Feature #2934

Updated by Alan Gray about 1 year ago

Implement and improve the GPU version of position buffer operations. Gerrit change 9169 implements the functionality, and a follow-up change will improve as below.

* -Use Use pinned host vectors for grid and gridset arrays and remove explicit cudahostregister/unregister calls in init fn- fn
* -Replace Replace allocatedevicebuffer with reallocatedevicebuffer in init fn- fn
* -Improve Improve variable naming in init and buffer ops fns- fns
* -Fix Fix issue with position buffer pinning to allow use of gmx api for memcpy- memcpy
* Implement sync point between PME and NB streams.
* Improve mechanism for deciding if position buffer needs to be
copied to GPU in advance of buffer op