Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
9 years agoWe should'nt allow the use of uncommited datatypes in communications.
scastelli [Tue, 10 Jun 2014 22:44:15 +0000 (00:44 +0200)]
We should'nt allow the use of uncommited datatypes in communications.
Small fix to follow more closely the specs in mpi_type_free

9 years agotorus should provide better results if latency is taken into account ..
degomme [Tue, 10 Jun 2014 13:09:35 +0000 (15:09 +0200)]
torus should provide better results if latency is taken into account ..

9 years agoSmall correction in a manpage
scastelli [Fri, 6 Jun 2014 07:42:56 +0000 (09:42 +0200)]
Small correction in a manpage

9 years agoFix memory leaks.
Arnaud Giersch [Thu, 5 Jun 2014 20:43:08 +0000 (22:43 +0200)]
Fix memory leaks.

9 years agoUpdate smpi* manpages.
Arnaud Giersch [Thu, 5 Jun 2014 20:35:42 +0000 (22:35 +0200)]
Update smpi* manpages.

9 years agoInstall additional manpages.
Arnaud Giersch [Thu, 5 Jun 2014 20:35:16 +0000 (22:35 +0200)]
Install additional manpages.

9 years agoFix distcheck.
Arnaud Giersch [Thu, 5 Jun 2014 20:31:45 +0000 (22:31 +0200)]
Fix distcheck.

9 years agoFortran SMPI is not working for now, so deactivate the build in cmake.
degomme [Thu, 5 Jun 2014 18:20:46 +0000 (20:20 +0200)]
Fortran SMPI is not working for now, so deactivate the build in cmake.
It would need a dirty hack as seen in smpi_main.h, but in F77 and F90, to begin with ...

9 years agosome cmake calls were forgotten here
degomme [Thu, 5 Jun 2014 17:57:50 +0000 (19:57 +0200)]
some cmake calls were forgotten here

9 years agoRemove temporary files.
Arnaud Giersch [Thu, 5 Jun 2014 14:41:51 +0000 (16:41 +0200)]
Remove temporary files.

9 years agoChange non-portable echo -e for printf.
Arnaud Giersch [Thu, 5 Jun 2014 14:14:08 +0000 (16:14 +0200)]
Change non-portable echo -e for printf.

9 years agoTypo.
Arnaud Giersch [Thu, 5 Jun 2014 14:04:51 +0000 (16:04 +0200)]
Typo.

9 years agoFix broken tesh file (with the Perl tesh)
Gabriel Corona [Wed, 4 Jun 2014 22:00:53 +0000 (00:00 +0200)]
Fix broken tesh file (with the Perl tesh)

It was working with the C tesh.

9 years agoSome man pages
scastelli [Wed, 4 Jun 2014 21:23:44 +0000 (23:23 +0200)]
Some man pages

9 years agoWell, that happens sometime (bad merge)
scastelli [Wed, 4 Jun 2014 18:32:59 +0000 (20:32 +0200)]
Well, that happens sometime (bad merge)

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
scastelli [Wed, 4 Jun 2014 18:27:06 +0000 (20:27 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

Conflicts:
src/smpi/smpiff.in

9 years agoFix tesh files
degomme [Wed, 4 Jun 2014 18:20:45 +0000 (20:20 +0200)]
Fix tesh files

9 years agoSome minor documentation fixes
scastelli [Wed, 4 Jun 2014 18:17:18 +0000 (20:17 +0200)]
Some minor documentation fixes

9 years agoUpdate of the smpicc man page
scastelli [Wed, 4 Jun 2014 18:16:19 +0000 (20:16 +0200)]
Update of the smpicc man page

9 years agoAdd a smpicxx man page
scastelli [Wed, 4 Jun 2014 18:15:46 +0000 (20:15 +0200)]
Add a smpicxx man page

9 years agoAdd version notes to smpiXXX scripts
scastelli [Wed, 4 Jun 2014 18:14:44 +0000 (20:14 +0200)]
Add version notes to smpiXXX scripts

9 years agoDeactivate temporarily one test.
degomme [Wed, 4 Jun 2014 18:02:34 +0000 (20:02 +0200)]
Deactivate temporarily one test.
It works with automatic privatization on, but would fail on Windows as we no longer provide a way to privatize global variables.
We can't either just use dynamic memory as in its F90 counterpart ...

9 years agoKill f2c. Finally. I hope.
degomme [Wed, 4 Jun 2014 17:51:58 +0000 (19:51 +0200)]
Kill f2c. Finally.        I hope.

9 years agomake smpiff behave like smpif90, so we don't use f2c anymore
degomme [Wed, 4 Jun 2014 16:19:37 +0000 (18:19 +0200)]
make smpiff behave like smpif90, so we don't use f2c anymore

9 years agoPrivatization : switch data segments when copying inside a single node
degomme [Wed, 4 Jun 2014 16:18:55 +0000 (18:18 +0200)]
Privatization : switch data segments when copying inside a single node

9 years agofix spell and remove trailing space
Takahiro Hirofuchi [Wed, 4 Jun 2014 17:23:42 +0000 (19:23 +0200)]
fix spell and remove trailing space

9 years agoIndentation
scastelli [Wed, 4 Jun 2014 16:54:56 +0000 (18:54 +0200)]
Indentation

9 years agoAdd enable_documentation option
Paul Bédaride [Wed, 4 Jun 2014 15:40:08 +0000 (17:40 +0200)]
Add enable_documentation option

9 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Takahiro Hirofuchi [Wed, 4 Jun 2014 14:22:52 +0000 (16:22 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

9 years agoadd a hopefully simple and clear example of MSG_vm
Takahiro Hirofuchi [Wed, 4 Jun 2014 14:13:50 +0000 (16:13 +0200)]
add a hopefully simple and clear example of MSG_vm

This is revival of masterslave_virtual_machines. It should be simpler
and clearer than the old one. Because the other examples of MSG_vm are
rather oriented to regression test, it would be nice that we have a
tutorial-oriented example here.

9 years agoIs seems as right as before, only shorter
scastelli [Wed, 4 Jun 2014 13:28:54 +0000 (15:28 +0200)]
Is seems as right as before, only shorter

9 years agoUse tesh perl for all platforms
Paul Bédaride [Wed, 4 Jun 2014 13:12:40 +0000 (15:12 +0200)]
Use tesh perl for all platforms

9 years agoSome documentation to NetworkModel.
scastelli [Wed, 4 Jun 2014 10:48:43 +0000 (12:48 +0200)]
Some documentation to NetworkModel.

9 years agoMinor corrections in doc
scastelli [Tue, 3 Jun 2014 18:03:46 +0000 (20:03 +0200)]
Minor corrections in doc

9 years agolet's build the doc when 'make doc' is called, just in case someone would plan to it
Martin Quinson [Wed, 4 Jun 2014 08:37:42 +0000 (10:37 +0200)]
let's build the doc when 'make doc' is called, just in case someone would plan to it

9 years agoAs this is done only with java compilation, use the right variable (find_path misses...
degomme [Wed, 4 Jun 2014 08:33:49 +0000 (10:33 +0200)]
As this is done only with java compilation, use the right variable (find_path misses javadoc.exe on win)

9 years agomore informative error message
Martin Quinson [Tue, 3 Jun 2014 17:33:28 +0000 (19:33 +0200)]
more informative error message

9 years agoRequalify teshes, as we really wanted to send 1 byte for this one.
degomme [Tue, 3 Jun 2014 15:34:51 +0000 (17:34 +0200)]
Requalify teshes, as we really wanted to send 1 byte for this one.

9 years agoRevert "the users are not the only ones lost with 10e0 :)"
degomme [Tue, 3 Jun 2014 15:24:13 +0000 (17:24 +0200)]
Revert "the users are not the only ones lost with 10e0 :)"
Indeed :p

This reverts commit cec110d828d0c4d14c6264e79e520a30653c2a4a.

9 years agothe users are not the only ones lost with 10e0 :)
Martin Quinson [Tue, 3 Jun 2014 15:12:36 +0000 (17:12 +0200)]
the users are not the only ones lost with 10e0 :)

9 years agodon't fool the users. Don't write 1 as 10e0
Martin Quinson [Tue, 3 Jun 2014 14:46:44 +0000 (16:46 +0200)]
don't fool the users. Don't write 1 as 10e0

9 years agoFix javadoc into simgrid_full.jar
Paul Bédaride [Tue, 3 Jun 2014 14:30:36 +0000 (16:30 +0200)]
Fix javadoc into simgrid_full.jar

9 years agoAdd javadoc into simgrid_full.jar
Paul Bédaride [Tue, 3 Jun 2014 10:53:28 +0000 (12:53 +0200)]
Add javadoc into simgrid_full.jar

9 years agoFix boost version
Paul Bédaride [Tue, 3 Jun 2014 10:17:36 +0000 (12:17 +0200)]
Fix boost version

9 years agoCheck boost version
Paul Bédaride [Tue, 3 Jun 2014 10:00:01 +0000 (12:00 +0200)]
Check boost version

9 years agoadd java doc link to simgrid's main doc
Augustin Degomme [Mon, 2 Jun 2014 21:51:16 +0000 (23:51 +0200)]
add java doc link to simgrid's main doc

9 years agoMake xbt_free a function-like macro.
Arnaud Giersch [Sat, 31 May 2014 21:08:11 +0000 (23:08 +0200)]
Make xbt_free a function-like macro.

Use xbt_free_f everywhere a pointer to function is needed.

9 years agoCosmetics.
Arnaud Giersch [Sat, 31 May 2014 20:40:12 +0000 (22:40 +0200)]
Cosmetics.

9 years agoInit version 3.12
Paul Bédaride [Mon, 2 Jun 2014 08:48:49 +0000 (10:48 +0200)]
Init version 3.12

9 years agoAdd link to documentation in Changelog
lysbleu [Mon, 2 Jun 2014 08:08:28 +0000 (10:08 +0200)]
Add link to documentation in Changelog

9 years agoAdd missing date to ChangeLog.
Arnaud Giersch [Sat, 31 May 2014 20:40:02 +0000 (22:40 +0200)]
Add missing date to ChangeLog.

9 years agoBe consistent wrt the number of empty lines between releases.
Arnaud Giersch [Sat, 31 May 2014 20:38:40 +0000 (22:38 +0200)]
Be consistent wrt the number of empty lines between releases.

9 years agoTypo in variable name (EXEEXT).
Arnaud Giersch [Fri, 30 May 2014 20:35:20 +0000 (22:35 +0200)]
Typo in variable name (EXEEXT).

9 years agoAdd FIXME.
Arnaud Giersch [Fri, 30 May 2014 14:16:21 +0000 (16:16 +0200)]
Add FIXME.

9 years agoremove leaks introduced by previous commit. Ressource::getProperty
suter [Sat, 31 May 2014 17:47:06 +0000 (19:47 +0200)]
remove leaks introduced by previous commit. Ressource::getProperty
creates a heterogeneous dict if set_property_value is called on a non
existing dict of properties. Sounds more logical to create a
heterogeneous dict during parsing too. BTW using homogeneous dict
everywhere makes chord example fails ...

9 years agoRelease 3 11 v3_11
Paul Bédaride [Sat, 31 May 2014 15:14:02 +0000 (17:14 +0200)]
Release 3 11

9 years agochange the dict in which parsed properties are stored from homogeneous
suter [Fri, 30 May 2014 21:56:02 +0000 (23:56 +0200)]
change the dict in which parsed properties are stored from homogeneous
to heterogeneous. A leak occured in
teshsuite/msg/storage/storage_basic.c after the addition of a call
MSG_storage_set_property_value that adds a new property to the dict. The
new element doesn't appear to be freed when freeing the resources. After
several tries, the proposed modification solves the issue without
breaking something else.

9 years agoremove duplicated line
suter [Fri, 30 May 2014 21:48:29 +0000 (23:48 +0200)]
remove duplicated line

9 years agochased tabs while looking for a leak
suter [Fri, 30 May 2014 21:48:08 +0000 (23:48 +0200)]
chased tabs while looking for a leak

9 years agochange key name to prevent reuse + indent (this example raised an issue
suter [Fri, 30 May 2014 21:44:53 +0000 (23:44 +0200)]
change key name to prevent reuse + indent (this example raised an issue
with the parsing of <prop>)

9 years agoremove cruft
suter [Fri, 30 May 2014 18:57:40 +0000 (20:57 +0200)]
remove cruft

9 years agoleak--
suter [Fri, 30 May 2014 18:56:47 +0000 (20:56 +0200)]
leak--

9 years agoleak--
suter [Fri, 30 May 2014 18:54:29 +0000 (20:54 +0200)]
leak--

9 years agoreplace sprintf by bprintf
suter [Fri, 30 May 2014 18:40:35 +0000 (20:40 +0200)]
replace sprintf by bprintf

9 years agoMakes file identifier unique in MSG file lib
Pierre Veyre [Fri, 30 May 2014 13:34:06 +0000 (15:34 +0200)]
Makes file identifier unique in MSG file lib

9 years agoReintroduce message erroneously removed by commit 7bee0ca.
Arnaud Giersch [Fri, 30 May 2014 13:06:26 +0000 (15:06 +0200)]
Reintroduce message erroneously removed by commit 7bee0ca.

9 years agoFix check for doxygen version.
Arnaud Giersch [Fri, 30 May 2014 12:45:03 +0000 (14:45 +0200)]
Fix check for doxygen version.

9 years agorename tesh entry to explicitly mention it is a bogus test
suter [Fri, 30 May 2014 12:10:37 +0000 (14:10 +0200)]
rename tesh entry to explicitly mention it is a bogus test
indent the XML file without tabs too

9 years agoCosemtics: break long lines, whitespace cleanup.
Arnaud Giersch [Fri, 30 May 2014 08:57:26 +0000 (10:57 +0200)]
Cosemtics: break long lines, whitespace cleanup.

9 years agotypos
suter [Fri, 30 May 2014 09:03:27 +0000 (11:03 +0200)]
typos

9 years agoremove useless function. private info is already freed by the
suter [Fri, 30 May 2014 09:01:42 +0000 (11:01 +0200)]
remove useless function. private info is already freed by the
__MSG_file_destroy function

9 years agoUpdate changelog to account for fat trees
Stéphane Castelli [Fri, 30 May 2014 08:43:59 +0000 (10:43 +0200)]
Update changelog to account for fat trees

9 years agoVery minor removal of unnecessary comments
Stéphane Castelli [Fri, 30 May 2014 07:26:14 +0000 (09:26 +0200)]
Very minor removal of unnecessary comments

9 years agoFix bug windows msg-file
Paul Bédaride [Wed, 28 May 2014 15:37:39 +0000 (17:37 +0200)]
Fix bug windows msg-file

9 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Augustin Degomme [Wed, 28 May 2014 14:54:23 +0000 (16:54 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

9 years agoslightly update compilation doc for Windows
Augustin Degomme [Wed, 28 May 2014 14:54:11 +0000 (16:54 +0200)]
slightly update compilation doc for Windows

9 years agoUpdate ChangeLog
Pierre Veyre [Wed, 28 May 2014 14:36:33 +0000 (16:36 +0200)]
Update ChangeLog

9 years agoRefer to fat trees in the platform doc
Stéphane Castelli [Wed, 28 May 2014 14:18:15 +0000 (16:18 +0200)]
Refer to fat trees in the platform doc

9 years agogenerate_memcheck_tests.pl does not support continued lines.
Arnaud Giersch [Wed, 28 May 2014 13:53:19 +0000 (15:53 +0200)]
generate_memcheck_tests.pl does not support continued lines.

9 years agodoc++
Stéphane Castelli [Wed, 28 May 2014 13:40:07 +0000 (15:40 +0200)]
doc++

9 years agoleak--
Stéphane Castelli [Wed, 28 May 2014 08:28:38 +0000 (10:28 +0200)]
leak--

9 years agoUse printf format %f instead of %e for this example.
Arnaud Giersch [Wed, 28 May 2014 12:48:04 +0000 (14:48 +0200)]
Use printf format %f instead of %e for this example.

Workaround for bug on Windows where exponents are printed with 3 digits
instead of 2.

9 years agoUse C++ style comments to fix doxygen output.
Arnaud Giersch [Wed, 28 May 2014 11:56:09 +0000 (13:56 +0200)]
Use C++ style comments to fix doxygen output.

9 years agoGory hack (try #2).
Arnaud Giersch [Wed, 28 May 2014 11:27:51 +0000 (13:27 +0200)]
Gory hack (try #2).

Semicolons are used both as list separator for cmake, and as path separator for
classpath on Windows. Since the cmake language doesn't permit to escape them
properly, try to use substitutions to make the java tests work on Windows.

9 years agoDoc surf++
Paul Bédaride [Wed, 28 May 2014 08:22:38 +0000 (10:22 +0200)]
Doc surf++

9 years agoone more line of doc
Martin Quinson [Tue, 27 May 2014 22:10:26 +0000 (00:10 +0200)]
one more line of doc

9 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Tue, 27 May 2014 22:09:33 +0000 (00:09 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

9 years agoRevert "Gory hack to correclty set classpath for tests on Windows."
Arnaud Giersch [Tue, 27 May 2014 22:03:40 +0000 (00:03 +0200)]
Revert "Gory hack to correclty set classpath for tests on Windows."

This reverts commit f741dad0926a35b69c285129f86e6b8200b3ef73.

It doesn't work as expected.

9 years agoimprove example, should be enough for this release
suter [Tue, 27 May 2014 20:33:54 +0000 (22:33 +0200)]
improve example, should be enough for this release

9 years agomissing file for distcheck
suter [Tue, 27 May 2014 19:29:17 +0000 (21:29 +0200)]
missing file for distcheck

9 years agouse the right executable
suter [Tue, 27 May 2014 19:23:06 +0000 (21:23 +0200)]
use the right executable

9 years agoadd msg-remote-io test to the list
suter [Tue, 27 May 2014 19:17:57 +0000 (21:17 +0200)]
add msg-remote-io test to the list

9 years agofill tesh file (still uncomplete)
suter [Tue, 27 May 2014 19:14:58 +0000 (21:14 +0200)]
fill tesh file (still uncomplete)

9 years agorevalidate tesh files
suter [Tue, 27 May 2014 15:04:27 +0000 (17:04 +0200)]
revalidate tesh files

9 years agowhen doing two consecutive write, each one should have the full
suter [Tue, 27 May 2014 14:47:16 +0000 (16:47 +0200)]
when doing two consecutive write, each one should have the full
bandwidth. It wasn't the case with the lines that were commented in
storage_n11.cpp

9 years agocomment a part that leads to suspect behaviors. write actions remain in
suter [Tue, 27 May 2014 14:45:34 +0000 (16:45 +0200)]
comment a part that leads to suspect behaviors. write actions remain in
the LMM even though the operation is over. It impacts the resource
sharing of all subsequent actions (as if the flows were still active)

9 years agounlink can be a remote operation too.
suter [Tue, 27 May 2014 14:43:41 +0000 (16:43 +0200)]
unlink can be a remote operation too.

9 years agoprinting path and not fullpath
suter [Tue, 27 May 2014 14:42:55 +0000 (16:42 +0200)]
printing path and not fullpath

9 years agogetting further in this example unveiled weird behaviors. Still
suter [Tue, 27 May 2014 14:41:49 +0000 (16:41 +0200)]
getting further in this example unveiled weird behaviors. Still
uncomplete

9 years agobummer, no file descriptor yest in open function
suter [Tue, 27 May 2014 12:47:10 +0000 (14:47 +0200)]
bummer, no file descriptor yest in open function