ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
3 446 коммитов 3 Ветки 0 Теги 130 MiB
17f37130d2
Граф коммитов

3446 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
George Bosilca
17f37130d2 First fully working version of GM. Next step ... improuvements ... 
This commit was SVN r3843.
 2004-12-17 08:39:07 +00:00
Craig E Rasmussen
c134c911e3 Changed declared type of function pointers to void* from MPI_Fint* 
This commit was SVN r3842.
 2004-12-17 05:18:01 +00:00
Jeff Squyres
ae5180aa3b Ok, it's *not* enough to only have one of the files compilable. Need 
to make them all compilable.

#if 0'ed out one section in soh_base_open.c that needs to be fixed.

This commit was SVN r3841.
 2004-12-17 03:20:39 +00:00
Jeff Squyres
63474e0232 Have to have *one* compilable file or some platforms complain. 
Grrr...

This commit was SVN r3840.
 2004-12-17 00:26:16 +00:00
Jeff Squyres
c58a99b6ac Add a missing Makefile.am for soh, and add some svn:ignore's. 
Shame on me for not doing a sanity build :-\ -- thanks Brian for
pointing it out...

This commit was SVN r3839.
 2004-12-16 23:28:02 +00:00
Brian Barrett
bb7de89545 * Add configure tests for SA_RESTART signal constant and sa_len 
* protect use of SA_RESTART in event library

This commit was SVN r3838.
 2004-12-16 21:37:57 +00:00
Jeff Squyres
32d85dd7eb Properly add the soh framework in all the places it needs to be. Left 
the src/mca/soh/base/*.c files out of the default build because
they're uncompilable right now -- don't want to step on any of Ralph's
local changes.

This commit was SVN r3837.
 2004-12-16 18:52:33 +00:00
Jeff Squyres
1fc56e8b9c Fix minor typo 
This commit was SVN r3836.
 2004-12-16 18:43:54 +00:00
Jeff Squyres
a5b61fa75c Remove svn:executable from source files 
This commit was SVN r3835.
 2004-12-16 17:49:50 +00:00
Brian Barrett
6d969db21b * Code for bug 1036 - add special CFLAGS to enable the restrict keyword 
for compilers that don't support it out of the box but can with
  the right flag

This commit was SVN r3834.
 2004-12-16 16:34:16 +00:00
Brian Barrett
d3d52a4aed * Changes to make MPI_Comm_spawn_multiple work properly 
This commit was SVN r3833.
 2004-12-16 15:42:02 +00:00
Craig E Rasmussen
cfdeb89420 Fixed declaration of function pointers by declaring as external and removing intent. 
This commit was SVN r3832.
 2004-12-16 04:58:22 +00:00
Craig E Rasmussen
88eb530a32 Fixed tests of function pointer parameters 
This commit was SVN r3831.
 2004-12-16 04:56:14 +00:00
Craig E Rasmussen
81afaad919 Set assignment of void types (pointers) to VOID_VAL 
This commit was SVN r3830.
 2004-12-16 04:54:15 +00:00
George Bosilca
58099fdca7 Correctly compute the stack count for contiguous datatypes. At the position 1 
we should always have the amount in bytes that still have to be copied on the last
basic datatype (count included).

This commit was SVN r3829.
 2004-12-16 02:15:08 +00:00
George Bosilca
a61a24f545 added support for em64t (cf. Torsten Hoefler). 
This commit was SVN r3828.
 2004-12-16 02:13:29 +00:00
Craig E Rasmussen
354d78b0b8 Fixed comment errors on some MPI_File_* methods. 
This commit was SVN r3827.
 2004-12-15 21:11:51 +00:00
Mitch Sukalski
543338c070 more fixes 
This commit was SVN r3826.
 2004-12-15 20:28:10 +00:00
Brian Barrett
c0985fad73 * turns out that there won't be a process status if the process died 
before it hit ompi_rte_init (duh!).  So don't print a ton of messages
  complaining about something that isn't really a problem

This commit was SVN r3825.
 2004-12-15 19:26:00 +00:00
Brian Barrett
e0483a5c26 * Registry no longer barfs when it gets pounded at startup, so remove 
sleep hack.
* Fix some places where processes would not get cleaned up if an error
  occured during startup

This commit was SVN r3824.
 2004-12-15 19:22:30 +00:00
Brian Barrett
adf9c7cb81 * fix book keeping error that caused badness when 1) processes were started 
on multiple nodes and 2) the processes unexpectedly quit

This commit was SVN r3823.
 2004-12-15 18:52:15 +00:00
Ralph Castain
087f9a361b Since the &*(&(&* subversion won't let me commit the whole thing - getting the $#@$# "won't delete locally modified directory nonsense again - I've committed this separately. I'll have to blow away my existing tree and checkout another to verify things still work. 
Grrrrrr...

This commit was SVN r3822.
 2004-12-15 18:38:34 +00:00
Ralph Castain
8d94778f1e Create a new state-of-health monitoring framework and move the bproc monitoring code to it. Put in an .ompi-ignore to prevent it from being compiled for now. Lots more definition needs to be done here - design document to follow when I can get to it. 
This commit was SVN r3821.
 2004-12-15 18:36:21 +00:00
Brian Barrett
43b565f110 * add missing header file 
This commit was SVN r3820.
 2004-12-15 03:04:04 +00:00
Craig E Rasmussen
24ab817703 1. Fixes for procedures with function pointer arguments. 
2. Fixed for void* when method is not templated (not an array).

This commit was SVN r3819.
 2004-12-14 23:25:55 +00:00
Craig E Rasmussen
f9c8c89f1b 1. Fixed interface declaration for procedures taking function pointer 
arguments.
2. Some void* arguments are Fortran integers, rather than array memory.
   This is needed for void* when methods don't have the template='yes'
   tag.

This commit was SVN r3818.
 2004-12-14 23:23:50 +00:00
Brian Barrett
1901882225 * first take at a cntl-c handler for mpirun. This does not do everything 
that we want, but will do a reasonable job at cleaning up the job
  if SIGINT (cntl-c) or SIGTERM are received between spawning of processes
  and the death of all the processes.

  If you see strange errors out of mpirun, please let me know.  I'm sure
  there are a couple race conditions.  I'm going to clean the code up
  tonight to try to reduce some of them.

This commit was SVN r3817.
 2004-12-14 21:21:14 +00:00
Brian Barrett
f6b8ac67ee * yeah, so it turns out that for an unsigned int, 0 - 1 doesn't equal -1. 
Since there are no elements in the list, this function doesn't need to
  do anything anyway.  So just short circuit

This commit was SVN r3816.
 2004-12-14 21:06:49 +00:00
Mitch Sukalski
c551d387a1 more IB header fixes 
This commit was SVN r3815.
 2004-12-14 20:05:12 +00:00
Brian Barrett
2a8f636d6e * and one more dumb mistake bites the dust 
This commit was SVN r3814.
 2004-12-14 18:27:05 +00:00
Brian Barrett
dd7c53dfa3 * fix dumb error causing segfault in mpirun 
This commit was SVN r3813.
 2004-12-14 18:04:39 +00:00
Mitch Sukalski
19dbfd376b IB header fixes 
This commit was SVN r3812.
 2004-12-14 17:56:51 +00:00
Tim Woodall
60e43d6738 set progress to be non-blocking for non-threaded build 
This commit was SVN r3811.
 2004-12-14 16:35:38 +00:00
Tim Woodall
572df54b2a enable event processing for oob w/ non-thread build 
This commit was SVN r3810.
 2004-12-14 16:34:10 +00:00
Jeff Squyres
7abc1f0f3d Remove the outdated src/os tree -- all this atomic stuff is now in 
src/include/sys (and has been for a long time).

This commit was SVN r3809.
 2004-12-14 16:15:15 +00:00
Brian Barrett
2b9f9f67a4 * if we are on broken linux threads, make sure that forks and waitpids all 
happen in the event thread so that the process starters can actually 
  reap the dead processes when required
* Added logic to ompi_mpi_abort to kill both local and remote groups

This commit was SVN r3808.
 2004-12-14 15:47:31 +00:00
Jeff Squyres
ef5edc5dbe Update the nightly unimplemented report to skip the MPI-2 one-sided 
functions

This commit was SVN r3807.
 2004-12-14 13:57:49 +00:00
Jeff Squyres
9ddee8c4b3 Remove accidental second Stuttgart copyright notice 
This commit was SVN r3806.
 2004-12-14 13:44:36 +00:00
Craig E Rasmussen
865edfd95b Removed optional tag from ierr declaration to correct error in string 
length.  This error was seen in some MPI functions with a char*
parameter on IBM XL compiler.

This commit was SVN r3805.
 2004-12-14 05:45:27 +00:00
Craig E Rasmussen
d499ffdbc9 Removed optional from ierr declaration. This was needed to get the string 
length parameter to come out correctly (for C interfaces with char*).

This commit was SVN r3804.
 2004-12-14 05:41:42 +00:00
Brian Barrett
be7d989b0e * remove the code to disable the event signal handling code, since we really 
need it for anything in the startup code to work

This commit was SVN r3803.
 2004-12-14 03:10:48 +00:00
Jeff Squyres
3966e30902 Remove every part of MPI-2 one-sided functionality from the tree with 
#if OMPI_WANT_MPI2_ONE_SIDED and some automake conditionals.  Also had
to add some AC_SUBSTs to eliminate part of mpif.h (otherwise the
"external" statements would have made undefined symbols).

All the MPI-2 one-sided functionality (including the skeleton
top-level MPI API functions that only invoke an MPI exception) can be
re-enabled with --enable-mpi2-one-sided.

This commit was SVN r3802.
 2004-12-14 02:35:03 +00:00
Jeff Squyres
41adbce3b0 Fix compiler warning: remove unused variable 
This commit was SVN r3801.
 2004-12-14 02:13:29 +00:00
Jeff Squyres
900f3bde32 - Remove some old debugging printf's 
- Formalize the Windoze output
- The facilities for lazy opening of files were already included in
  here (yay foresight!); so just don't open the file aggressively when
  we ompi_output_open(); instead, let the first ompi_output() open the
  file.  This allows the session directory to stay empty (and
  therefore removable) if the file is never written to.

This commit was SVN r3800.
 2004-12-13 22:39:09 +00:00
Jeff Squyres
49c6784a21 Add a missing OMPI_THREAD_UNLOCK. Doh! 
This commit was SVN r3799.
 2004-12-13 22:06:40 +00:00
George Bosilca
32285cb1f5 Handle the unexpected messages. 
This commit was SVN r3798.
 2004-12-13 21:44:02 +00:00
Jeff Squyres
50afa840cc Add simple wrappers around malloc / free so that these functions are 
at least usable -- they just don't provide any benefit for message
passing yet.

This commit was SVN r3797.
 2004-12-13 20:02:02 +00:00
Brian Barrett
cb89d32009 * Cleanup of name server usage in the pcm (also known as actually using the 
name server).
* Add return status message for kill messages from the contact pcm doing 
  the actual killing so that MPI_Abort or ompi_rte_{kill,term}_{proc,job}
  have a useful return value.
* Cleanup the per-started-process local storage in the pcm base to not have
  so much code duplication
* Since there are now 4 kill functions (signal or terminate a proc or job)
  combine them into one function in the pcm interface.  Makes life easier
  all around for PCM authors.  Already had to combine for the message
  transfer.
* Fix race condition in the bootproxy code that was causing it not to
  have the right count for number of alive processes

This commit was SVN r3796.
 2004-12-13 15:41:59 +00:00
Brian Barrett
a1aeb8dab3 * Add some checks for bad parameters so we don't have frees of NULL 
pointers and the like

This commit was SVN r3795.
 2004-12-13 14:11:38 +00:00
George Bosilca
904d075c39 Resolve the fragmentation problem with contiguous data. Now we respect the maximum 
amount suggested by the caller, and update the fields correctly.

This commit was SVN r3794.
 2004-12-13 05:40:56 +00:00