This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug tree-optimization/31966] Miscompiles valid code with -ftree-vectorize and -march=nocona
- From: "dorit at gcc dot gnu dot org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: 1 Jul 2007 08:47:59 -0000
- Subject: [Bug tree-optimization/31966] Miscompiles valid code with -ftree-vectorize and -march=nocona
- References: <bug-31966-6477@http.gcc.gnu.org/bugzilla/>
- Reply-to: gcc-bugzilla at gcc dot gnu dot org
------- Comment #3 from dorit at gcc dot gnu dot org 2007-07-01 08:47 -------
I was able to reproduce the behavior on a Pentinum4 with a recent 4.3 snapshot.
It doesn't look like it's the vectorizer's fault - nothing gets vectorized.
However, if I disable the tree-level if-conversion (which is automatically
enabled by -ftree-vectorize) - the result of '-ftree-vectorize -O2
-march=nocona divop.c -o divop' becomes '3CBA83'.
--
dorit at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Keywords| |wrong-code
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=31966