Newsgroups: comp.parallel.mpi
From: salo@mrjones.engr.sgi.com (Eric Salo)
Subject: Re: Order of message arrival question
Organization: Silicon Graphics, Inc.  Mountain View, CA
Date: 30 May 1996 23:40:10 GMT
Message-ID: <4olbkq$g7g@murrow.corp.sgi.com>

> Is it possible for this program to do the following?
> 
> B received
> END

Assuming a correct program and a correct MPI implementation, I believe
that ths is not possible. MPI does guarentee strict message ordering,
but the order in which MPI_Waitany() processes them is undefined. So
while it is possible for MPI_Waitany() to complete message B first,
message A must have already arrived and would be detected by a subsequent
Test/Wait.

I think.

Eric Salo         Silicon Graphics Inc.             "Do you know what the
(415)933-2998     2011 N. Shoreline Blvd, 7L-802     last Xon said, just
salo@sgi.com      Mountain View, CA   94043-1389     before he died?"

