This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [RFC] PowerPC DFA description
- From: Daniel Egger <degger at fhm dot edu>
- To: David Edelsohn <dje at watson dot ibm dot com>
- Cc: Vladimir Makarov <vmakarov at redhat dot com>, dalej at apple dot com,Daniel Berlin <dan at dberlin dot org>,GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: 30 May 2002 00:24:46 +0200
- Subject: Re: [RFC] PowerPC DFA description
- References: <200205292215.SAA29682@makai.watson.ibm.com>
Am Don, 2002-05-30 um 00.15 schrieb David Edelsohn:
> Maybe we need separate automata for each Altivec function unit,
> but I don't understand your need to add vec_permute2.
In contrast to the 7450 which has four AlitVec units (VUI1, VUI2, VFPU
and VPU) the 7400 has two units only (VALU and VPU) the former of which
having three subunits. Since I couldn't imagine any better way to model
that I followed the pattern I though I found in your description by
adding a new automaton for the completely seperate vector unit.
But then again I'm just a beginner concerning DFA. :)
--
Servus,
Daniel