\lstinputlisting[language={}]{strncpy.c}
\begin{itemize}
- \item "TODO
+ \item two simple-looking for-loops, unfortunately sequentially
+ data-dependent in the first.
+ \item Power ISA added a hard-coded variant of this inner
+ data-dependent capacity into VSX - only for strcpy!
+ \item even the null-ing part is not straightforward as
+ it could be mis-aligned compared to the VSX width.
+ \item end-result is that assembler-optimised strncpy on Power
+ ISA v3.0 is a whopping 240 instructions. SVP64 is 10
\end{itemize}
}