This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: ldq and stq on UltraSparc I and II
- From: Jakub Jelinek <jakub at redhat dot com>
- To: "David O'Brien" <obrien at FreeBSD dot org>
- Cc: gcc at gcc dot gnu dot org, davem at redhat dot com, rth at redhat dot com
- Date: Tue, 30 Apr 2002 23:54:17 +0200
- Subject: Re: ldq and stq on UltraSparc I and II
- References: <20020430141112.A78266@dragon.nuxi.com>
- Reply-to: Jakub Jelinek <jakub at redhat dot com>
On Tue, Apr 30, 2002 at 02:11:12PM -0700, David O'Brien wrote:
> Dave/Richard,
>
> I found that GCC 3.1 uses ldq and stq to load long doubles w/HARD_QUAD.
> The problem is UltraSparc I and II CPU's do not have the instructions in
> silicon. FreeBSD has now emulated them, but of course there is a
> performance hit. Should the sparc description be changed to not use
> these CPU's? Or should -mcpu's possible values be expanded for greater
> granularity on modern [UltraSparc] processors?
What I don't understand is if you emulate hard quad instructions
in the kernel, what's the problem of just taking the emulation code, add
wrappers to match the _Qp_* calling conventions and put it into libc.
Jakub