx.cuh |
| | Wrapper functions for single PTX instructions — using inline PTX assembly — which are not already available in the official CUDA includes.
|
| |
| file | shared_memory.cuh |
| | Utility code for working with (mostly dynamic) shared memory in device-side CUDA functions.
|
| |
| file | shuffle.cuh |
| | Templated warp-shuffle operation variants.
|
| |
| file | time.cuh |
| | CUDA device-side functions having to do with timing and the hardware clock.
|
| |
