George is right -- you *can* do this, but it is *not advised* (you'll
likely run out of memory or other resources pretty quickly -- if you
can run at all!). :-)
Try mpi_leave_pinned, and check out those FAQ sections that I sent,
particularly the OpenFabrics section, for how to specifically
Have a look at the FAQ; we discuss quite a few of these kinds of issues:
- http://www.open-mpi.org/faq/?category=tuning
- http://www.open-mpi.org/faq/?category=openfabrics
More specifically, what Eugene is saying is correct -- OMPI has made
tradeoffs for various, complicated reasons. One of t
In order to get good performance out of your test application, the
whole message has to be send in just one fragment. The reason is that
as long as there is no progress thread for the MPI library (internal
to the library), there is no way to make progress.
Now, I can explain how to do this,
vladimir marjanovic wrote:
In
order to overlap communication and computation I don't want to use
MPI_Wait.
Right. One thing to keep in mind is that there are two ways of
overlapping communication and computation. One is you start a send
(MPI_Isend), you do a bunch of computation
From: Eugene Loh
To: Open MPI Users
Sent: Thursday, 6 November, 2008 18:08:26
Subject: Re: [OMPI users] Progress of the asynchronous messages
vladimir marjanovic wrote:
I am new user of Open MPI, I've used MPICH before.
There is performance bug wit
vladimir marjanovic wrote:
I am new user of Open MPI, I've used MPICH before.
There is performance bug with the following scenario:
proc_B: MPI_Isend(...,proc_A,..,&request)
do{
sleep(1);
MPI_Test(..,&flag,&request);
Hi,
I am new user of Open MPI, I've used MPICH before.
There is performance bug with the following scenario:
proc_B: MPI_Isend(...,proc_A,..,&request)
do{
sleep(1);
MPI_Test(..,&flag,&request);
count++
}whi
