No reviewer.

Contributed by Dmitri Gribenko <gribozavr@gmail.com>.

http://lists.mcs.anl.gov/pipermail/mpich2-dev/2012-October/000997.html

MPI_.

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

No reviewer.

Reviewed by goodell.

even though no device currently takes advantage of this.

No reviewer.

1. Move the new extension FT routines into the src/mpi/comm directory
instead of the separate src/mpix directory, since it's clearly using
the MPI internals.

2. Move the MPIX_mutex functionality to mpi.h.in instead of a separate
mpix.h.  This will allow us to use device-specific mpix_foo.h
functionality that the user can use to buy-in to device-specific
extensions.

3. Move the ARMCI and Mutex functionality to src/armci and src/mutex
directories respectively.

Reviewed by goodell.

Updated window model and flavor attributes in the window object from integers
to enum types.

Reviewer: buntinas

Added the missing disp_unit argument (was added in a later revision of the MPI
3.0 spec) and fixed a bug in base pointer calculations when processes pass a
size of 0.  Added a test case to test MPI-2 ops on shared memory windows.

Reviewer: buntinas

No reviewer.

Also update the mprobe regression test to cover this case.

Thanks to Lisandro Dalcin for reporting this bug.

Reviewed by buntinas@.

Split up so that the later impl code is easier to find/read.

Reviewed by buntinas@.

These annotations allow the compiler to perform type checking between
the C language type of a buffer and the MPI_Datatype specified by the
user.

This new code relies on experimental features currently under
consideration for addition to Clang:

http://lists.cs.uiuc.edu/pipermail/cfe-commits/Week-of-Mon-20120521/058137.html

Code courtesy of Dmitri Gribenko <gribozavr@gmail.com>, with help from
Hal Finkel @ ALCF.

Reviewer: balaji

since we don't need to maintain backward compatibility here.
Hardcoded them to const, so they are better tested.

Reviewed by goodell.

yet implemented below the ADI level.

[svn-r10031] Added several MPICH2_CONST qualifiers previously missed (found when compiling the MPI-3 examples), as well as adding reduce_scatter_block to MPE2 collchk

Some support within ROMIO is missing.

No reviewer.

Reviewed by balaji@.

disabled for the public interfaces, but all internal functions use
const.

No reviewer.

[svn-r9794] Mark the MPI(X)_T routines to be skipped when generating the other language bindings, as these only have C bindings

[svn-r9745] Removed bonus comma from end of enum definition in mpi.h.in to supress gcc -pedantic warnings.

This corresponds to the functionality described in MPI Forum ticket #328.

Reviewed by buntinas@.

From MPI Forum ticket 168:
http://svn.mpi-forum.org/trac2/mpi-forum-web/ticket/168

This version will not work for multithreaded initializations of MPI.
Unfortunately, an implementation that deals with multithreading
correctly is much more complex.

Includes a simple test of the MPIX_Comm_idup functionality.

No reviewer.

This includes MPIX_Mprobe, MPIX_Improbe, MPIX_Mrecv, and MPIX_Imrecv.

!!!NOTE!!! This change adds four more functions to the ADI.

The current implementation of MPIX_Mprobe is much less efficient than it
could be.  Right now it polls the unexpected queue (UQ), much like
MPI_Probe does.  A better implementation would enqueue the "message"
object on the PQ so that the matching is handled by the progress engine
in the various packet handlers.  Unfortunately, such an implementation
is surprisingly complicated at this point.

Includes only a simple test for now (test/mpi/pt2pt/mprobe), but it at
least shows that our Mprobe functionality basically all works.

Reviewed by buntinas@.

[svn-r9424] Added MPIX_Comm_reenable_anysource functionality.  This is a manual merge of the dev/reenableas branch.  Reviewed by goodell@

[svn-r9394] Added query functions for failed processes.  This is a manual merge of the groupfailed branch, because svn choked.  Reviewed by goodell@

can play around with the tag requirement changes more easily. This
commit also deletes the older src/mpix/comm directory which had the
original implementation of MPIX_Comm_create_group, but a separate
"real svn" commit will be required to truly remove that directory from
svn.

This resolves an ambiguity introduced by following MPI-2.2's suggestion
of setting MPI_UNWEIGHTED==NULL.  See MPI Forum ticket #294:
https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/294

Also enhance the test suite to test for issues related to MPI_UNWEIGHTED
and specifying empty graphs.

AFAICT the Fortran interface works fine with this change.

No reviewer.

Most of the problems associated with this implementation have to do with
initialization bootstrapping/teardown issues.  Using the new interface
to profile MPI_Init/MPI_Finalize certainly has at least a few bugs right
now.  Use entirely within an MPI_Init/MPI_Finalize region should
basically work fine.

Two performance variables are exposed right now, the expected and
unexpected queue lengths.  All environment variables from the parameter
interface are exposed via the new "control variable" API.

No reviewer.

default, it sets the split communicator to a copy of MPI_COMM_SELF,
unless overridden by the device.

Reviewed by buntinas.

The src/binding/f77/buildiface script can now handle an arbitrary number
of function prefixes, although "MPI_" and "MPIX_" are the only ones
enabled by default.  This commit also moves the MPIX_Icollective and
PMPIX_I* prototypes between "Begin Prototypes"/"End Prototypes" in
mpi.h so that the buildiface script can see them.

Reviewed by gropp@.

Reviewed by balaji@.

No reviewer.

These functions build but will yield an error at runtime if invoked.
They will correctly call any collective function overrides specified in
comm_ptr->coll_fns, permitting devices to experiment with NBC
implementation before a complete implementation is available above the
ADI.

Reviewed by buntinas@.