OpenMP for Accelerators
Cray Inc., 380 Jackson Street, Suite 210 St. Paul, MN
OpenMP in the Petascale Era, Lecture Notes in Computer Science, Volume 6665/2011, 108-121, 2011
@article{beyer2011openmp,
title={OpenMP for Accelerators},
author={Beyer, J. and Stotzer, E. and Hart, A. and de Supinski, B.},
journal={OpenMP in the Petascale Era},
pages={108–121},
year={2011},
publisher={Springer}
}
OpenMP [14] is the dominant programming model for shared-memory parallelism in C, C++ and Fortran due to its easy-to-use directive-based style, portability and broad support by compiler vendors. Compute-intensive application regions are increasingly being accelerated using devices such as GPUs and DSPs, and a programming model with similar characteristics is needed here. This paper presents extensions to OpenMP that provide such a programming model. Our results demonstrate that a high-level programming model can provide accelerated performance comparable to that of hand-coded implementations in CUDA.
October 21, 2011 by hgpu
