[MPICH] Stopping processors?

[Rajeev Thakur]

You can do a single MPI_Iprobe with a wildcard src and tag, MPI_ANY_SOURCE,
MPI_ANY_TAG. It will match a stop message from anyone.

Rajeev 

> -----Original Message-----
> From: owner-mpich-discuss at mcs.anl.gov 
> [mailto:owner-mpich-discuss at mcs.anl.gov] On Behalf Of Michaela Heyer
> Sent: Thursday, April 26, 2007 4:10 AM
> To: mpich-discuss at mcs.anl.gov
> Subject: Re: [MPICH] Stopping processors?
> 
> Hi Guys,
> Thanks for the replies!
> 
> Rajeev, what you suggested was my initial idea also. The 
> problem with this is 
> that I have about 200 different algorithms so the way I see 
> it I'd have to 
> add MPI_Iprobe (actually I was gonna use MPI_Test) to all the 
> algorithms and 
> possible call it even more than once to really make sure I 
> get stopped quite 
> quickly...which just doesn't seem feasible.
> 
> Darius, I like the idea with the threads! I haven't really 
> worked much with 
> threads, so I will have to look into it but I think it might work...
> 
> Michaela
> 
> 
> 
> 
> On Tuesday 24 April 2007 16:47, Darius Buntinas wrote:
> > One idea would be to have each worker process spawn a "computation"
> > thread which actually does the computation.  The "main" 
> thread of the
> > process would issue a blocking receive waiting for a "done" message.
> >
> > When a computation thread at some process finishes, it 
> sends messages to
> > the other processes and to itself.  When a main thread 
> receives a done
> > message, it checks whether it received the message from its own
> > computation thread.  If so, it does a pthread_join() and reads the
> > result, otherwise it does a pthread_cancel().
> >
> > At this point the main thread can wait for a message to 
> start the next
> > computation.
> >
> >
> > If you have a lot of processes having one process send a 
> done message to
> > every other process isn't scalable.  You could optimize in 
> that case by
> > having the processes forward the message in a tree.
> >
> > -d
> 
> 
> 
> 
> On Tuesday 24 April 2007 16:59, Rajeev Thakur wrote:
> > You could have all processes post an MPI_Irecv and then 
> periodically call
> > MPI_Iprobe to see if there is an incoming message. The process that
> > finishes first sends others a stop message.
> >
> > Rajeev
> >
> > > -----Original Message-----
> > > From: owner-mpich-discuss at mcs.anl.gov
> > > [mailto:owner-mpich-discuss at mcs.anl.gov] On Behalf Of 
> Michaela Heyer
> > > Sent: Tuesday, April 24, 2007 9:21 AM
> > > To: mpich-discuss at mcs.anl.gov
> > > Subject: [MPICH] Stopping processors?
> > >
> > > Hi,
> > > I'm hoping someone can help me with this...
> > > Essentially I'm looking for a way to tell one or more
> > > processors to stop
> > > whatever they are currently doing and move on to 
> something else. The
> > > situation is as follows: Let's say we have n processors all
> > > working on
> > > different algorithms. I only really need the result of 
> one of these
> > > algorithms so whichever processor finishes first should tell
> > > all the other
> > > ones to stop so they can all move on to the next problem.
> > > It's a bit like a
> > > race...and speed is vital! (That's why I can't really wait
> > > for all processors
> > > to finish their algorithms)
> > > At the moment I'm using MPI_Abort() to shutdown the whole
> > > process. This works
> > > fine and does exactly what I need but the problem is that it
> > > is very very
> > > slow as it shuts down and restarts all the processors. So
> > > what I'm looking
> > > for is something like a "milder" version of MPI_Abort() i.e.
> > > stop everything
> > > but don't shutdown the processors.
> > > I have been looking but can't find anything sutitable so I'm
> > > starting to think
> > > that maybe it's impossible? It would be great if you could
> > > prove me wrong :-)
> > > Thanks,
> > > Michaela
> 
>