Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Problems with computation-communication overlap innon-blocking mode
From: Alex A. Granovsky (gran_at_[hidden])
Date: 2014-03-11 05:55:02

Dear Nikola,

you can check this presentation:

for the solution we have been using with Firefly (formerly PC GAMESS) for
more than last ten years.

Hope this helps.

Kind regards,
Alex Granovsky

-----Original Message-----
From: Velickovic Nikola
Sent: Friday, March 07, 2014 6:49 PM
To: users_at_[hidden]
Subject: [OMPI users] Problems with computation-communication overlap
innon-blocking mode

Dear all,

I have a simple MPI program with two processes using non-blocking
communication illustrated bellow:

process 0: process 1:

MPI_Isend MPI_Irecv

compute stage compute stage

MPI_Wait MPI_Wait

Actual communication is performed by offloading it to another thread, or
using DMA (KNEM module is used for this).
Ideally what should happen is that process 0 issues a non-blocking send,
process 1 receives the data
and in the meantime (in parallel) the CPU cores where the processes run are
doing the compute stage.
When compute stage is completed calling MPI_Wait wraps up the communication.

When I profile my application it turns out that actual communication is
initiated with MPI_Wait (significant amount of time is spent there) and
hence disables overlapping
communication and computation since MPI_Wait is called after the compute
Computation in my test case takes more time than communication so MPI_Wait
should not be consuming significant amount of time since the communication
should be over by then.

This I confirmed also by using MPI_Test instead of MPI_Wait.
MPI_Test has the same effect as MPI_Wait (to the best of my knowledge) but
is non-blocking.
When placing MPI_Test strategically in the compute stage it initiates the
communication and a certain communication-computation overlap is achieved.

Could you please shed some light for me if I am doing something wrong with
the library?
Is it the way it should behave (MPI_Wait initiates the actual transfer)?
How to achieve communication-computation overlap?

users mailing list