This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: PATCH: tune ARM's rtx_costs function
- From: Richard Earnshaw <rearnsha at arm dot com>
- To: James Lemke <jim at wasabisystems dot com>
- Cc: Richard dot Earnshaw at arm dot com, Ian Lance Taylor <ian at wasabisystems dot com>, Ben Elliston <bje at wasabisystems dot com>, gcc-patches at gcc dot gnu dot org
- Date: Thu, 09 Oct 2003 09:52:28 +0100
- Subject: Re: PATCH: tune ARM's rtx_costs function
- Organization: ARM Ltd.
- Reply-to: Richard dot Earnshaw at arm dot com
> > But unless you are forcing the compilation levels, that's going to use -O2
> > everywhere, which isn't interesting, since we always did use a new pseudo
> > at O2. It's compilation times at O0 and O1 that are interesting.
>
> For "time make CXXFLAGS_FOR_TARGET=-O1 all-target-libstdc++-v3" I get
> the following times.
>
> User time is slightly longer 251.75 vs 252.59 which is +0.33%.
> Noise level?
>
> Reference time with preserve_subexpressions_p ()..
> real 6m9.795s
> user 4m11.750s
> sys 1m48.330s
>
> Time without preserve_subexpressions_p ()..
> real 6m2.698s
> user 4m12.590s
> sys 1m46.170s
>
And at -O0?
R.