Clang is less agressive than nvccnvcc, so number of functions did not getn
inlined into the kernel by default. That prevented SROA from eliminating
loads/stores to temporary buffers and resulted in abysmal performance.
Replaced inline with __forceinline__ to ensure that we do inline the
functions necessary for optimal performance.
Unlike nvcc, clang always sees both host and device-side code during
compilation. CUDA_LOG macro is used in both host and device code, so when it
expanded to contain device-only code, that resulted in errors when it was used
from the host-side functions.
In order to make CUDA_LOG work with clang it was split into two parts -- a pair
of target-attribute-based overloaded functions that perform host or device
specific parts of logging, and a printf which works on both sides.
