[Mpi3-ft] one sided

Darius Buntinas buntinas at mcs.anl.gov
Tue Oct 18 14:56:45 CDT 2011


I got some feedback from Jim and Pavan on the one-sided section.  One thing Jim pointed out was that we don't want to make window creation synchronizing, and the fail-or-succeed everywhere requirement would do that.

If we say that window creation should not fail due to failed processes, that would accomplish the same thing:  If a window is created by a correct program, then it will succeed at all live processes.  Note that if an incorrect program specifies invalid parameters then the window creation may fail at some processes and succeed at others, but this is what we already have today.

However, it's possible that some implementations cannot satisfy this requirement because, e.g., they do collectives as part of the operation.  So maybe we should have two options:

  Either:
    window creation won't fail because if failed processes
  or
    window creation will either succeed or fail everywhere and if window creation fails at 
    any process it fails at every process

-d






More information about the mpiwg-ft mailing list