Unroll array copy/clone primops in the native and LLVM code generators
#4928 (closed) added inline primops for copying and cloning arrays. It would be beneficial to create an unrolled loop, instead of a call to
memcpy, when the copy is of a statically know small size. I suggest we use an unrolling threshold of 128 bytes, as that's what both GCC and LLVM use for the same optimization.