From: "Alain Coetmeur" <alain.coetmeur@icdc.caissedesdepots.fr>
Newsgroups: comp.parallel.mpi
Subject: Re: use of MPI_WAIT in non-blocking mode
Date: Mon, 28 Dec 1998 16:42:04 +0100
Organization: Informatique-CDC
Message-Id: <76893b$hrf1@puligny.idt.cdc.fr>
References: <36879DE9.3A0C1CE7@LL.MIT.EDU>
Mime-Version: 1.0
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: 8bit


Michael Starkie a écrit dans le message <36879DE9.3A0C1CE7@LL.MIT.EDU>...
>I am having trouble understanding the difference between the following 2
>examples.
>
>example 1:
>    ...
>    MPI_IRECV(inval, 1, MPI_REAL, 1, 0, req, ierr)
>    MPI_WAIT(req, status, ierr)
>     ...
>
>example 2:
>    ...
>    MPI_RECV(inval, 1, MPI_REAL, 1, 0, req, ierr)
    I think you mean "status" instead of "req"

>Example 1 is used in the Interface Standard Document.  In example 1, a
>non-blocking receive is followed by a wait. Isn't this the same behavior
>as a blocking receive?


If someone tell me they are not equivalent when things goes
as usual (ie: when the req is created)
I want to know why !

this would really look strange.