OpenACC

OpenACC is a programming standard for parallel computing developed by Cray, CAPS, Nvidia and PGI. The standard is designed to simplify parallel programming of heterogeneous CPU/GPU systems.^[1] Like in OpenMP, the programmer can annotate C, C++ and Fortran source code to identify the areas that should be accelerated using PRAGMA compiler directives and additional functions.^[2] Unlike OpenMP, code can be started not only on CPU, but also on GPU.

Compiler support

Suport of OpenACC is planned in compilers from PGI, Cray, and CAPS^[3]

Example

OpenACC defines some pragmas, for example:

#pragma acc region

References

1. ^ . http://www.theinquirer.net/inquirer/news/2124878/nvidia-cray-pgi-caps-launch-openacc-programming-standard-parallel-computing. 
2. ^ http://www.openacc-standard.org/Downloads/OpenACC.1.0.pdf?attredirects=0&d=1
3. ^ http://www.xbitlabs.com/news/other/display/20111116234815_OpenACC_Standard_to_Help_Developers_to_Take_Advantage_of_GPU_Compute_Accelerators.html

External links

• http://www.openacc-standard.org/