From: Rolf Rabenseifner <Rabenseifner@XXXXXXXXXXXXXXXXXXXX>
Subject: Re: MPI-2.1 corrections, Batch 2 / AlltoallW
To: mpi-21@XXXXXXXXXXXXX
Date: Fri, 20 Jul 2001 10:29:04 +0200 (CEST)
In-Reply-To: <OF65372FCA.58075F9E-ONC1256A8F.00285296@XXXXXXXXXXXXXXXXXXX>
X-Mailer: ELM [version 2.5 PL3]
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-mpi-21@XXXXXXXXXXXXX
Precedence: bulk
Reply-To: mpi-21@XXXXXXXXXXXXX

> so it's still in the current (?) Fortran standard. How do those vendors
> like Cray get by that force REAL=DOUBLE PRECISION=64 bit, like on the T3E?

Always, if you use DOUBLE PRECISION on the T3E, the compiler issues a warning
that it compiles DOUBLE PRECISION as REAL, i.e., that the compiler breaks
the Fortran standard. ;-)

Best regards
Rolf 


Dr. Rolf Rabenseifner                      High Performance Computing
Parallel Computing                         Center Stuttgart    (HLRS)
Rechenzentrum Universitaet Stuttgart (RUS) Phone:    ++49 711 6855530
Allmandring 30                             FAX:      ++49 711 6787626
D-70550 Stuttgart                   rabenseifner@XXXXXXXXXXXXXXXXXXXX
Germany                        http://www.hlrs.de/people/rabenseifner