This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: Polyhedron performance regression
- From: "Paul Richard Thomas" <paul dot richard dot thomas at gmail dot com>
- To: stevenb dot gcc at gmail dot com, richard dot guenther at gmail dot com, paolo dot bonzini at lu dot unisi dot ch, fortran at gcc dot gnu dot org
- Date: Sun, 12 Nov 2006 13:16:30 +0100
- Subject: Re: Polyhedron performance regression
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=B6R2Syudf2a7pQvXXKIrfenQ1EmbmKwzCfB5dLFf2ItlsA1u3dXM+tGtyGtcovpxnnV7n+p0gidqYaVXFzqK+r7OQW+tykCsWVB9FXnx8+1UC9yIcDT5pshJcqK2Pmr9bo6t+E1G6Eu3TDl7SvXozJw6S3QLQqFpubcXOI2xjo0=
Dear All,
I do not think that the regression is Paolo's doing, although he "helped" a bit.
On x86_ia64/FC5 with:
/svn-4.3/bin/gfortran -static -O3 -ffast-math -funroll-loops ac.f90
time ./a.out
revision time
118474 9.77s
118475 12.3s
current 33.0s !
Note that -ftree-vectorize has not been used, although this is a dual
core - nothing to do with vectorisation either....
Paul
I cannot do any mor on this until next Friday - am on my way out of
the door to the airport... well, 5 minutes ago:)