This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug middle-end/38846] [Graphite] 35% slower using -floop* than without graphite (gas_dyn of Polyhedron)
- From: "burnus at gcc dot gnu.org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Sun, 24 Oct 2010 19:30:45 +0000
- Subject: [Bug middle-end/38846] [Graphite] 35% slower using -floop* than without graphite (gas_dyn of Polyhedron)
- Auto-submitted: auto-generated
- References: <bug-38846-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=38846
Tobias Burnus <burnus at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |RESOLVED
Resolution| |FIXED
--- Comment #8 from Tobias Burnus <burnus at gcc dot gnu.org> 2010-10-24 19:30:37 UTC ---
(In reply to comment #7)
> This pr looks like a duplicate of pr43359. Can you check that it has not been
> fixed?
Seems so. I get for gas_dyn: w/o Graphite 0m11.713s/0m11.664s; with graphite
0m10.826s/0m11.309s.
Thus: Mark as FIXED. (I did not do a full check of all combinations, but some
further tests, which look positive.)
Cross-ref: For Graphite + induct.f90: See PR 40979.
(On my system [Athlon64 x2]: with -fgraphite-identity it is about as fast as
without graphite [or slightly faster], but others see still some substantial
slow down.)