What I was asking about is:
http://gcc.gnu.org/onlinedocs/gcc-4....ml#ARM-Options
Ref: Option -mfpu=
Note that gcc will not autovectorize unless -funsafe-math-optimizations is also passed.
Also:
http://gcc.gnu.org/onlinedocs/gcc-4....tor-Extensions
__AND__ I am not sure if byte arrays ever get "autovectorized" without special declarations in the code such as described above. (for ARM, I do know how to do it for MIPS with/without the DSP units).
But anyhow -
Don't waste any time on this question, I will stumble on the answer RSN myself.