libSCALE  0.2.0
A modern C++ CUDA API
Device Functions

Device-side APIs. More...

Modules

 Atomics
 Type-safe wrappers around the atomic operators found in GPU runtime APIs.
 
 Device Intrinsics
 These APIs provide direct (and usually non-portable) access to hardware features that are either not supported by the compiler (yet), or which manufacturers don't document.
 
 Lanemask Functions
 Functions for computing lane masks.
 
 Shuffle
 Generic warp shuffle support supporting arbitrary input types.
 
 Synchronisation Functions
 Access to the more elaborate syncthreads variants.
 

Detailed Description

Device-side APIs.