[Mpi3-hybridpm] First cut at slides

[Jeff Squyres (jsquyres)]

On Jun 28, 2013, at 10:05 PM, Pavan Balaji <balaji at mcs.anl.gov> wrote:

>> Put differently: A's FINALIZE is collective with B/first FINALIZE (by
>> definition), but in practice it may need to synchronize with B/second
>> FINALIZE.
> 
> Good point.  Would requiring MPI to not synchronize when it's not finalizing fix this?


There be dragons thar...

                    ___====-_  _-====___ 
             __--^^^      //     \\     ^^^--_
            _-^         // (    ) \\         ^-_
           -           //  |\^^/|  \\           -
         _/           //   (0::0)   \\            \_
        /            ((     \\//     ))             \ 
      -     MPI       \\    (oo)    //    FINALIZE   -
     -                 \\  / \/ \  //                 -
    -                   \\/      \//                   -
  / /|           /\      (        )      /\           |\ \
  |/ | /\_/\_/\_/  \_/\  (   /\   )  /\_/  \_/\_/\_/\ | \|
  `  |/  V  V  `    V  \_(| |  | |)_/  V    '  V  V  \|  '
     `   `  `       `   / | |  | | \   '       '  '   '
                      <(  | |  | |  )>             
                     <__\_| |  | |_\__>           
                     ^^^^ ^^^  ^^^ ^^^^^

-- 
Jeff Squyres
jsquyres at cisco.com
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/