NVIDIA Opens Up OpenACC Toolkit, But Only For Academia

NVIDIA is announcing today the release of a new OpenACC Toolkit for enhancing GPU computing, but sadly it's only free in the long-run for academia developers and researchers.

The NVIDIA blog post mentions, "Computing cores aren’t getting faster. Rather processors are getting more parallel. This has been the trend for the last decade, and is likely to continue. If you’re a researcher, you can take advantage of parallel computing to accelerate your scientific application with OpenACC. It’s an approach that’s resulted in big leaps forward for many of your colleagues. The HPC community has embraced OpenACC because it simplifies parallel programming for modern processors, like GPUs. Indeed, 8,000-plus researchers and scientists have already adopted the OpenACC programming standard since it was developed four years ago by leading HPC vendors like Cray, PGI and NVIDIA. To get this power in the hands of more researchers, we’re releasing our NVIDIA OpenACC Toolkit. It’s a free, all-in-one suite of OpenACC parallel programming tools."

The only downdside is that this new toolkit, which features the PGI Accelerator Fortran/C Workstation Compiler Suite for Linux with OpenACC 2.0 support, is only free to academia developers and researchers. Commercial users just having a ninety-day free trial. Of course, for now you also need to be using the proprietary NVIDIA Linux graphics driver with there being no CUDA or OpenACC support within the open-source Nouveau driver but just limited support for OpenCL via the Gallium3D Clover state tracker.

For an OpenACC 2.0 compiler that's free for all and fully open-source, the GCC support for OpenACC/OpenMP with (GPU) device offloading continues to be improved in GCC 5 and newer.