Autovectorizing HIRLAM; some progress.

3 msg	gcc 4.2.2, libgomp under cygwin
4 msg	PR1634: Request for gcc-cvs-patches list
6 msg	Idea to refine -Wtype-limits
1 msg	Bounce Test
1 msg	[Fwd: Libiberty problem in gcc-4.3 snapshots]
7 msg	[RFC] [PATCH] 32-bit pointers in x86-64
8 msg	Re: Designs for better debug info in GCC. Choic...

Autovectorizing HIRLAM; some progress.
\ Toon Moene (24 Nov 2007)
. \ Toon Moene (24 Nov 2007)
. \ Dorit Nuzman (25 Nov 2007)
. . \ Toon Moene (25 Nov 2007)

3 msg	Infinite loop when trying to bootstrap trunk
1 msg	gcc-4.3-20071123 is now available
1 msg	Status of GCC 4.3 on IA64 (Debian)
5 msg	[Fwd: Re: FW: matrix linking]
8 msg	Does gcc support compiling for windows x86-64?
1 msg	RiW k sLG
7 msg	-Wconversion bug in g++-4.3?
5 msg	Simple way to write almost same pattern?
2 msg	unsatisfied link error
1 msg	gcc-4.2-20071121 is now available
2 msg	Status of GCC 4.3 on SPARC (Debian)
7 msg	Problem with ARM_DOUBLEWORD_ALIGN on ARM

Subject:	Autovectorizing HIRLAM; some progress.
Group:	Gcc
From:	Toon Moene
Date:	24 Nov 2007

L.S.,

I noticed some unexpected progress last night (as opposed to about a
week ago).

Previous figures:

5316 loops vectorized
6060 loops not vectorized

New figures:

5188 loops vectorized
6189 loops not vectorized

i.e., 201 loops *more* recognized by the vectorizer, of which 72 got
vectorized, 129 not.

As I see no activity (svn-wise) on the vectorizer front, it probably is
the better alias analysis by Richard Guenther ...

--
Toon Moene - e-mail: toon - phone: +31 346 214290
Saturnushof 14, 3738 XG Maartensdijk, The Netherlands
At home: http://moene.indiv.nluug.nl/~toon/
GNU Fortran's path to Fortran 2003: http://gcc.gnu.org/wiki/Fortran2003