ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
10 943 коммитов 3 Ветки 0 Теги 130 MiB
18d1d3b408
Граф коммитов

10943 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Galen Shipman
18d1d3b408 Add ORTE ALPS support (Cray XT CNL) 
This commit was SVN r17482.
 2008-02-17 19:29:06 +00:00
Galen Shipman
cec3d96a94 configure changes for Cray XT CNL (adds --with-alps param) auto detection is 
not included (or desired) 

This commit was SVN r17481.
 2008-02-17 19:02:36 +00:00
Galen Shipman
db3bd304f6 Platform file for Cray XT - CNL 
This commit was SVN r17480.
 2008-02-17 19:00:09 +00:00
Gleb Natapov
354c5bc5e1 Don't call progress() from OB1 fragment scheduling functions. They don't serve 
any purpose and case recursion calls to progress engine.

This commit was SVN r17478.
 2008-02-17 12:42:32 +00:00
Rich Graham
1cd8a2e578 checkpoint - works for 2 procs, but not more. 
This commit was SVN r17477.
 2008-02-17 05:21:58 +00:00
George Bosilca
058e8d5f11 These have to be defined when we don't include ompi_config.h 
This commit was SVN r17475.
 2008-02-16 18:05:07 +00:00
George Bosilca
512b24affb Add support for all optional Fortran logical types (MPI_LOGICAL1, 
MPI_LOGICAL2, MPI_LOGICAL4 and MPI_LOGICAL8). This commit close
the ticket #331.

This commit was SVN r17473.
 2008-02-15 22:54:20 +00:00
Shiqing Fan
26be580c2d Remove the MPI level functions inside Open MPI library, and avoid break the usage of weak symbols. Thanks to George. 
This commit was SVN r17469.
 2008-02-15 10:31:29 +00:00
Rich Graham
8006927ae8 free buffer, rather than ask for another one, when done with the memory. 
This commit was SVN r17468.
 2008-02-15 04:21:58 +00:00
Rich Graham
2277b47ab9 register mca_coll_sm2_allreduce_intra - function still does not do any 
reduction operations.

This commit was SVN r17467.
 2008-02-15 04:13:00 +00:00
Rich Graham
9b0687e6df add buffer allocation and deallocation calls to the allreduce routine, so 
I can start debugging the memory management code.  The allreduce fucntion
 does nothing at this stage.

This commit was SVN r17466.
 2008-02-15 03:59:14 +00:00
George Bosilca
be2579467a With the new ompi_free_list this is not needed anymore. 
This commit was SVN r17465.
 2008-02-15 03:22:16 +00:00
Rich Graham
41943dbd76 adding missing files. 
This commit was SVN r17462.
 2008-02-15 00:59:28 +00:00
Rich Graham
41f4b06b39 buffer allocate/release code is fully written, and compiles. Now need to debug. 
This commit was SVN r17461.
 2008-02-15 00:57:44 +00:00
Rich Graham
7cc58768cd checkpoint something that compiles 
This commit was SVN r17460.
 2008-02-15 00:33:14 +00:00
Rich Graham
292d930eea check point. 
This commit was SVN r17457.
 2008-02-14 20:00:26 +00:00
Donald Kerr
58bf7f5a1d add uintptr_t to prevent the possibility of a signed extension occuring 
This commit was SVN r17456.
 2008-02-14 19:16:34 +00:00
Aurelien Bouteiller
3ffe845187 Fixed warning. 
This commit was SVN r17454.
 2008-02-14 15:18:19 +00:00
Jeff Squyres
6420db7088 Add missing header file that caused compilation errors in the 
rhc-step2b branch last night.

This commit was SVN r17453.
 2008-02-14 14:10:27 +00:00
George Bosilca
255cd2186b Improve the performance of the MX BTL. Correct the fake PUT 
protocol.

This commit was SVN r17452.
 2008-02-14 04:38:55 +00:00
Aurelien Bouteiller
e7aaf6aa67 Patch to introduce PRI printf constants on architecture that do not provide C99 inttypes.h. Mainly usefull on windows, but might also prove helpful to deal with all the size_t and other size changing datatypes that used to be casted long long in printf/opal_output to avoid warnings. 
This commit was SVN r17451.
 2008-02-14 03:31:49 +00:00
Adrian Knoth
f1648f08df Advanced address selection code from Thomas Peiselt. Re #1207, #1027 
This commit was SVN r17450.
 2008-02-13 21:53:00 +00:00
Dan Lacher
6ff2123833 "fixes trac:1213" 
C++ breakage when used with --enable-visibility

This commit was SVN r17448.

The following Trac tickets were found above:
  Ticket 1213 --> https://svn.open-mpi.org/trac/ompi/ticket/1213
 2008-02-13 19:47:16 +00:00
Josh Hursey
95c31388e1 It was observed that the component constraint logic is currently only used 
by the checkpoint/restart feature. Other constraints could be enforced here,
but at the moment it is only the checkpointable constraint.

So this commit just removes this logic from non-c/r builds. If someone 
wanted to add a new constraint in the future then there is a comment in
the code that directs them a bit.

This commit was SVN r17447.
 2008-02-13 19:26:25 +00:00
Sharon Melamed
5b2dab2439 Reverted commit # r17443 
This commit was SVN r17446.

The following SVN revision numbers were found above:
  r17443 --> open-mpi/ompi@88ce5a2b73
 2008-02-13 14:07:12 +00:00
Matthias Jurenz
bdc616837a Added "AUTOMAKE_OPTION = -Wno-gnu" 
This commit was SVN r17445.
 2008-02-13 13:22:44 +00:00
Sharon Melamed
88ce5a2b73 Replaced PLPA to the latest PLPA (plpa-1.1a3r123) 
This commit was SVN r17443.
 2008-02-13 13:09:11 +00:00
Gleb Natapov
0a1fa2cb56 req_match_received is set inside MCA_PML_OB1_RECV_REQUEST_MATCHE(). 
This commit was SVN r17442.
 2008-02-13 08:34:39 +00:00
Gleb Natapov
876f49f1a7 Remove unnecessary assignment. It is done later in the same function. 
This commit was SVN r17441.
 2008-02-13 08:28:25 +00:00
George Bosilca
79381c0c44 Don't forget to add the memhecker.h header file to the "make dist". 
This commit was SVN r17440.
 2008-02-13 02:19:06 +00:00
Shiqing Fan
92bf2f27f3 Show information of memchecker component. 
This commit was SVN r17439.
 2008-02-12 23:07:14 +00:00
Rainer Keller
9cd2c6f48b - Instead of calling RUNNING_ON_VALGRIND, 
implement specific function, thereby
   removing bogus requirement on valgrind/valgrind.h
   dough...
 - Call specific function runindebugger() before
   doing expensive checks on each component of struct.
 - Get rid of void* warnings..

This commit was SVN r17438.
 2008-02-12 20:37:51 +00:00
Jeff Squyres
280bf75b5f Update svn:ignore's to no longer ignore all the sym links that were 
previously generated.

This commit was SVN r17437.
 2008-02-12 19:06:00 +00:00
Jeff Squyres
17ede97ef8 Two fixes to revert some long-ago decisions that seemed like a good 
idea at the time, but led to logistical difficulties in importing new
versions of ROMIO: 

* We are effectively eliminating the ROMIO file prefix rule hacks in
  the ROMIO component, which create symlinks from foo.c to
  io_romio_foo.c.  In reality, the file name conflict potential will
  be small.
* Additionally, we are effectively eliminating the ROMIO function
  prefix rule in the ROMIO component.  This is another place where
  there are generally problems with the merge up new versions of ROMIO
  and/or patches from the user community (for their own local builds).
  In reality, since other major MPI implementations provides the same
  exact symbols, it won't cause any practical problems for users.

In return, we make it ''much'' simpler to apply ROMIO patches to Open
MPI.  The problem right now is that any patch will have filenames such
as ad_panfs.c, but Open MPI will only have io_romio_ad_panfs.c, making
things extremely difficult for users.  I believe, for example, that
this would make it possible for LANL to have applied their patches
without too much hassle on either their part or our part.  It will
also make things easier for OMPI when we/they want to do the next
ROMIO upgrade (this was one of the sources of problems on each
upgrade).

This commit was SVN r17436.
 2008-02-12 18:55:17 +00:00
Shiqing Fan
54c7b71cfd Use the correct way of including memchecker.h, which will work with '--with-devel-headers'. 
This commit was SVN r17435.
 2008-02-12 18:01:17 +00:00
Rainer Keller
7621800477 - Fix and add comments -- output full name for pd 
- Protect argument in macro...

This commit was SVN r17434.
 2008-02-12 16:59:59 +00:00
Rainer Keller
b20f434306 - really minor fix in comment. 
This commit was SVN r17433.
 2008-02-12 16:54:27 +00:00
Jeff Squyres
7746549f30 '''TEMPORARY''' fix for #1211 to allow normal builds on the trunk: 
ensure that including valgrind.h is within the WANT_MEMCHECKER macro.  

But this does not seem right; memchecker is a framework and valgrind
is the component -- why are we including a component-specific header
file in a top-level OMPI .h file?  It seems like there should be a
memchecker .h file that generically hides these component-specific
details (i.e., what if we add some other memchecker components
someday?).

This commit was SVN r17432.
 2008-02-12 15:06:02 +00:00
Jeff Squyres
8cc9a8e992 Update svn:ignore 
This commit was SVN r17431.
 2008-02-12 14:45:55 +00:00
Jeff Squyres
45ea7230ad Update the hgignore script 
This commit was SVN r17430.
 2008-02-12 14:22:54 +00:00
Jeff Squyres
6d75691de3 Remove now-useless variable. 
This commit was SVN r17429.
 2008-02-12 13:09:34 +00:00
Jeff Squyres
6adc5015f9 This file was accidentally re-introduced in r17409. 
This commit was SVN r17428.

The following SVN revision numbers were found above:
  r17409 --> open-mpi/ompi@98f70d6318
 2008-02-12 13:07:44 +00:00
Jeff Squyres
04e026fa98 Fix "make check"; manually include <string.h> since the datatype 
header files were re-orged to have fewer dependencies

This commit was SVN r17427.
 2008-02-12 13:02:53 +00:00
Matthias Jurenz
12782ba700 Added Ralfs's patch to make future contrib integration easier. Thanks, Ralf! 
This commit was SVN r17426.
 2008-02-12 11:48:01 +00:00
Shiqing Fan
fa79631d41 and fix a miss type. 
This commit was SVN r17425.
 2008-02-12 08:50:13 +00:00
Shiqing Fan
f5792bbda5 merging the memchecker into trunk. 
This commit was SVN r17424.
 2008-02-12 08:46:27 +00:00
Tim Mattox
357bbe00b3 Updated the NEWS file for 1.2.6 changes. 
This commit was SVN r17421.
 2008-02-11 21:49:21 +00:00
Matthias Jurenz
ecd5d4e634 merging VampirTrace-5.4.4.3 into the main branch 
This commit was SVN r17417.
 2008-02-11 11:47:29 +00:00
Gleb Natapov
cf801edfe5 Use carto topology framework to choose which HCAs to use. 
This commit was SVN r17414.
 2008-02-11 10:34:11 +00:00
George Bosilca
ee321748a6 The lost space. 
This commit was SVN r17413.
 2008-02-10 22:08:49 +00:00