[patch] adjust default nvptx launch geometry for OpenACC offloaded regions

[Tom de Vries]

On 06/20/2018 11:59 PM, Cesar Philippidis wrote:
> Now it follows the formula contained in
> the "CUDA Occupancy Calculator" spreadsheet that's distributed with CUDA.

Any reason we're not using the cuda runtime functions to get the
occupancy (see PR85590 - [nvptx, libgomp, openacc] Use cuda runtime fns
to determine launch configuration in nvptx ) ?

Thanks,
- Tom