refs kylelutz/compute#9
device, context, and queue are initialized statically in `context_setup.hpp`.
With this change all tests are able to complete when an NVIDIA GPU is in
exclusive compute mode.
Side effect of the change:
Time for all tests to complete reduced from 15.71 to 13.03 sec Tesla C2075.
This removes the check for local_memory_size in test_kernel. The
local memory size differs between platforms and some (e.g. Intel)
don't report any local memory usage.
This fixes the check for the local memory size in the
get_work_group_info kernel test.
While the kernel only allocates 16 float's, some platforms
will use more local memory. This changes the test to check
for at least 16 float's worth of local memory.
