Open MPI logo

Open MPI User's Mailing List Archives
  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list
 About
  Publications
  Open MPI Team
  FAQ
  Videos
 Open MPI Software
  Download
  Documentation
  Source Code Access
  Bug Tracking
  Regression Testing
  Version Information
 Sub-Projects
  Hardware Locality
  MPI Testing Tool
  Portable Linux Processor Affinity
  Open MPI User Docs
  Open Tool for Parameter Optimization
 Community
  Mailing Lists
    OMPI announce archives
    OMPI users archives
    OMPI devel archives
    OMPI docs archives
    hwloc announce archives
    hwloc users archives
    hwloc devel archives
    MTT announce archives
    MTT users archives
    MTT developers archives
    ORCM users archives
    ORCM devel archives
  Getting Help/Support
  Contribute
  Mirrors
  Contact
  License
 
Date view Thread view Subject view Author view

Subject: Re: [OMPI users] MPI_Reduce performance
From: Eugene Loh (eugene.loh_at_[hidden])
Date: 2010-09-09 15:32:20

Alex A. Granovsky wrote:
Isn't in evident from the theory of random processes and probability theory that in the limit of infinitely
large cluster and parallel process, the probability of deadlocks with current implementation is unfortunately
quite a finite quantity and in limit approaches to unity regardless on any particular details of the program.
No, not at all.  Consider simulating a physical volume.  Each process is assigned to some small subvolume.  It updates conditions locally, but on the surface of its simulation subvolume it needs information from "nearby" processes.  It cannot proceed along the surface until it has that neighboring information.  Its neighbors, in turn, cannot proceed until their neighbors have reached some point.  Two distant processes can be quite out of step with one another, but only by some bounded amount.  At some point, a leading process has to wait for information from a laggard to propagate to it.  All processes proceed together, in some loose lock-step fashion.  Many applications behave in this fashion.  Actually, in many applications, the synchronization is tightened in that "physics" is made to propagate faster than neighbor-by-neighbor.

As the number of processes increases, the laggard might seem relatively slower in comparison, but that isn't deadlock.

As the size of the cluster increases, the chances of a system component failure increase, but that also is a different matter.
Date view Thread view Subject view Author view
[Flag]
 Indiana University (Main Open MPI server)
This site is located in: Bloomington, IN, USA
Page last modified: 9-Sep-2010
©2004-2013 The Open MPI Project