On Tue, 21 Jul 2015 12:29:21 -0700, Andy Lutomirski said:

> That's not what I meant.  We do something in the C code that tells the
> build step which way the initial state goes.  At link time, we make
> the initial state actually work like that.  Then, at run time, we can
> still switch it again if needed.

OK, that's something different than what I read the first time around.

I'm thinking that a good adjective would be "brittle", in the face of
recalcitrant GCC releases.  Look at the fun we've had over the years
getting things that *should* be fairly intuitive to work correctly (such
as "inline").

Having said that, if somebody comes up with something that actually
works, I'd be OK with it...

Attachment: pgpYvkJobctLv.pgp
Description: PGP signature

Reply via email to