GitLab

Implementation of MPI-3 window info query routines.

Reviewer: balaji

moved some error messages which should have been mpix to mpi.

Reviewed by dinan.

The RMA op dispatch macro was previously defined in a private header used by
the high level routines.  This has been moved to mpiimpl.h to join the rest of
the RMA op table code.   This will allow other routines to dispatch RMA ops at
the ADI correctly.

Reviewer: goodell.

MPI_.

A slightly older version of this patch was reviewed by goodell.

By setting "indent-tabs-mode:nil" we should hopefully begin to slowly
squeeze out hard tabs from the source without a disruptive (to
downstream projects) whitespace-fixing change.

No reviewer.

In several places, after checking for a parameter (e.g., comm) we were
directly using it assuming that the parameter is valid.  Since the
previous ERRTEST macros did not jump to fn_fail on an error, this
could result in undefined behavior if the parameter was invalid.  Now,
since we jump on errors within the macros themselves, once the check
is done, we know that the parameter values are valid.

Reviewed by buntinas.

Reviewer: balaji

yet implemented below the ADI level.

[svn-r8069] Detect and report incorrect use of assert and/or rank in Win_lock and Win_unlock.  These detect an error in the current test suite that manifested itself as a storage leak.  Also corrected some man page information and instrumentation for RMA completion in non-fence modes

[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

This is done as a separate commit to de-clutter the change with actual
logic changes in it.

No reviewer.

[svn-r5355] Added (or moved) MPIU_THREADPRIV_DECL so that the thread-private area is acquired only once within a routine, since the data (pointer to the thread-private area) is fixed during the execution.  This reduces the overhead of the nest increment/decrement, for example

[svn-r3177] Switch to the new macro for the global thread critical section (most of this is an automated change, tested against the MPICH2 test suite)

[svn-r917] RMA updates - fixed mixed sync bug, flattened one level of call, replaced incorrect global function table with per-window table.  Also updated configure to 2.62