Jan Vroonhof <vroonhof(a)math.ethz.ch> writes:
Footnotes:
[1] i.e. I am betting the compiler use a builtin memcmp. However
looking at the sparc output it seems that gcc doesn't always do
that.
That's not necessarily a bad thing. For instance, some sparcs support
special instructions set for graphics work, analogous to Intel's MMX.
On those systems the libc memcpy() function will use those
instructions and be significantly faster than the code produced by
Gcc. (Except for the funcall overhead.)