This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
Re: FORALL Under GFORTRAN Concurrency Test
- From: "Joseph North" <joseph dot north at gmail dot com>
- To: kupfem at rpi dot edu
- Cc: "David Dunham" <dunham at starpower dot net>, "William Gropp" <gropp at mcs dot anl dot gov>, fortran at gcc dot gnu dot org
- Date: Wed, 17 Oct 2007 10:01:06 -0500
- Subject: Re: FORALL Under GFORTRAN Concurrency Test
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; bh=zsgjGhVBawIRXSTY2JXNYD/eQ2SBrK9hVMni6CO3dvQ=; b=o8tvr7KRmERkNULDpnI3GlgBWhcERnBPR0YKtn5efktNjzsoKRXGLAFApUPkieBMa94yEvWD3CYsxo5DbrJn+xGkJ3tEerMqC07RYyDFdNPw1KyJIw7TDXXnph9DZhVnlcpfgY1BAqINm+Sq7zV2vENH7gUDn6fM+hW/i3AvL1Q=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=kGRkT3O4YsXO2NAZss0bFBruwCwyWBTKT3SRMeD7O3mxofpbQz/TwKR0XKWxLIo2ThMyvh62O8PPLitKLRF1fr7RtPVg8xjtYLdJu3h6xrjFQjedgM3KmILoPQCUN2IU4ZTVIPKOmj3r1xFD2jfxdVF9Da/nkxhLDXZmtuEs3Ng=
- References: <200710162051.l9GKpsPY024484@smtp5.server.rpi.edu>
On 10/16/07, kupfem@rpi.edu <kupfem@rpi.edu> wrote:
> ==============Original message text===============
> On Mon, 15 Oct 2007 9:27:10 EDT "Joseph North" wrote:
>
> Dear Mike:
>
>
> I am just starting to explore gfortran v. 4.1.2 under Fedora 7, x86_64
> on an AMD Athlon 64 X2 Dual-Core Processor 560++ based PC.
> I have a copy of your book, Classical FORTRAN,
> QA 76.73 F25 K867 2002 MAIN, UT Austin.
> When I tried a simple forall, it ran for ~ 4 s but only on CPU1!
> How can I realize concurrency therefor, please?!
> I can demonstrate LAM/MPI concurrency utilizing my 2 cores for
> another example, however, I haven't tried a forall test therefor.
> I could send you more detailed info, if you'd like to help, and I thank
> you antedatedly therefor.
> Tempus fugit et ad augusta per angusta.
>
>
> Nil desparare (Gauss),
>
> Joseph Roy D. North
> Le Roi Du Nord
> 3220 Duval Road, Apt. 1110
> Austin, TX 78759-3524, USA
>
> Scientia est Potentia!
>
> ===========End of original message text===========
>
> The gfortran wiki seems to suggest that automatic parallelization is
> under development (not just for FORALL but for DO loops as well) but
> not yet released. I guess for the moment you will have to stick with
> MPI for parallelizing your programs.
>
>
>
Hi Mike:
OK, thanks: darn! And, I may now also have to wait for a Quad-Core AMD
Opteron, Barcelona, Phenom, based PC.
LAM/MPI has worked for a simple pi evaluation (i.e., William Gropp, et al.:
USING MPI, 1994, & ANL code repository).
Tempus fugit et ad augusta per angusta.
Nil desparare (Gauss),
Joseph Roy D. North
Le Roi Du Nord
3220 Duval Road, Apt. 1110
Austin, TX 78759-3524, USA
Scientia est Potentia!