Re: compilation architecture

[John Reiser <jreiser BitWagon com>]

> Don't be silly. Try some > i386 distro, and look at the difference.

The rule is:  Anyone who proposes a change because of performance,
must supply *measurements* which support the change.
The measurements must be reproducible on other machines
by other members of the community, so the environment and
test procedure must be well-specified, too.

--