Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
10 years agocosmetics
alegrand [Tue, 15 Dec 2009 16:33:17 +0000 (16:33 +0000)]

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6896 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDo not spread getline management here and there but only in simgrid_config.h.
alegrand [Tue, 15 Dec 2009 16:33:06 +0000 (16:33 +0000)]
Do not spread getline management here and there but only in simgrid_config.h.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6895 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoremove useless dependencies
alegrand [Tue, 15 Dec 2009 16:33:04 +0000 (16:33 +0000)]
remove useless dependencies

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6894 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoTry to improve getline portability...
alegrand [Tue, 15 Dec 2009 16:33:01 +0000 (16:33 +0000)]
Try to improve getline portability...

In the configure, you test for the presence of getline using
    #define _GNU_SOURCE
    #include <stdio.h>
So it is detected as functionnal on my machine (hardy) but if you do
not put these lines in simgrid_config.h it will break. The only thing
is that other headers may include stdio.h earlier in which case the
later _GNU_SOURCE will be useless... :(

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6893 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agokill now unused variable
mquinson [Fri, 11 Dec 2009 13:42:37 +0000 (13:42 +0000)]
kill now unused variable

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6892 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDo not clear memory before freeing it (useless and fails on supernovae's ubuntu when...
mquinson [Fri, 11 Dec 2009 13:41:24 +0000 (13:41 +0000)]
Do not clear memory before freeing it (useless and fails on supernovae's ubuntu when size=0)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6891 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoMore explicit inline marking of functions
mquinson [Fri, 11 Dec 2009 13:31:43 +0000 (13:31 +0000)]
More explicit inline marking of functions

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6890 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoallow smpicc to survive to non-functionnal readlink on mac (by doing as if there...
mquinson [Fri, 11 Dec 2009 12:53:16 +0000 (12:53 +0000)]
allow smpicc to survive to non-functionnal readlink on mac (by doing as if there were no link around)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6889 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agodon't try to distribute a file which does not exist (anymore)
mquinson [Fri, 11 Dec 2009 12:53:14 +0000 (12:53 +0000)]
don't try to distribute a file which does not exist (anymore)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6888 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAvoid a name conflict with /usr/include/sys/wait.h on mac (at least)
mquinson [Fri, 11 Dec 2009 12:26:49 +0000 (12:26 +0000)]
Avoid a name conflict with /usr/include/sys/wait.h on mac (at least)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6887 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoWe need to try linking the code to detect getline, or gcc will think that this is...
mquinson [Fri, 11 Dec 2009 12:25:28 +0000 (12:25 +0000)]
We need to try linking the code to detect getline, or gcc will think that this is a yet undefined external symbol

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6886 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agouse simgrid_config.h in example code relying on getline
mquinson [Fri, 11 Dec 2009 12:20:59 +0000 (12:20 +0000)]
use simgrid_config.h in example code relying on getline

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6885 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDo not mark inline hte functions of which we manipulate pointers to
mquinson [Fri, 11 Dec 2009 12:18:36 +0000 (12:18 +0000)]
Do not mark inline hte functions of which we manipulate pointers to

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6884 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDo not mark all public function as potentially inline since it breaks on mac (get...
mquinson [Fri, 11 Dec 2009 12:13:56 +0000 (12:13 +0000)]
Do not mark all public function as potentially inline since it breaks on mac (get inlined in any case). Mark inline functions explicitelly

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6883 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agocreating a neat config file is good. Using it is better ;)
mquinson [Fri, 11 Dec 2009 10:50:46 +0000 (10:50 +0000)]
creating a neat config file is good. Using it is better ;)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6882 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agomissing file
mquinson [Fri, 11 Dec 2009 10:39:39 +0000 (10:39 +0000)]
missing file

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6881 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoInstall a configure-generated header file containing whether the system have getline...
mquinson [Fri, 11 Dec 2009 10:38:52 +0000 (10:38 +0000)]
Install a configure-generated header file containing whether the system have getline and asprintf

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6880 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoalso activate our asprintf internal implementation if there is one in libc, but a...
mquinson [Fri, 11 Dec 2009 08:57:14 +0000 (08:57 +0000)]
also activate our asprintf internal implementation if there is one in libc, but a broken one. Say hello to ubuntu ;)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6879 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agodocument how to get java bindings compiling
mquinson [Thu, 10 Dec 2009 14:56:15 +0000 (14:56 +0000)]
document how to get java bindings compiling

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6878 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFix default target about dax.dtd for the ones not having flexml
mquinson [Thu, 10 Dec 2009 14:17:23 +0000 (14:17 +0000)]
Fix default target about dax.dtd for the ones not having flexml

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6877 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAutomatically generare html files from our bibtex file.
alegrand [Thu, 3 Dec 2009 12:44:45 +0000 (12:44 +0000)]
Automatically generare html files from our bibtex file.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6867 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoUse external files for the bibliography.
alegrand [Thu, 3 Dec 2009 12:44:20 +0000 (12:44 +0000)]
Use external files for the bibliography.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6866 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFix a bug noted by Martin (weird undefined variable elem_list)
alegrand [Thu, 3 Dec 2009 12:44:16 +0000 (12:44 +0000)]
Fix a bug noted by Martin (weird undefined variable elem_list)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6865 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDocument supernovae
mquinson [Wed, 2 Dec 2009 21:10:51 +0000 (21:10 +0000)]
Document supernovae

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6864 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoStop building a 3.3.3 version...
navarrop [Wed, 2 Dec 2009 16:34:13 +0000 (16:34 +0000)]
Stop building a 3.3.3 version...

3.3.3 has been stable for a while. We're preparing the 3.3.4 here.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6863 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAnother try to get the make dist working with or without supernovae
mquinson [Wed, 2 Dec 2009 15:49:30 +0000 (15:49 +0000)]
Another try to get the make dist working with or without supernovae
This was not a bug of automake, but a feature: it seeks every files
  which may be needed by a if/endif branch and makes sure they are in
  the archive. Adding an extra variable didn't solve the issue since
  automake follows variable definitions.
Declaring supernovae files as BUILT_SOURCE was uneffective (still
  trying to add them to the archive) and counter productive (automake
  tried to build them even in non-supernovae mode)
So the solution is to prevent automake from derivating the DIST files
  from the lib_*_la_SOURCES. For that, I use nodist_lib_*_la_SOURCES
  and take care of the EXTRA_DIST files manually.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6862 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoCircumvent a bug in automake (at least found in v1.11)
mquinson [Wed, 2 Dec 2009 11:01:31 +0000 (11:01 +0000)]
Circumvent a bug in automake (at least found in v1.11)
If lib*_la_SOURCES are defined in a if/endif alternative, it works for
  compilation, but the dist target uses the first variante of the
  variable, regardless of whether this is the used variante or not.
So, use yet another name in the alternative and define lib*_la_SOURCES
  only once, out of the alternatives

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6861 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoinclude all the needed files in the archive so that the tar.gz compiles afterward
mquinson [Wed, 2 Dec 2009 10:34:19 +0000 (10:34 +0000)]
include all the needed files in the archive so that the tar.gz compiles afterward

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6860 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoReplay is not mature enough for distribution, yet
mquinson [Wed, 2 Dec 2009 10:34:17 +0000 (10:34 +0000)]
Replay is not mature enough for distribution, yet

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6859 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoReplay is not mature enough for distribution, yet
mquinson [Wed, 2 Dec 2009 10:20:33 +0000 (10:20 +0000)]
Replay is not mature enough for distribution, yet

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6858 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agocreate the listener thread in joinable mode since we join it at the end
mquinson [Wed, 2 Dec 2009 10:18:30 +0000 (10:18 +0000)]
create the listener thread in joinable mode since we join it at the end

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6857 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoModify the output of the action replay tool.
suter [Mon, 30 Nov 2009 15:39:35 +0000 (15:39 +0000)]
Modify the output of the action replay tool.
Each action now output a message wit the same structure as its input
PLUS an extra field giving the time spent to execute this action

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6856 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agodefault of supernovae should be the opposite of maintainer-mode
mquinson [Tue, 24 Nov 2009 11:36:15 +0000 (11:36 +0000)]
default of supernovae should be the opposite of maintainer-mode

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6855 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoForce initialization of a variable to shut gcc 4.4 up
mquinson [Tue, 24 Nov 2009 11:28:18 +0000 (11:28 +0000)]
Force initialization of a variable to shut gcc 4.4 up

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6854 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agomore inlining
mquinson [Fri, 20 Nov 2009 20:40:46 +0000 (20:40 +0000)]
more inlining

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6853 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoMark two more functions as inline in supernovae, and use selective update by default
mquinson [Fri, 20 Nov 2009 20:40:32 +0000 (20:40 +0000)]
Mark two more functions as inline in supernovae, and use selective update by default

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6852 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoForce memory allocation functions to always inline
mquinson [Fri, 20 Nov 2009 20:40:17 +0000 (20:40 +0000)]
Force memory allocation functions to always inline

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6851 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agokill useless code
mquinson [Fri, 20 Nov 2009 20:40:03 +0000 (20:40 +0000)]
kill useless code

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6850 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoMark a bunch of functions as candidates to inlining. Not quite sure that gcc does...
mquinson [Fri, 20 Nov 2009 11:50:32 +0000 (11:50 +0000)]
Mark a bunch of functions as candidates to inlining. Not quite sure that gcc does it, yet

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6849 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agothese are variables, not functions. Use the right macro
mquinson [Fri, 20 Nov 2009 11:50:08 +0000 (11:50 +0000)]
these are variables, not functions. Use the right macro

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6848 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoIn supernovae mode, declare every public functions as [potentially] inline
mquinson [Fri, 20 Nov 2009 11:50:05 +0000 (11:50 +0000)]
In supernovae mode, declare every public functions as [potentially] inline

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6847 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoTake into account "recent" simix modifications
alegrand [Fri, 20 Nov 2009 09:59:00 +0000 (09:59 +0000)]
Take into account "recent" simix modifications

Namely, the use of semaphores for communications in SIMIX_process

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6846 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoremove wrong comment
alegrand [Fri, 20 Nov 2009 09:55:32 +0000 (09:55 +0000)]
remove wrong comment

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6845 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoChange the code so that it compiles in supernovae mode
mquinson [Fri, 20 Nov 2009 09:47:53 +0000 (09:47 +0000)]
Change the code so that it compiles in supernovae mode
 - _simgrid_log_channel__default is then a macro defined in
   mk_supernovae.sh instead of a global static to the compilation unit
 - lots and lots of static symbol renaming (prefixing) to avoid name
   clashes. I love eclipse refactoring functions

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6844 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoTry to compile in supernovae mode when requested to
mquinson [Fri, 20 Nov 2009 09:47:29 +0000 (09:47 +0000)]
Try to compile in supernovae mode when requested to

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6843 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoA configure option to control the supernovae mode
mquinson [Fri, 20 Nov 2009 09:47:26 +0000 (09:47 +0000)]
A configure option to control the supernovae mode

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6842 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAlso include hostfile into the archive since makecheck needs that
mquinson [Wed, 18 Nov 2009 07:30:16 +0000 (07:30 +0000)]
Also include hostfile into the archive since makecheck needs that

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6841 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoSome files missing from the archive. This prevents makecheck from running well
mquinson [Wed, 18 Nov 2009 07:28:20 +0000 (07:28 +0000)]
Some files missing from the archive. This prevents makecheck from running well

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6840 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoBugfix: Initialize variable and remove from heap when action is suspended.
donassbr [Mon, 16 Nov 2009 15:41:27 +0000 (15:41 +0000)]
Bugfix: Initialize variable and remove from heap when action is suspended.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6839 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agotypo found by Medhi while doing the tutorial
mquinson [Wed, 11 Nov 2009 16:09:33 +0000 (16:09 +0000)]
typo found by Medhi while doing the tutorial

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6838 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agodon't trust gcc for cleaning your code after you. he's too dumb to be trusted
mquinson [Tue, 10 Nov 2009 12:33:10 +0000 (12:33 +0000)]
don't trust gcc for cleaning your code after you. he's too dumb to be trusted

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6837 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoRevert "try to port the gras simulation side to the new smx_network infrastructure...
mquinson [Tue, 10 Nov 2009 12:32:54 +0000 (12:32 +0000)]
Revert "try to port the gras simulation side to the new smx_network infrastructure (not yet working)"
This git branch is not ready for public consumption yet (sorry)

This reverts commit 063c63642a29000a011c0d6176d30eb62a4e0dca.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6836 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agotry to port the gras simulation side to the new smx_network infrastructure (not yet...
mquinson [Tue, 10 Nov 2009 12:28:14 +0000 (12:28 +0000)]
try to port the gras simulation side to the new smx_network infrastructure (not yet working)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6835 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoKill portability to MAC for sake of compiling on linux. See #8852 for a proper soluti...
mquinson [Tue, 10 Nov 2009 11:52:05 +0000 (11:52 +0000)]
Kill portability to MAC for sake of compiling on linux. See #8852 for a proper solution (which will want for the IJD to arrive)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6834 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFirst implementation of allReduce action (Refactoring will be needed
suter [Thu, 5 Nov 2009 22:48:55 +0000 (22:48 +0000)]
First implementation of allReduce action (Refactoring will be needed
at some point)

All involved processes exit at the same time

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6833 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFix test. Remove timestep parameter.
donassbr [Wed, 4 Nov 2009 12:14:20 +0000 (12:14 +0000)]
Fix test. Remove timestep parameter.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6832 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoRemove parameter timestep.
donassbr [Wed, 4 Nov 2009 12:14:17 +0000 (12:14 +0000)]
Remove parameter timestep.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6831 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoChanges implementation of CPU TI. Now, it uses the simple integration of trace and...
donassbr [Wed, 4 Nov 2009 12:13:53 +0000 (12:13 +0000)]
Changes implementation of CPU TI. Now, it uses the simple integration of trace and does a binary search to find the points in the array.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6830 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAdd 2 tests to handle problems when using timesteps too big.
donassbr [Wed, 4 Nov 2009 12:13:50 +0000 (12:13 +0000)]
Add 2 tests to handle problems when using timesteps too big.
This part of code will disappear soon, but this commit can be used to retrieve this implementation of trace integration feature (with multi levels).

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6829 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAdd tests to skip actions that aren't running or have priority = 0.
donassbr [Wed, 4 Nov 2009 12:13:26 +0000 (12:13 +0000)]
Add tests to skip actions that aren't running or have priority = 0.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6828 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoRemove old code and useless code.
donassbr [Wed, 4 Nov 2009 12:13:23 +0000 (12:13 +0000)]
Remove old code and useless code.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6827 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoNot using set/get functions is bad, but raising an errer when a set
suter [Fri, 30 Oct 2009 17:27:34 +0000 (17:27 +0000)]
Not using set/get functions is bad, but raising an errer when a set
modifies an existing data is worse.

Remove the paranoid assert

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6826 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoadd a reduce X bytes Y flops action
suter [Thu, 29 Oct 2009 22:24:49 +0000 (22:24 +0000)]
add a reduce X bytes Y flops action
once the root has received all the contributions of X bytes from the
other processes, it computes Y flops. The other processes exit the
function as soon as they their send is completed.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6825 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoRefactor spawned_send and bcast_spawned_send
suter [Thu, 29 Oct 2009 21:15:57 +0000 (21:15 +0000)]
Refactor spawned_send and bcast_spawned_send

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6824 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoadd a flat broadcast action
suter [Thu, 29 Oct 2009 20:59:50 +0000 (20:59 +0000)]
add a flat broadcast action
requires a comm_size action to set the size of the MPI_COMM_WORLD
update the actions_with_isend.txt to include the Isend action

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6823 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoplug a memleak
mquinson [Thu, 29 Oct 2009 16:10:40 +0000 (16:10 +0000)]
plug a memleak

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6822 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoforgot to remove the cleaning of a remove data
suter [Thu, 29 Oct 2009 10:52:55 +0000 (10:52 +0000)]
forgot to remove the cleaning of a remove data

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6821 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoadd an Isend, just the prototype for the barrier action
suter [Thu, 29 Oct 2009 10:51:46 +0000 (10:51 +0000)]
add an Isend, just the prototype for the barrier action

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6820 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agotry harder not to overflow that buffer
mquinson [Thu, 29 Oct 2009 07:00:59 +0000 (07:00 +0000)]
try harder not to overflow that buffer

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6819 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agotry to ensure that stdio is loaded when str.h is loaded, so that __USE_GNU is defined...
mquinson [Wed, 28 Oct 2009 22:36:02 +0000 (22:36 +0000)]
try to ensure that stdio is loaded when str.h is loaded, so that __USE_GNU is defined on glibc

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6818 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoTry to fix #8852 (SimGrid won't compile on Ubuntu 9.10) by betterly checking my argum...
mquinson [Wed, 28 Oct 2009 22:17:55 +0000 (22:17 +0000)]
Try to fix #8852 (SimGrid won't compile on Ubuntu 9.10) by betterly checking my arguments to standard functions

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6817 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agosmall improvements suggested by Arnaud
suter [Fri, 23 Oct 2009 05:59:09 +0000 (05:59 +0000)]
small improvements suggested by Arnaud

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6813 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAdd Irecv and wait actions and corresponding example
suter [Thu, 22 Oct 2009 18:12:25 +0000 (18:12 +0000)]
Add Irecv and wait actions and corresponding example

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6812 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoChange the waitany functions on semaphore and communications to return the rank of...
mquinson [Tue, 20 Oct 2009 13:10:35 +0000 (13:10 +0000)]
Change the waitany functions on semaphore and communications to return the rank of the object in the dynar instead of the object itself

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6811 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoImplement smx_comm_t SIMIX_network_waitany(xbt_dynar_t comms)
mquinson [Tue, 20 Oct 2009 13:10:31 +0000 (13:10 +0000)]
Implement smx_comm_t SIMIX_network_waitany(xbt_dynar_t comms)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6810 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoImplement smx_sem_t SIMIX_sem_acquire_any(xbt_dynar_t sems)
mquinson [Tue, 20 Oct 2009 13:10:07 +0000 (13:10 +0000)]
Implement smx_sem_t SIMIX_sem_acquire_any(xbt_dynar_t sems)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6809 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agowhen requested to acquire a cond or semaphore with max_duration=0, call the regular...
mquinson [Tue, 20 Oct 2009 13:10:04 +0000 (13:10 +0000)]
when requested to acquire a cond or semaphore with max_duration=0, call the regular blocking function instead of the internal code so that the dummy action in charge of detecting host failures get created

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6808 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoImplement Asynchronous send/recv in SIMIX (you dreamt of it? It's here now)
mquinson [Tue, 20 Oct 2009 13:09:40 +0000 (13:09 +0000)]
Implement Asynchronous send/recv in SIMIX (you dreamt of it? It's here now)
Too bad that nobody cared enough to propagate the change to MSG (yet).

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6807 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoEnough is enough. Add semaphores as SIMIX synchronization mechanism.
mquinson [Tue, 20 Oct 2009 13:09:36 +0000 (13:09 +0000)]
Enough is enough. Add semaphores as SIMIX synchronization mechanism.

Check the SIMIX_sem_release_forever() function, which allows something
between conditions and pure semaphores.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6806 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAdapt tests to the fact that we can now detect that there was a timeout during commun...
mquinson [Tue, 20 Oct 2009 13:09:13 +0000 (13:09 +0000)]
Adapt tests to the fact that we can now detect that there was a timeout during communication

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6805 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agouse a bit more informative actions'names. Helpful while debuging
mquinson [Tue, 20 Oct 2009 13:09:10 +0000 (13:09 +0000)]
use a bit more informative actions'names. Helpful while debuging

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6804 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoAdd SIMIX_rdv_{set,get}_data; tiny fixups
mquinson [Tue, 20 Oct 2009 13:08:47 +0000 (13:08 +0000)]
Add SIMIX_rdv_{set,get}_data; tiny fixups

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6803 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoNew function: SIMIX_action_set_name()
mquinson [Tue, 20 Oct 2009 13:08:44 +0000 (13:08 +0000)]
New function: SIMIX_action_set_name()

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6802 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agouseless cosmetics
mquinson [Tue, 20 Oct 2009 13:08:20 +0000 (13:08 +0000)]
useless cosmetics

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6801 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoa script to generate a strassen workflow (+cosmetics on other script)
mquinson [Tue, 20 Oct 2009 13:08:16 +0000 (13:08 +0000)]
a script to generate a strassen workflow (+cosmetics on other script)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6800 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFix a vicious bug in dictionaries inducing that some elements were not freed on xbt_d...
mquinson [Fri, 16 Oct 2009 09:06:55 +0000 (09:06 +0000)]
Fix a vicious bug in dictionaries inducing that some elements were not freed on xbt_dict_free()

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6799 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoIntegrate patch #8636: Obey DESTDIR when installing documentation (thanks to Robson...
mquinson [Fri, 16 Oct 2009 07:54:18 +0000 (07:54 +0000)]
Integrate patch #8636: Obey DESTDIR when installing documentation (thanks to Robson Peixoto)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6798 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoIntroduce a MSG_TIMEOUT_FAILURE return code and use it for communication timeouts...
mquinson [Fri, 16 Oct 2009 07:37:44 +0000 (07:37 +0000)]
Introduce a MSG_TIMEOUT_FAILURE return code and use it for communication timeouts (closes #8563)

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6797 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoFix #8569: XBT/synchro.h has redundant declarations
mquinson [Fri, 16 Oct 2009 07:37:42 +0000 (07:37 +0000)]
Fix #8569: XBT/synchro.h has redundant declarations

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6796 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoA script to recompile and rerun the whole chain from platfile+daxfile to actual repla...
mquinson [Thu, 15 Oct 2009 16:26:55 +0000 (16:26 +0000)]
A script to recompile and rerun the whole chain from platfile+daxfile to actual replay on simulator

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6795 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoA script to generate neat DAX files of fork/joins
mquinson [Thu, 15 Oct 2009 16:26:32 +0000 (16:26 +0000)]
A script to generate neat DAX files of fork/joins

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6794 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoUse private headers to help debugging
mquinson [Thu, 15 Oct 2009 16:26:30 +0000 (16:26 +0000)]
Use private headers to help debugging

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6793 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoVarious fixes. Working (in SG) for ForkJoins, but not for Montage.
mquinson [Thu, 15 Oct 2009 16:26:07 +0000 (16:26 +0000)]
Various fixes. Working (in SG) for ForkJoins, but not for Montage.
* Change synchronization scheme for ending: workers send go to master
  instead of having the master calling amok_pm_group_end() right after
  the setup. This killed the workers ways too early.
* make sure that workers do create all mandatory sockets to others
  since dopar threads have real difficulties speaking to the listener
  thread to add new sockets
* instead of having a callback to the go message in the worker which
  does all the work, do explicitely wait for that message and move the
  code in worker's main()

Like I said, there is still a deadlock when trying to replay
Montage_25, but this may related to the fact that this workflow seems
somehow broken. the "cimages.tbl" file, generated by root and consumed
by ID00021@mImgTbl is mangled in the dot output, and thus presumably
also in memory representation. More to come tomorrow.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6792 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoconditions are not semaphores. signals can get lost if delivered before you are waiti...
mquinson [Thu, 15 Oct 2009 16:26:05 +0000 (16:26 +0000)]
conditions are not semaphores. signals can get lost if delivered before you are waiting on the cond. So only wait on the condition if the message were not delevered already, and ignore all this cruft in other cases

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6791 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agostart threads only if I have more than 1 element to handle
mquinson [Thu, 15 Oct 2009 16:25:42 +0000 (16:25 +0000)]
start threads only if I have more than 1 element to handle

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6790 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoRevert the change inducing that GRAS processes keep quiet when leaving on simulator...
mquinson [Thu, 15 Oct 2009 16:25:40 +0000 (16:25 +0000)]
Revert the change inducing that GRAS processes keep quiet when leaving on simulator, since it's helpful sometimes, and since it breaks several tesh files

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6789 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoplug various memleaks
mquinson [Thu, 15 Oct 2009 16:25:17 +0000 (16:25 +0000)]
plug various memleaks

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6788 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoMore informative error message
mquinson [Thu, 15 Oct 2009 16:25:15 +0000 (16:25 +0000)]
More informative error message

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6787 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agoDo not call xbt_thread_exit at the end of the dopar worker since this call forcefully...
mquinson [Thu, 15 Oct 2009 16:24:51 +0000 (16:24 +0000)]
Do not call xbt_thread_exit at the end of the dopar worker since this call forcefully kills the process in SG, preventing the wrapper to cleanup around before leaving

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6786 48e7efb5-ca39-0410-a469-dd3cf9ba447f

10 years agounify the log channels for SG and RL implementations of xbt_synchro
mquinson [Thu, 15 Oct 2009 16:24:49 +0000 (16:24 +0000)]
unify the log channels for SG and RL implementations of xbt_synchro

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/simgrid/simgrid/trunk@6785 48e7efb5-ca39-0410-a469-dd3cf9ba447f