libSCALE  0.2.0
A modern C++ CUDA API
Modules
Here is a list of all modules:
[detail level 1234]
 Address-Space QualificationAddress space restriction specifiers for pointers
 AssertionsEnhanced CUDA assertions, including:
 Device FunctionsDevice-side APIs
 AtomicsType-safe wrappers around the atomic operators found in GPU runtime APIs
 Device IntrinsicsThese 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
 Texture IntrinsicsPlugging some holes in the NVIDIA® texture fetch API, and making it less annoying to use in template code
 Lanemask FunctionsFunctions for computing lane masks
 ShuffleGeneric warp shuffle support supporting arbitrary input types
 Synchronisation FunctionsAccess to the more elaborate syncthreads variants
 Host APIHost-side CUDA API (use instead of libcuda)
 ExceptionsException objects for errors from the GPU runtime API
 NVTX Tools ExtensionA (very cut-down) API wrapper for NVTX
 Named RequirementsSimilarly to the standard library, we define Named Requirements to specify constraints that must be satisfied by type parameters
 Utilities
 Memory Manipulation Utilities
 Smart Pointer UtilitiesUtilities for dealing with smart pointers
 DeletersSmart pointer deleter functions, suitable for use with STL smart pointers
 Type Traits