On 6 February 2010 11:37, Claus Assmann <ca+OpenBSD_tech@esmtp.org> wrote:
quoted text
>
> Putting that kind of "optimization" into programs that read/write
> large amount of data seems like the wrong way to go. It belongs in
> a central place.
>
> (That's just a comment from a clueless bystander...)
>

It belongs in *both* places. and the central place can do a better job
with better hints from userland.

There is a balance to be struck between doing things intelligently at
the source, and doing things with a central optimization.

If you go too far towards central optimization you get bloat like GCC
4 centrally..