C++ Accelerated Massive Parallelism (C++ AMP) an API for GPGPU/APU/multi-core programming for C++ developers. It can target both discrete and integrated GPUs on Windows and Linux.
C++ AMP accelerates the execution of C++ code by taking advantage of the data-parallel hardware that's commonly present as a graphics processing unit (GPU) either integrated into the CPU or on a discrete graphics card. The C++ AMP programming model includes support for multidimensional arrays, indexing, memory transfer, and tiling. It also includes a mathematical function library. You can use C++ AMP language extensions to control how data is moved from the CPU to the GPU and back.
C++ AMP is an open specification with implementations on Windows with Visual C++ and DirectX and Linux with CLANG/LLVM and OpenCL. It will target GPUs which support DirectX 11 or OpenCL.