1. 07 Sep, 2012 2 commits
  2. 05 Sep, 2012 2 commits
  3. 30 Aug, 2012 3 commits
  4. 23 Aug, 2012 1 commit
  5. 08 Aug, 2012 1 commit
    • James Dinan's avatar
      [svn-r10114] Removed old/unused RMA vtable in CH3. · 52d980d7
      James Dinan authored
      Removed the old RMA virtual function infrastructure from CH3 -- this code was
      all already dead.  Function overrides are already provided per-window in the
      MPID_Win structure.  Overrides for non-window-specific (window creation)
      operations will be added shortly.
      
      Reviewer: buntinas
      52d980d7
  6. 24 Jul, 2012 1 commit
  7. 18 Jun, 2012 1 commit
  8. 15 Apr, 2012 1 commit
  9. 06 Apr, 2012 1 commit
  10. 04 Nov, 2011 1 commit
  11. 06 Apr, 2011 1 commit
  12. 28 Feb, 2011 1 commit
  13. 21 Jan, 2011 1 commit
  14. 08 Nov, 2010 1 commit
  15. 06 Nov, 2010 1 commit
    • William Gropp's avatar
      [svn-r7416] Major improvement to RMA performance for long lists of operations,... · 3608ca24
      William Gropp authored
      [svn-r7416] Major improvement to RMA performance for long lists of operations, an immediate mode accumulate for single ints, store the MPID_Comm within the window, and added a basic performance instrumentation interface that was extensively used to improve the RMA performance (enabled with --enable-g=instr).  With these fixes, MPICH2 can run the one-sided version of the Graph500 benchmark at a respectable if not great rate
      3608ca24
  16. 06 Oct, 2010 1 commit
  17. 08 Sep, 2010 1 commit
  18. 31 Aug, 2010 1 commit
  19. 11 Aug, 2010 2 commits
  20. 09 Aug, 2010 1 commit
  21. 06 Aug, 2010 1 commit
  22. 29 Jul, 2010 1 commit
  23. 28 Jul, 2010 1 commit
  24. 27 Jul, 2010 1 commit
    • David Goodell's avatar
      [svn-r6919] completion counter cleanup (adds MPID_cc_t) · 0a5c22ae
      David Goodell authored
      When compiled for fine-grained threading, the completion counter serves
      as a form of lockfree signalling.  As such, atomic access and memory
      barriers must be used to ensure correctness.
      
      In per-object mode, this code also contains valgrind client request annotations
      to inform Helgrind/DRD/TSan about the lockfree signalling pattern.
      
      No reviewer.
      0a5c22ae
  25. 09 Jun, 2010 1 commit
  26. 25 May, 2010 1 commit
  27. 05 Jan, 2010 1 commit
    • David Goodell's avatar
      [svn-r6103] refactor MPIU trmem and valgrind code to MPL (ticket #898). · 3c18dd24
      David Goodell authored
      This commit moves the existing tracing memory allocation and valgrind
      code utilities to MPL.  This permits other code like gforker to use the
      trmem code while allowing MPICH2 to remain thread-safe when using
      tracing.  gforker is not updated to the MPL routines by this commit.
      
      Reviewed by buntinas@.
      3c18dd24
  28. 26 Sep, 2009 1 commit
    • David Goodell's avatar
      [svn-r5374] Fix subarray test failures introduced in r4099. · 8e8831f3
      David Goodell authored
      The MPIDI_CH3U_Request_load_recv_iov function must fill the iov in the
      rreq at offset 0 *and* set rreq->dev.iov_offset to 0 because callers of
      this function as an OnDataAvail function don't know what action is
      occurring in the handler and can't set the offset to zero themselves.
      
      See r4099 and ticket #462 for some info on the previous test1_dt bug.
      
      Reviewed by buntinas@.
      8e8831f3
  29. 12 Jun, 2009 1 commit
  30. 06 May, 2009 1 commit
    • Darius Buntinas's avatar
      [svn-r4411] Fixed nemesis to correctly set vc state (instead of setting all... · 14a1e1cf
      Darius Buntinas authored
      [svn-r4411] Fixed nemesis to correctly set vc state (instead of setting all vcs to active.  Renamed MPIDI_Comm_get_vc to MPIDI_Comm_get_vc_set_active to alert caller to side-effect.  Added MPIDI_CHANGE_VC_STATE macro to set the vc state and call debugging macro.  Changed all places where vc state is changed to use this macro.  Reviewed by goodell@.
      14a1e1cf
  31. 13 Mar, 2009 1 commit
    • Jayesh Krishna's avatar
      [svn-r4062] 1) Modifying the datatype code to find the number of contig blocks... · ac4f4cd1
      Jayesh Krishna authored
      [svn-r4062] 1) Modifying the datatype code to find the number of contig blocks in an instance of an MPI derived datatype - Since finding the real number of contig blocks is not easy we find a reasonable upper bound instead. This also fixes the case where the number of contig blocks was uninitialized for contiguous datatypes. Refer ticket #428 for details (2) Adding a test case, test1_dt.c, to test the fix - Review @ rross, thakur
      ac4f4cd1
  32. 14 Feb, 2009 1 commit
  33. 31 Dec, 2008 1 commit
  34. 06 Nov, 2008 1 commit
  35. 09 Oct, 2008 1 commit