Optimize performance of memset() and memcpy()

Builds upon the approach taken by the x86 version of k_memset()
and k_memcpy() APIs, which uses word-sized operations for greater
efficiency when manipulating large buffers. The algorithms used
here are architecture-independent.

Change-Id: I01ea8b22c8e6028f881e9b61ccc3a01e8ba4c02b
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
1 file changed