1
1
Граф коммитов

75 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
f9c5adb86f Fix to enable the --disable-mpi-io configure option.
This commit was SVN r20330.
2009-01-23 14:15:51 +00:00
Jeff Squyres
207a61e8d9 Fixes trac:1072: allow MPI C++ constants to be used as array sizes, such
as:

  char name[MPI::MAX_PORT_NAME];

This commit was SVN r20310.

The following Trac tickets were found above:
  Ticket 1072 --> https://svn.open-mpi.org/trac/ompi/ticket/1072
2009-01-21 23:02:51 +00:00
Jeff Squyres
4d8a187450 Two major things in this commit:
* New "op" MPI layer framework
 * Addition of the MPI_REDUCE_LOCAL proposed function (for MPI-2.2)

= Op framework =

Add new "op" framework in the ompi layer.  This framework replaces the
hard-coded MPI_Op back-end functions for (MPI_Op, MPI_Datatype) tuples
for pre-defined MPI_Ops, allowing components and modules to provide
the back-end functions.  The intent is that components can be written
to take advantage of hardware acceleration (GPU, FPGA, specialized CPU
instructions, etc.).  Similar to other frameworks, components are
intended to be able to discover at run-time if they can be used, and
if so, elect themselves to be selected (or disqualify themselves from
selection if they cannot run).  If specialized hardware is not
available, there is a default set of functions that will automatically
be used.

This framework is ''not'' used for user-defined MPI_Ops.

The new op framework is similar to the existing coll framework, in
that the final set of function pointers that are used on any given
intrinsic MPI_Op can be a mixed bag of function pointers, potentially
coming from multiple different op modules.  This allows for hardware
that only supports some of the operations, not all of them (e.g., a
GPU that only supports single-precision operations).

All the hard-coded back-end MPI_Op functions for (MPI_Op,
MPI_Datatype) tuples still exist, but unlike coll, they're in the
framework base (vs. being in a separate "basic" component) and are
automatically used if no component is found at runtime that provides a
module with the necessary function pointers.

There is an "example" op component that will hopefully be useful to
those writing meaningful op components.  It is currently
.ompi_ignore'd so that it doesn't impinge on other developers (it's
somewhat chatty in terms of opal_output() so that you can tell when
its functions have been invoked).  See the README file in the example
op component directory.  Developers of new op components are
encouraged to look at the following wiki pages:

  https://svn.open-mpi.org/trac/ompi/wiki/devel/Autogen
  https://svn.open-mpi.org/trac/ompi/wiki/devel/CreateComponent
  https://svn.open-mpi.org/trac/ompi/wiki/devel/CreateFramework

= MPI_REDUCE_LOCAL =

Part of the MPI-2.2 proposal listed here:

    https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/24

is to add a new function named MPI_REDUCE_LOCAL.  It is very easy to
implement, so I added it (also because it makes testing the op
framework pretty easy -- you can do it in serial rather than via
parallel reductions).  There's even a man page!

This commit was SVN r20280.
2009-01-14 23:44:31 +00:00
Jeff Squyres
1bedf18305 OMPI_DECLSPEC is no longer necessary when it's static. Duh.
This commit was SVN r20254.
2009-01-13 15:09:16 +00:00
Jeff Squyres
34b7b6cfe8 Really fixes trac:623: there still is a difference between MPI::SEEK_SET
and ::SEEK_SET (duh); that's why it's listed in constants.h.  So put
that back and make it (static const int) rather than extern, and then
remove the instantiation from mpicxx.cc.  Ditto for the other 2.

This commit was SVN r20251.

The following Trac tickets were found above:
  Ticket 623 --> https://svn.open-mpi.org/trac/ompi/ticket/623
2009-01-12 22:06:16 +00:00
Jeff Squyres
20831c36d2 Fixes trac:623: we changed SEEK_SET (and friends) to be (static const int)
in mpicxx.h a while ago, but somehow accidentally left "extern const
int" for SEEK_SET (and friends) in constants.h.  This commit removes
the extraneous "extern" versions.

This commit was SVN r20250.

The following Trac tickets were found above:
  Ticket 623 --> https://svn.open-mpi.org/trac/ompi/ticket/623
2009-01-12 21:50:50 +00:00
Jeff Squyres
2f94a151e1 Fix a const cast.
This commit was SVN r20146.
2008-12-17 15:29:02 +00:00
Shiqing Fan
a5281f0434 - 1/4 commit for Windows Visual Studio and CCP support:
CMakeLists and .windows files.
  In contribs preconfigured and precompiled parts.

This commit was SVN r20108.
2008-12-10 20:59:20 +00:00
Rolf vandeVaart
1ad9d0459e Add a check for LOCK_SHARED in the sys/synch.h file. If it exists then smash it to avoid problems with preprocessor and C++.
This fixes trac:1477.

Help provided by Jeff and Terry.

This commit was SVN r19533.

The following Trac tickets were found above:
  Ticket 1477 --> https://svn.open-mpi.org/trac/ompi/ticket/1477
2008-09-10 12:58:30 +00:00
Jeff Squyres
1382b29aa3 Add the MPI::Comm::Call_errhandler() function (it was previously
missing!).  Fixes trac:1483.

This commit was SVN r19503.

The following Trac tickets were found above:
  Ticket 1483 --> https://svn.open-mpi.org/trac/ompi/ticket/1483
2008-09-05 12:26:06 +00:00
Jeff Squyres
46da10ff08 An optimization/improvement from our old way of providing
MPI::SEEK_SET and friends, suggested by Doug Gregor.  This way allows
users to utilize SEEK_SET in a case statement, which they could not do
with our previous method.

This commit was SVN r19494.
2008-09-04 15:02:52 +00:00
Jeff Squyres
0d618b519f Fix MPI::IN_PLACE to be (void* const). Fixes trac:1465.
This commit was SVN r19420.

The following Trac tickets were found above:
  Ticket 1465 --> https://svn.open-mpi.org/trac/ompi/ticket/1465
2008-08-26 17:36:08 +00:00
Jeff Squyres
fc7e5f1c0d Fix CID 1095: ensure to initialize the File
This commit was SVN r19252.
2008-08-12 13:13:02 +00:00
Jeff Squyres
76b4040fbf Fix CIDs 830, 831, 858: minor resource leaks on error
This commit was SVN r19237.
2008-08-11 20:40:04 +00:00
Jeff Squyres
fa25de320e Fixes CIDs 421, 422, 423, 424, 425 426
Possibly fixes CID 417

 * ensure to initialize inner members upon default constructors using
   the same syntax across all classes
 * remove some member variables that aren't used anymore
 * "initialize" the inner MPI_Status in the default constructor for
   MPI::Status by calling the default constructor mpi_status().  This
   may or may not silence CID 417; we'll see what happens in
   subsequent Coverity Prevent runs.

This commit was SVN r19228.
2008-08-08 13:49:44 +00:00
Jeff Squyres
9f4d4c4312 Fixes trac:1409: ensure that the C++, F77, and F90 bindings libraries
are properly linked against libmpi.la.

This required a little creative AM usage, inspired by discussion on
OMPI devel list:

 * Make a new ompi/mpi/f77/Makefile_f77base.include; effectively move
   the building of the f77 "base" glue stuff (libmpi_f77base.la) into
   this Makefile and away from ompi/mpi/f77/Makefile.am.  The sources
   in question require some specific CPPFLAGS, so we couldn't just add
   the raw sources into libmpi_la_SOURCES, unfortunately.
 * Include this new Makefile in the top-level ompi/Makefile.am
 * The libmpi_f77base.la LT convenience library was already sucked
   into libmpi.la; breaking it out into its own Makefile allows us
   to build it earlier and therefore complete buidling libmpi.la
   earlier.
 * Side effect: the ompi/mpi/Makefile.am is now mostly unnecessary; it
   no longer specifies a SUBDIRS for each of the bindings directories
   to traverse into (since they are now in the top-level SUBDIRS).  As
   such, the man pages are now also now included in the top-level
   ompi/Makefile.am.

The end of the result is that libmpi.la -- including a few sources
from mpi/f77 -- is fully built before the C++, F77, and F90 bindings
are built.  Therefore, the C++, F77, and F90 bindings libraries can
all link against libmpi.la.

This commit was SVN r19040.

The following Trac tickets were found above:
  Ticket 1409 --> https://svn.open-mpi.org/trac/ompi/ticket/1409
2008-07-25 21:18:05 +00:00
Jeff Squyres
f366f49179 Remove some leftover kruft; the STL is no longer used, so this lock is
no longer necessary.

This commit was SVN r18694.
2008-06-20 13:39:26 +00:00
Jeff Squyres
7a1206d912 Two more minor changes:
* Put the variable in the MPI namespace; keeps it safely segregated
   from user apps
 * Need to actually "extern" the variable to make the compiler not
   complain that the variable is never referenced

This commit was SVN r18693.
2008-06-20 13:36:02 +00:00
Jeff Squyres
a884eebdf1 This warning has been bugging me in MTT nightly runs for forever: make
the char string ident in the C++ library be non-static so that other
places can see it.  This makes the C++ library version string
analogous to all the other version strings.

This commit was SVN r18679.
2008-06-19 14:40:37 +00:00
Jeff Squyres
12426b64ea Per MPI-2 ballot 3, the definition of MPI::BOTTOM has changed. w00t!
Fixes trac:1175.

This commit was SVN r17850.

The following Trac tickets were found above:
  Ticket 1175 --> https://svn.open-mpi.org/trac/ompi/ticket/1175
2008-03-17 21:42:27 +00:00
Jeff Squyres
7d03300a76 Based on a patch from Brian about how to remove "naked" AC defined
macros in mpi.h. (e.g., HAVE_LONG_LONG); instead, prefix _all_ macros
with "OMPI_".

This commit was SVN r17591.
2008-02-26 01:45:32 +00:00
Jeff Squyres
6d75691de3 Remove now-useless variable.
This commit was SVN r17429.
2008-02-12 13:09:34 +00:00
Dan Lacher
98f70d6318 Convert the C++ Comm, Datatype and Winn keyval creation and intercept callbacks
to *not* use the STL as well as removing the STL use from the error handler
routines.  This was removing the STL from the C++ bindings (Solaris has 2
versions of the STL; if OMPI uses one and an MPI application wants to use
another, Bad Things happen).

The main idea is to wrap up the C++ callback function pointers and the user's
extra_state into our own struct that is passed as the extra_state to the C
keyval registration along with the intercept routines in intercepts.cc. When the
C++ intercepts are activated, they unwrap the user's callback and extra state
and call them.

This commit was SVN r17409.
2008-02-10 19:29:25 +00:00
Jeff Squyres
404f8d1076 Nothing substantial: just move the generalized request intercept data
structure up into the MPI::Grequest class (rather than being a struct
definition outside of any class) to be similar to how the keyval
intercept data structures are organized.  Fix one minor compiler
warning in the process.

This commit was SVN r17171.
2008-01-21 15:56:21 +00:00
Jeff Squyres
ab60cfd948 Fix some typos.
This commit was SVN r17168.
2008-01-21 14:34:25 +00:00
Jeff Squyres
72bef32e65 Convert the C++ Comm keyval creation and intercept callbacks to *not*
use the STL.  This is the first step in removing the STL from the C++
bindings (Solaris has 2 versions of the STL; if OMPI uses one and an
MPI application wants to use another, Bad Things happen).

The main idea is to wrap up the C++ callback function pointers and the
user's extra_state into our own struct that is passed as the
extra_state to the C keyval registration along with the intercept
routines in intercepts.cc.  When the C++ intercepts are activated,
they unwrap the user's callback and extra state and call them.

It got a little more complicated than that, however:

 * I realized that we were returning errors back from
   Comm::create_keyval() incorrectly, so I fixed that.
 * Instead of using STL maps to store associations, we now use an
   opal_list_t which has to be guaranteed to be initialized correctly
   and only once in a multi-threaded environment.
 * Because of whackyness in the C++ bindings, it is possible to call
   Comm::Create_keyval with C callbacks (!).  If both registered
   callbacks are C functions, then ensure to avoid all the C++
   machinery.

This commit was SVN r17125.
2008-01-12 13:20:38 +00:00
Jeff Squyres
728eccda87 Found this compatibility code yesterday when reviewing some of the C++
bindings with Dan: it's no longer necessary since we're firmly tied to
Open MPI (I'm not sure it was ever necessary, actually...).

This commit was SVN r17017.
2007-12-21 16:23:13 +00:00
Jeff Squyres
26d8fe70c3 Fixes trac:1029: add in support for MPI_CONVERSION_FN_NULL.
This commit brings over all the work from the /tmp-public/datarep
branch.  See commits r16855, r16859, r16860 for the highlights of what
was done.

This commit was SVN r16891.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r16855
  r16859
  r16860

The following Trac tickets were found above:
  Ticket 1029 --> https://svn.open-mpi.org/trac/ompi/ticket/1029
2007-12-07 13:09:07 +00:00
Jeff Squyres
a5798803aa Remove kruft
This commit was SVN r16852.
2007-12-05 14:03:12 +00:00
Ethan Mallove
005652c9d4 * Embed ident strings into the Open MPI libraries using one of the following
methods (in order of precedence):
  1. #pragma ident <ident string> (e.g., Intel and Sun)
  1. #ident <ident string> (e.g., GCC)
  1. static const char ident[] = <ident string> (all others)
By default, the ident string used is the standard Open MPI version string. Only
the following libraries will get the embedded version strings (e.g., DSOs will
not):
  * libmpi.so
  * libmpi_cxx.so
  * libmpi_f77.so
  * libopen-pal.so
  * libopen-rte.so
* Added two new configure options:
  * `--with-package-name="STRING"` (defaults to "Open MPI username@hostname
    Distribution"). `STRING` is displayed by `ompi_info` next to the "Package"
    heading.
  * `--with-ident-string="STRING"` (defaults to the standard Open MPI version
    string - e.g., X.Y.Zr######). `%VERSION%` will expand to the Open MPI
    version string if it is supplied to this configure option.

This commit was SVN r16644.
2007-11-03 02:40:22 +00:00
Brian Barrett
2b8af283de Add ability to completely turn off MPI one-sided support, so that users
can experiment with using ROMIO directly.

This commit was SVN r15922.
2007-08-18 21:35:51 +00:00
Shiqing Fan
0f468f3668 - Remove the solution and project files, will commit them later.
This commit was SVN r15705.
2007-07-31 17:07:02 +00:00
Shiqing Fan
4d7b349cdb - Add VC8 solution and project files.
- If one wants to use this solution, remember to unload the project 'orte-restart' which is currently not working for Windows.

This commit was SVN r15680.
2007-07-30 11:05:34 +00:00
Rainer Keller
0cd2f99711 - Get rid of pendatic C++ namespace warning.
This commit was SVN r15127.
2007-06-18 21:29:09 +00:00
Brian Barrett
7c9bae5eb7 need to protect these includes as well...
This commit was SVN r14912.
2007-06-06 16:25:18 +00:00
Brian Barrett
beb6dd1924 Include the C++ bindings from mpi.h in a way that doesn't require an extra
-I for ${includedir}/openmpi.  Solves many problems, and with just a tad
bit of hackery.  Don't know why I didn't just do this earlier.

Refs trac:542

This commit was SVN r14853.

The following Trac tickets were found above:
  Ticket 542 --> https://svn.open-mpi.org/trac/ompi/ticket/542
2007-06-05 01:42:47 +00:00
Sven Stork
a04c8eb39a - Bring over the visibility feature, for a finer symbol export control
via the visibility feature that is provided by some compilers.

  Per default this feature is disabled, to enable it you need to
  configure with --enable-visibility and obviously you need a compiler
  with visibility support. Please refer to the wiki for more information.
  https://svn.open-mpi.org/trac/ompi/wiki/Visibility

This commit was SVN r14582.
2007-05-04 09:03:37 +00:00
Jeff Squyres
b7b893b771 Need to EXTRA_DIST README.txt so that it gets included in the tarball;
the *_DATA files are not automatically picked up for inclusion into
the tarball.

This commit was SVN r13667.
2007-02-15 16:21:25 +00:00
Jeff Squyres
260f1fd468 Fixes trac:817
The C++ bindings were not tracking keyvals properly -- they were
freeing some internal meta data when Free_keyval() was called, not
when the keyval was actually destroyed (keyvals are refcounted in the
C layer, just like all other MPI objects, because they can live for
long after their corresponding Free call is invoked).  This commit
fixes this problem and several other things:

 * Add infrastructure on the ompi_attribute_keyval_t for an "extra"
   destructor pointer that will be invoked during the "real"
   constructor (i.e., when OBJ_RELEASE puts the refcount to 0).  This
   allows calling back into the C++ layer to release meta data
   associated with the keyval.
 * Adjust all cases where keyvals are created to pass in relevant
   destructors (NULL or the C++ destructor).
 * Do essentially the same for MPI::Comm, MPI::Win, and MPI:Datatype:
   * Move several functions out of the .cc file into the _inln.h file
     since they no longer require locks
   * Make the 4 Create_keyval() functions call a common back-end
     keyval creation function that does the Right Thing depending on
     whether C or C++ function pointers were used for the keyval
     functions.  The back-end function does not call the corresponding
     C MPI_*_create_keyval function, but rather does the work itself
     so that it can associate a "destructor" callback for the C++
     bindings for when the keyval is actually destroyed.
   * Change a few type names to be more indicative of what they are
     (mostly dealing with keyvals [not "keys"]).
 * Add the 3 missing bindings for MPI::Comm::Create_keyval().
 * Remove MPI::Comm::comm_map (and associated types) because it's no
   longer necessary in the intercepts -- it was a by-product of being
   a portable C++ bindings layer.  Now we can just query the C layer
   directly to figure out what type a communicator is.  This solves
   some logistics / callback issues, too.
 * Rename several types, variables, and fix many comments in the
   back-end C attribute implementation to make the names really
   reflect what they are (keyvals vs. attributes).  The previous names
   heavily overloaded the name "key" and were ''extremely''
   confusing.

This commit was SVN r13565.

The following Trac tickets were found above:
  Ticket 817 --> https://svn.open-mpi.org/trac/ompi/ticket/817
2007-02-08 23:50:04 +00:00
Pak Lui
01c45b9637 * should fix the uninitialized function pointers. This is the patch to the
patch in r13391

This commit was SVN r13411.

The following SVN revision numbers were found above:
  r13391 --> open-mpi/ompi@289fbd08de
2007-02-01 05:07:53 +00:00
Pak Lui
289fbd08de * Fix the MPI::Datatype::Create_keyval() & MPI::Win::Create_keyval()
not being able to take C function pointers for either of the 
	copy or the delete fn. Fix by overloading the Create_keyval methods. 
    Fix trac #737, #738. Reviewed by jsquyres.
  *	A couple of cxx tests in ompi-tests (winkeyval.cc & typekeyval.cc) 
	will be re-enabled to regression test for this fix.

This commit was SVN r13391.
2007-01-31 15:00:41 +00:00
Jeff Squyres
61bc9fed3c Duh. Free the temp array when we're done with it. While we're making
this switch, use a clear variable name, too.

This commit was SVN r13347.
2007-01-29 19:04:57 +00:00
Jeff Squyres
e6a0069e95 Fix from an as-yet uncommitted test that Pak will commit shortly.
Found another places that we were incorrectly casting a C++ MPI handle
array to the corresponding C array type and hoping for the best (which
won't work at all).  This commit fixes things so that we now do the
proper conversion between C<-->C++ handles.

This commit was SVN r13346.
2007-01-29 18:44:46 +00:00
Jeff Squyres
b9120aed6d Always make sure to create $(includedir)/openmpi, even if we were
configured with --disable-mpi-cxx so that the default -I flags in the
wrapper compilers don't point to a directory that doesn't exist.
Thanks to Martin Audet for identifying the problem.

This commit was SVN r13296.
2007-01-25 01:59:22 +00:00
Pak Lui
ff1dd4f16d * fixes ticket #730 for supporting both of the pre-errata argument set and
post-errata argument set of MPI::Win::Get_attr

This commit was SVN r13063.
2007-01-10 16:41:21 +00:00
Pak Lui
de51464aad * fix #730 for removing an extra argument from MPI::Win::Get_attr as being
corrected in the MPI 2.0 errata.
 * initialized some variables to make our sensitive sun compiler not to 
   not warn about them when user apps are compiling.

This commit was SVN r13058.
2007-01-09 23:48:39 +00:00
George Bosilca
e72b0c1044 Some compilers (VC) don't like conversions between int and bool.
This commit was SVN r13043.
2007-01-08 22:00:49 +00:00
Brian Barrett
1ba97181dc A number of MPI-2 compliance fixes for the C++ bindings:
* Added Create_errhandler for MPI::File
  * Make errors_throw_exceptions a first-class predefined exception
    handler, and make it work for Comm, File, and Win
  * Deal with error handlers and attributes for Files, Types, and Wins
    like we do with Comms - can't just cast the callbacks from C++
    signatures to C signatures.  Callbacks will then fire with the
    C object, not the C++ object.  That's bad.

Refs trac:455

This commit was SVN r12945.

The following Trac tickets were found above:
  Ticket 455 --> https://svn.open-mpi.org/trac/ompi/ticket/455
2006-12-30 23:41:42 +00:00
Jeff Squyres
0a28212392 This is a workaround to bug in the Intel C++ compiler, version 9.1
(all versions up to and including 20060925).  The issue has been
reported to Intel, along with a small [non-MPI] test program that
reproduces the problem (the test program and the OMPI C++ bindings
work fine with Intel C++ 9.0 and many other C++ compilers).

In short, a static initializer for a global variable (i.e., its
constructor is fired before main()) that takes as an argument a
reference to a typedef'd type will simply get the wrong value in the
argument.  Specifically:

{{{
namespace MPI {
    Intracomm COMM_WORLD(MPI_COMM_WORLD);
}
}}}

The constructor for MPI::Intracomm should get the value of
&ompi_mpi_comm_world.  It does not; it seems to get a random value.

As mandated by MPI-2, annex B.13.4, for C/C++ interoperability, the
prototype for this constructor is:

{{{
class Intracomm {
public:
    Intracomm(const MPI_Comm& data);
};
}}}

Experiments with icpc 9.1/20060925 have shown that removing the
reference from the prototype makes it work (!).  After lots of
discussions about this issue with a C++ expert (Doug Gregor from IU),
we decided the following (cut-n-paste from an e-mail):

-----
> So here's my question: given that OMPI's MPI_<CLASS> types are all
> pointers, is there any legal MPI program that adheres to the above
> bindings that would fail to compile or work properly if we simply
> removed the "&" from the second binding, above?

I don't know of any way that a program could detect this change. FWIW,
the C++ committee has agreed that implementation of the C++ standard
library are allowed to decide arbitrarily between const& and by-value.
If they don't care, MPI users won't care.

When you remove the '&', I suggest also removing the "const". It is
redundant, but can trigger some strange name mangling in Sun's C++
compiler.
-----

So with this change:

 * we now work again with the Intel 9.1 compiler
 * our C++ bindings do not exactly conform to the MPI-2 spec, but
   valid/legal MPI C++ apps cannot tell the difference (i.e., the
   functionality is the same)

This commit was SVN r12514.
2006-11-09 17:34:12 +00:00
Jeff Squyres
31e8f510fe After review with Rolf, decided to be a bit more safe and instead of
assigning status._cancelled, call MPI_STATUS_SET_CANCELLED.

This commit was SVN r12471.
2006-11-07 20:49:31 +00:00