[AMDGPU][Libomptarget] Rework logic for locating kernarg pools

Previous logic was to always use the first kernarg pool found to allocate
kernel args. This patch changes this to use only the kernarg pool which
has non-zero size. This logic is also reworked to not use any globals.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D103600