1
1
Граф коммитов

4506 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
07c7a7a255 Make ompi_info behave a bit better if STL decides not to play with 0
length string constructors.  Print a developer warning if we have a
too-long field (in developer builds only).

This commit was SVN r21315.
2009-05-28 16:15:06 +00:00
Jeff Squyres
590fbcff6c Shorten the labels so that we don't throw C++ exceptions for 0-length
strings (true fix for that coming after this).  Also rename so that
its names that MPI users will care about.

This commit was SVN r21314.
2009-05-28 15:51:46 +00:00
Jeff Squyres
97fa83d24f Fix a compiler warning: string::size_type is unsigned, so checking for
>=0 is meaniningless.

This commit was SVN r21313.
2009-05-28 15:44:11 +00:00
Jeff Squyres
f960f2d944 Fix compiler warning
This commit was SVN r21312.
2009-05-28 13:34:48 +00:00
Jeff Squyres
1834fc4ac6 Nysal noticed some repeated header files; removed.
This commit was SVN r21310.
2009-05-28 12:05:42 +00:00
George Bosilca
2f9765926e This is the real commit, the previous one was just a test ... to make
sure Jeff is reading all commits ;)

This commit was SVN r21308.
2009-05-28 00:49:40 +00:00
George Bosilca
63118c9beb Do not allow redefinition of MPI_MAX_DATAREP_STRING.
This commit was SVN r21307.
2009-05-28 00:37:19 +00:00
George Bosilca
be320ca959 Don't add the offset to all segments, only the first one should be affected. Thanks
to Roberto Ammendola for this bug report and patch.

This commit was SVN r21300.
2009-05-27 16:12:18 +00:00
Edgar Gabriel
d93def71ea second part of the 'running out of cids problem', this time focusing on what
happens when hierarch is used. . Two major items:
 - modify the comm_activate step to take an additional argument, indicating
 whether the new communicatio has to go through the collective selection
 step. This is not required sometimes (e.g. when a process calls
 MPI_COMM_SPLIT with color=MPI_UNDEFINED), and contributed significantly to
 the exhaustion of cids.
 - when freeing a communicator, check whether we can reuse the block of cids
 assigned to that comm. This only works if the current front of the cid
 assignment (cid_block_start) is right ater the block of cids assigned to this
 comm.

Fixes trac:1904
Fixes trac:1926

This commit was SVN r21296.

The following Trac tickets were found above:
  Ticket 1904 --> https://svn.open-mpi.org/trac/ompi/ticket/1904
  Ticket 1926 --> https://svn.open-mpi.org/trac/ompi/ticket/1926
2009-05-27 15:21:07 +00:00
Shiqing Fan
b3c077e112 Microsoft doesn't provide inet_pton and inet_ntop APIs on Windows XP, but only on Windows Vista and 2008. So add a stand alone version of inet_pton and inet_ntop functions from ISC.
This commit was SVN r21295.
2009-05-27 14:32:30 +00:00
Josh Hursey
1c58367f8b Fix for makedistcheck. Make sure that distclean removes the mpi-ext.h file that is automaticly generated at configure time.
This commit was SVN r21293.
2009-05-27 14:05:04 +00:00
Rainer Keller
51e2b5dcef - Make the maximum length user strings configurable... Namely
MPI_MAX_PROCESSOR_NAME
      MPI_MAX_ERROR_STRING
      MPI_MAX_OBJECT_NAME
      MPI_MAX_INFO_KEY
      MPI_MAX_INFO_VAL
      MPI_MAX_PORT_NAME
      MPI_MAX_DATAREP_STRING

   Defaults stay as theyr currently are -- and now give an explanation on the
   min/max values being used in a central place...
   m4-macro _OPAL_WITH_OPTION_MIN_MAX_VALUE may be benefical in other parts
   of the configure system.

 - We need some of these in the lower level OPAL for an upcoming commit!
   All other levels base their values on them.

This commit was SVN r21292.
2009-05-27 12:54:40 +00:00
Rainer Keller
88390b0d7c - Just remove white-space at end of lines
This commit was SVN r21291.
2009-05-27 12:46:04 +00:00
Shiqing Fan
7a495e936c Add the generated mpi_portable_platform.h into the install file list.
This commit was SVN r21290.
2009-05-27 12:16:36 +00:00
Rainer Keller
4b9aecb188 - Fix a few buglet's, "suppported", ": ", and
stay below 63 characters  in length...

This commit was SVN r21286.
2009-05-27 02:04:54 +00:00
Rainer Keller
653656f012 - Hey, as of r19461, we're officially endorse MPI-2.1
... even in Fortran ;-)

This commit was SVN r21284.

The following SVN revision numbers were found above:
  r19461 --> open-mpi/ompi@008fa8c5cc
2009-05-27 00:32:23 +00:00
Josh Hursey
3e847c19f0 Per RFC: MPI Interface Extensions Infrastructure
Add infrastructure for MPI Interface Extensions. This allows a developer to create new MPI interfaces that are non-standard.

The following email thread describes the functionality proposed in the RFC:
  http://www.open-mpi.org/community/lists/devel/2009/05/5997.php

The following wiki page describes how to use and enable the extensions:
  https://svn.open-mpi.org/trac/ompi/wiki/MPIExtensions

This commit was SVN r21272.
2009-05-26 20:49:35 +00:00
Shiqing Fan
19ecbfa324 A quick and simple fix for Windows supporting deprecated functionality warnings, let MTT run again first. MS compiler attributes check has to be accomplished in order to fully enable this feature on Windows.
This commit was SVN r21267.
2009-05-23 22:12:54 +00:00
Rainer Keller
fbb2834977 - Missed string.h to get rid of warnings...
This commit was SVN r21265.
2009-05-22 23:47:49 +00:00
Rainer Keller
916eb1fb1e - As proposed in RFC and telcon, warn the user about deprecated
functionality (per MPI-2.1). This warning can be toggled using
   --enable-mpi-interface-warning (default OFF), but can be
   selectively turned on passing
       mpicc -DOMPI_WANT_MPI_INTERFACE_WARNING

   Using icc, gcc < 4.5, warnings (such as in mpi2basic_tests) show:
     type_vector.c:83: warning: ‘MPI_Type_hvector’ is deprecated
     (declared at /home/../usr/include/mpi.h:1379)

   Using gcc-4.5 (gcc-svn) these show up as:
     type_vector.c:83: warning: ‘MPI_Type_hvector’ is deprecated
     (declared at /home/../usr/include/mpi.h:1379):
     MPI_Type_hvector is superseded by MPI_Type_create_hvector in MPI-2.0


   Jeff and I propose to turn such warnings on with Open MPI-1.7 by default.


 - Detection of user-level compiler is handled using the preprocessor
   checks of GASnet's other/portable_platform.h (thanks to Paul Hargrove
   and Dan Bonachea) adapted into ompi/include/mpi_portable_platform.h
   (see comments).

   The OMPI-build time detection is output (Familyname and Version)
   with ompi_info.

   This functionality (actually any upcoming __attribute__) are turned
   off, if a different compiler (and version) is being detected.


 - Note, that any warnings regarding (user-compiler!=build-compiler)
   as discussed in the RFC are _not_ included for now.


 - Tested on Linux with --enable-mpi-interface-warning on
   Linux, gcc-4.5 (deprecated w/ specific msg)
   Linux, gcc-4.3 (deprecated w/o specific msg)
   Linux, pathscale 3.1 (deprecated w/o specific msg)
   Linux, icc-11.0 (deprecated w/o specific msg)

   Linux, PGI-8.0.6 accepts __deprecated__ but does not issue a warning,
   further investigation needed...

This commit was SVN r21262.
2009-05-22 04:39:43 +00:00
Rainer Keller
225a1d6d8e - For memcpy and memset need string.h
This commit was SVN r21259.
2009-05-21 22:36:06 +00:00
George Bosilca
26342508de It is supposed not to be set until we detect our local rank ...
This commit was SVN r21256.
2009-05-20 17:41:13 +00:00
George Bosilca
7bd97ac17b Try to deal with the ticket #1831. I think we might reach a case where the
shm_fifos values are only partially updated, and this leads to wrong values
for the offset. Moving the write barrier at the right place, plus forcing
some read barriers might help.

In addition I get rid of the sm_offset array which is completely useless.

This commit was SVN r21253.
2009-05-19 22:50:44 +00:00
Abhishek Kulkarni
b48f13cda4 Minor fix in the man page for MPI_Comm_remote_size
This commit was SVN r21252.
2009-05-19 15:23:44 +00:00
Jeff Squyres
8dc83b0865 Use the newer ORTE_NAME_PRINT instead of ORTE_NAME_ARGS
This commit was SVN r21250.
2009-05-18 14:38:13 +00:00
Jeff Squyres
17761f60b9 Clean up a few compiler warnings
This commit was SVN r21243.
2009-05-14 15:40:38 +00:00
Jeff Squyres
efd229b56b Clean up bunches of compiler warnings
This commit was SVN r21242.
2009-05-14 15:39:53 +00:00
Rainer Keller
b2f8095ba7 - Update to fix in r21234: as discussed on devel@,
for printing size_t use "%lu" and cast to (unsigned long).

This commit was SVN r21238.

The following SVN revision numbers were found above:
  r21234 --> open-mpi/ompi@22b6177fb9
2009-05-14 14:10:22 +00:00
Rainer Keller
d5cb1b4f97 - Shown by __opal_attribute_format__, probably macro
was converted from opal_output_verbose

This commit was SVN r21237.
2009-05-14 13:57:37 +00:00
Pavel Shamis
14eb11c18a Removing unused and duplicated XRC code.
I just found that we have 2 place where we call for XRC domain
creation. First one in init_one_device() and second one prepare_device_for_use().
They have absolutely identical code, but the call in init_one_device() is useless
because on this stage we don't know about QP configuration and we don't know if we need 
XRC at all. So I removing the duplicated code from init_one_device().

This commit was SVN r21235.
2009-05-14 13:15:00 +00:00
Rainer Keller
22b6177fb9 - Use the "z" length modifier for size_t arguments for printf.
This commit was SVN r21234.
2009-05-14 00:52:20 +00:00
Rainer Keller
73fd329cbd - Add the proper __opal_attribute_format__(__printf__...) to
declarations.

This commit was SVN r21226.
2009-05-14 00:10:59 +00:00
Iain Bason
a282cf062c Roll back Jeff's roll back (r21028) of Iain's changes (r20926, r20941, r20950).
It turns out that the "Intel" interpretation of the MPI spec violates
the Fortran standard (section 14.6.1.1 of the Fortran 95 standard).

This commit was SVN r21225.

The following SVN revision numbers were found above:
  r20926 --> open-mpi/ompi@0a24eadaad
  r20941 --> open-mpi/ompi@045b0e8871
  r20950 --> open-mpi/ompi@73af921c22
  r21028 --> open-mpi/ompi@25249c9843
2009-05-13 18:32:13 +00:00
Jeff Squyres
424d9ed0c8 Fix "reorder" parameter to be logical, per MPI spec.
This commit was SVN r21215.
2009-05-12 14:08:14 +00:00
Ralph Castain
d396f0a6fc Per the discussion on the devel list, move the binding of processes to processors from MPI_Init to process start. This involves:
1. replacing mpi_paffinity_alone with opal_paffinity_alone - for back-compatibility, I have aliased mpi_paffinity_alone to the new param name. This caus
es a mild abstraction break in the opal/mca/paffinity framework - per the devel discussion...live with it. :-) I also moved the ompi_xxx global variable
 that tracked maffinity setup so it could be properly closed in MPI_Finalize to the opal/mca/maffinity framework to avoid an abstraction break.

2. Added code to the odls/default module to perform paffinity binding and maffinity init between process fork and exec. This has been tested on IU's odi
n cluster and works for both MPI and non-MPI apps.

3. Revise MPI_Init to detect if affinity has already been set, and to attempt to set it if not already done. I have *not* tested this as I haven't yet f
igured out a way to do so - I couldn't get slurm to perform cpu bindings, even though it supposedly does do so.

This has only been lightly tested and would definitely benefit from a wider range of evaluation...

This commit was SVN r21209.
2009-05-12 02:18:35 +00:00
Jeff Squyres
f7f5603d5c * No need for warning aggregation here; orte_show_help() does that
for us already.
 * Slightly clarify the error message strings; now they match the new
   error strings for btl_openib_ipaddr_in|exclude

This commit was SVN r21197.
2009-05-09 12:29:06 +00:00
Jeff Squyres
cd6c6e6206 Add some error checking into the btl_openib_ipaddr_in|exclude
calculations, and fix a few small memory leaks in that same logic.

This commit was SVN r21196.
2009-05-09 12:28:09 +00:00
Edgar Gabriel
0bc8164a11 fix the group_compare operation which failed to recognize unequal groups in
case the first process of the group was not represented at all in the second
group. Also added some cleanup of the code w.r.t. booleans vs. ints.
 
Thanks for Geoffrey Irving for reporting the bug and providing the initial
solution. 

This commit was SVN r21192.
2009-05-08 13:51:28 +00:00
Jeff Squyres
c166678cf2 Gah -- forgot to test the case where btl_tcp_if_include wasn't
specified.  :-(

This commit was SVN r21191.
2009-05-07 21:50:02 +00:00
Jeff Squyres
97c9610b7f Note to self: test error messages before committing.
This commit was SVN r21190.
2009-05-07 20:31:26 +00:00
Jeff Squyres
4779520787 Add the ability to btl_tcp_if_include and btl_tcp_if_exclude based on
subnet specifications (in addition to interface names).  These
parameters now take a comma-delimited list of interfaces names and/or
a.b.c.d/x specifications (only IPv4 currently supported for subnet
specifications).  For example:

  mpirun --mca btl_tcp_if_include 10.10.30.0/8,eth0

This commit was SVN r21189.
2009-05-07 18:53:33 +00:00
Shiqing Fan
537b8cd8b1 Get rid of improper use of SET_SOURCE_FILES_PROPERTIES. When using the latest CMake (2.6 patch 4), we get many errors, which didn't show in previous version.
This commit was SVN r21188.
2009-05-07 17:41:05 +00:00
Rainer Keller
c868ec21b0 - Fix Coverity CID 30;
If there is no errhandler, can't reference it...
   Return early.

This commit was SVN r21187.
2009-05-07 17:05:15 +00:00
Rainer Keller
2941cb1494 - Fix Coverity CID 525 and 526 --- and some more;
- due to the <= with we could overrun the array
   - we didn't correctly test at _all_, since we never marked the
     ranks already excluded / included...
   - when returning in error, we should free (elements_int_list)...

This commit was SVN r21186.
2009-05-07 16:45:18 +00:00
Jeff Squyres
af8f0438ef Make a better error message when the TCP BTL fails to connect
This commit was SVN r21184.
2009-05-07 14:09:35 +00:00
Jeff Squyres
04f3b23f1b Fix one tiny name change that was missed.
This commit was SVN r21183.
2009-05-06 21:41:59 +00:00
Jeff Squyres
93ed8cf78f Remove this very, very outdated file.
This commit was SVN r21182.
2009-05-06 21:03:34 +00:00
Greg Koenig
60485ff95f This is a very large change to rename several #define values from
OMPI_* to OPAL_*.  This allows opal layer to be used more independent
from the whole of ompi.

NOTE: 9 "svn mv" operations immediately follow this commit.

This commit was SVN r21180.
2009-05-06 20:11:28 +00:00
Matthias Jurenz
fb3bbb8021 Updated version number to 5.4.9
This commit was SVN r21178.
2009-05-06 10:54:43 +00:00
Matthias Jurenz
3f83c94328 Fixed faulty searching for matching filter directive
This commit was SVN r21177.
2009-05-06 10:54:27 +00:00