This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Optimal Optimizations: A Very Preliminary Report
- From: Michael Matz <matz at suse dot de>
- To: Nathanael Nerode <neroden at twcny dot rr dot com>
- Cc: gcc at gcc dot gnu dot org
- Date: Wed, 13 Aug 2003 00:38:35 +0200 (CEST)
- Subject: Re: Optimal Optimizations: A Very Preliminary Report
Hi,
On Tue, 12 Aug 2003, Nathanael Nerode wrote:
> (Incidentally, the evidence for that particular case indicates that
> -fschedule-insns should be abandoned entirely, while -fschedule-insns2
> should be standard.)
For this particular case! Scott is testing ooo architectures, which
generally do not benefit that greatly from scheduling anyway. The picture
is wholly different with in-order archs where pre-regalloc scheduling can
make a horribly high difference (if it's given that there is a reasonable
number of registers, so that scheduling does not interfere with regalloc
that much).
Actually for ooo arches the target cost function of pre-regalloc
scheduling should not be cycle length, but instead necessary register
count for evaluating the expressions. This helps much more on those
archs by making the problem of register allocation a bit easier. We
currently don't have such a scheduler, though.
Ciao,
Michael.