This is the mail archive of the fortran@gcc.gnu.org mailing list for the GNU Fortran project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack

From: Thomas Koenig <tkoenig at netcologne dot de>
To: Jerry DeLisle <jvdelisle at verizon dot net>
Cc: FX <fxcoudert at gmail dot com>, fortran at gcc dot gnu dot org, gcc-patches at gcc dot gnu dot org
Date: Thu, 20 Mar 2008 16:01:39 +0100
Subject: Re: [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack
References: <1205918358.3189.11.camel@meiner.onlinehome.de> <19c433eb0803190311u5cb0ccfqf8a4e1abe54c2dc7@mail.gmail.com> <1205946458.4077.3.camel@meiner.onlinehome.de> <47E1C06E.7010900@verizon.net>

On Wed, 2008-03-19 at 18:39 -0700, Jerry DeLisle wrote:
> Can we see any shifts in polyhedron or spec?

I suspect not for polyhedron; the improvement is for
kind=10 and kind=16 real and complex types, plus for
kind=1 and kind=2 integers.  I don't have access to SPEC
sources to see if repacking arrays makes a big difference
there.

I'll continue working along those lines for
the intrinsics (currently working on pack and
unpack).

	Thomas

References:
- [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack
  - From: Thomas Koenig
- Re: [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack
  - From: FX
- Re: [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack
  - From: Thomas Koenig
- Re: [patch, libfortran] Speed up / orthogonalize in_pack and in_unpack
  - From: Jerry DeLisle

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]