Implementing a GPU-Portable Field Line Tracing Application with OpenMP Offload.

Accelerated computing is becoming more diverse as new vendors and architectures come into play. Although platform-specific programming models promise ease of development and better control over performance, they still restrict the portability of scientific applications. As the OpenMP offloading specification becomes adopted by more compilers, this programming model stands out as a vendor-neutral portable approach to heterogeneous programming. In this study, we port a plasma physics oriented field line tracing code from a CPU-based MPI+OpenMP approach to a GPU accelerated version, using OpenMP's offloading capabilities. We analyze GPU performance across different vendors with respect to the original CPU version and test both prescriptive and descriptive approaches to accelerator programming. A maximum 6x acceleration over the CPU implementation was achieved using OpenMP's high-level offloading directives. In addition, we demonstrate portability across three different vendor GPUs with no code modifications.