This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug middle-end/32396] [4.1/4.2/4.3 Regression] gcc uses 0 as altivec load/store index
- From: "pinskia at gcc dot gnu dot org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: 26 Dec 2007 01:25:35 -0000
- Subject: [Bug middle-end/32396] [4.1/4.2/4.3 Regression] gcc uses 0 as altivec load/store index
- References: <bug-32396-14709@http.gcc.gnu.org/bugzilla/>
- Reply-to: gcc-bugzilla at gcc dot gnu dot org
------- Comment #2 from pinskia at gcc dot gnu dot org 2007-12-26 01:25 -------
Hmm, This looks related to PR 34529. Since we allow base+const before reload
for vector moves, we then prop that into the move instruction. After reload,
we use an extra register to store the base+const but never move that add into
the move instruction with using the register for the constant. Also we never
do loop code motion after reload also so we never move the li instruction
outside of the loop.
--
pinskia at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |pinskia at gcc dot gnu dot
| |org
BugsThisDependsOn| |34529
Severity|enhancement |minor
Status|UNCONFIRMED |NEW
Ever Confirmed|0 |1
Keywords| |missed-optimization
Last reconfirmed|0000-00-00 00:00:00 |2007-12-26 01:25:35
date| |
Summary|[PPC/Altivec, regression?] |[4.1/4.2/4.3 Regression]
|gcc uses 0 as altivec |gcc uses 0 as altivec
|load/store index |load/store index
Target Milestone|--- |4.1.3
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=32396