Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
11 years agoUpdate next version to 3.7.1.
Arnaud Giersch [Wed, 23 May 2012 09:00:38 +0000 (11:00 +0200)]
Update next version to 3.7.1.

11 years agoCosmetics: correctly align Cmake messages, and replace tabs with spaces.
Arnaud Giersch [Tue, 22 May 2012 13:04:52 +0000 (15:04 +0200)]
Cosmetics: correctly align Cmake messages, and replace tabs with spaces.

11 years agoMerge of cpu_update_actions_state_full and net_update_actions_state_full
navarro [Tue, 22 May 2012 15:24:32 +0000 (17:24 +0200)]
Merge ... cpu_update_actions_state_full and net_update_actions_state_full

11 years agoMerge cpu_update_actions_state_lazy and net_update_actions_state_lazy
navarro [Tue, 22 May 2012 14:29:24 +0000 (16:29 +0200)]
Merge cpu_update_actions_state_lazy and net_update_actions_state_lazy

11 years agoForget to remove this line from previous commit
navarro [Tue, 22 May 2012 13:42:31 +0000 (15:42 +0200)]
Forget to remove this line from previous commit

11 years agoMerge cpu and network
navarro [Tue, 22 May 2012 13:28:25 +0000 (15:28 +0200)]
Merge cpu and network
Remove *_update_action_remaining_lazy and *_share_resources_lazy from cpu.c and network.c
Add functions generic_share_resources_lazy and generic_update_action_remaining_lazy

11 years agoFix compilation with MSG_DEPRECATED
navarro [Tue, 22 May 2012 13:17:01 +0000 (15:17 +0200)]
Fix compilation with MSG_DEPRECATED

11 years agoEnsure that lfields[] is fully initialized.
Arnaud Giersch [Tue, 22 May 2012 11:58:37 +0000 (13:58 +0200)]
Ensure that lfields[] is fully initialized.

Fixes compilation error:

In file included from .../src/xbt/mmalloc/mm.c:24:0:
.../src/xbt/mmalloc/mm_diff.c: In function ‘get_addr_memory_map’:
.../src/xbt/mmalloc/mm_diff.c:373:9: error: ‘lfields[5]’ may be used uninitialized in this function [-Werror=uninitialized]
cc1: all warnings being treated as errors

In fact, once strtok returns NULL, subsequent searches with the same parameters
return NULL too.

11 years agoThe mutex is useless when mallocators are disabled.
Arnaud Giersch [Tue, 22 May 2012 10:01:33 +0000 (12:01 +0200)]
The mutex is useless when mallocators are disabled.

11 years agoFix compilation when using MSG_USE_DEPRECATED
navarro [Tue, 22 May 2012 09:35:29 +0000 (11:35 +0200)]
Fix compilation when using MSG_USE_DEPRECATED

11 years agoadd an example of usage of SD_TASK_COMP_PAR_AMDHAL typed tasks. No
Frederic Suter [Tue, 22 May 2012 08:50:21 +0000 (10:50 +0200)]
add an example of usage of SD_TASK_COMP_PAR_AMDHAL typed tasks. No
tesh file yet.

11 years agoAdd a new type of typed task that we may be able to autoschedule.
Frederic Suter [Tue, 22 May 2012 08:42:28 +0000 (10:42 +0200)]
Add a new type of typed task that we may be able to autoschedule.

SD_TASK_COMP_PAR_AMDAHL represents a parallel tasks whose initial work
(amount parameter upon creation) is distributed among host according
to the Amdahl's law. Such tasks are created with a parameter alpha
that corresponds to the non-parallelizable part of the computation.

Before calling SD_task_schedulel or SD_task_schedulev, the
SD_task_distribute_comp_amdahl function has to be called with the
desired number of workstations. The filling of computation_amount and
communication_amount (actually empty) structures is then done seamlessly.

Not sure whether SD_task_distribute_comp_amdahl should be
automatically called within SD_task_schedulev or not. Easy to modify
if we want to hide everything. An option could to call it if the user
didn't do it.

move all the creation functions at the same place in the process.

11 years agorevalidate the tesh file for sd_test. BTW the timings were strange
Frederic Suter [Tue, 22 May 2012 08:40:44 +0000 (10:40 +0200)]
revalidate the tesh file for sd_test. BTW the timings were strange
when looking at the work to do and the hosts' processing power

11 years agothe "amount" field leads to weird behaviors when dealing with parallel
Frederic Suter [Tue, 22 May 2012 08:38:08 +0000 (10:38 +0200)]
the "amount" field leads to weird behaviors when dealing with parallel
tasks. At SURF level, only computation_amount and communication_amount
should be used. Get rid off amount in *execute_parallel_task functions.
Use 1 when creating the surf action.

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid
Marion Guthmuller [Mon, 21 May 2012 13:59:30 +0000 (15:59 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid

11 years agomodel-checker : get location of pointed address in comparison of process memory area
Marion Guthmuller [Mon, 21 May 2012 13:59:24 +0000 (15:59 +0200)]
model-checker : get location of pointed address in comparison of process memory area

11 years agoA few more details in some functions descriptions
Duco van Amstel [Sun, 20 May 2012 11:23:23 +0000 (13:23 +0200)]
A few more details in some functions descriptions

11 years agomy two cents on this release :)
Arnaud Legrand [Tue, 15 May 2012 16:18:10 +0000 (12:18 -0400)]
my two cents on this release :)

11 years agoSet up documentation for simix
Arnaud Legrand [Mon, 14 May 2012 18:45:37 +0000 (14:45 -0400)]
Set up documentation for simix

11 years agotiny post-release adjustment
Martin Quinson [Tue, 15 May 2012 13:43:28 +0000 (15:43 +0200)]
tiny post-release adjustment

11 years agoAhem. Typo in release nick name. Retagging and everything v3_7
Martin Quinson [Tue, 15 May 2012 11:39:52 +0000 (13:39 +0200)]
Ahem. Typo in release nick name. Retagging and everything

11 years agoRELEAAAAAAAASE
Martin Quinson [Tue, 15 May 2012 11:31:14 +0000 (13:31 +0200)]
RELEAAAAAAAASE

11 years agoMissing include (?).
Arnaud Giersch [Mon, 14 May 2012 15:22:45 +0000 (17:22 +0200)]
Missing include (?).

11 years agoSpell check in NEWS and ChangeLog.
Arnaud Giersch [Mon, 14 May 2012 14:27:54 +0000 (16:27 +0200)]
Spell check in NEWS and ChangeLog.

11 years agoSD_simulate doesn't return a NULL-terminated array since a long time now
Frederic Suter [Mon, 14 May 2012 14:49:18 +0000 (16:49 +0200)]
SD_simulate doesn't return a NULL-terminated array since a long time now

11 years agoadd a short proof of corectness. should work too
Martin Quinson [Mon, 14 May 2012 13:46:53 +0000 (15:46 +0200)]
add a short proof of corectness. should work too

11 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Mon, 14 May 2012 12:59:22 +0000 (14:59 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

11 years agoargument why parallel execution don't jeopardize reproducibility even if we never...
Martin Quinson [Mon, 14 May 2012 12:59:07 +0000 (14:59 +0200)]
argument why parallel execution don't jeopardize reproducibility even if we never sort process_to_run explicitely (and cite XKCD appropriatly)

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid
Christophe Thiéry [Mon, 14 May 2012 12:55:55 +0000 (14:55 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid

11 years agoRemove old cruft.
Arnaud Giersch [Mon, 14 May 2012 12:47:43 +0000 (14:47 +0200)]
Remove old cruft.

11 years agoAdd comments to this script
Christophe Thiéry [Mon, 14 May 2012 12:39:58 +0000 (14:39 +0200)]
Add comments to this script

11 years agoTypo.
Arnaud Giersch [Mon, 14 May 2012 08:45:56 +0000 (10:45 +0200)]
Typo.

11 years agomissing file in .tgz causing errors in ctest
Martin Quinson [Sun, 13 May 2012 21:59:13 +0000 (23:59 +0200)]
missing file in .tgz causing errors in ctest

11 years agoprepare the NEWS file for next release
Martin Quinson [Sun, 13 May 2012 21:49:53 +0000 (23:49 +0200)]
prepare the NEWS file for next release

11 years agoupdate the ChangeLog
Martin Quinson [Sun, 13 May 2012 21:40:26 +0000 (23:40 +0200)]
update the ChangeLog

11 years agoMerge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid
Martin Quinson [Sun, 13 May 2012 21:22:15 +0000 (23:22 +0200)]
Merge branch 'master' of scm.gforge.inria.fr:/gitroot/simgrid/simgrid

11 years agomake xbt_os_thread module public (Java needs it, at least)
Martin Quinson [Sun, 13 May 2012 21:20:51 +0000 (23:20 +0200)]
make xbt_os_thread module public (Java needs it, at least)

11 years agoensure that this header can be made public by relying on public simgrid_config.h...
Martin Quinson [Sun, 13 May 2012 21:17:24 +0000 (23:17 +0200)]
ensure that this header can be made public by relying on public simgrid_config.h, not private gras_config.h

11 years agomodel-checker : parser for dwarf file (to complete ...)
Marion Guthmuller [Fri, 11 May 2012 17:07:06 +0000 (19:07 +0200)]
model-checker : parser for dwarf file (to complete ...)

11 years ago[trace] update ChangeLog to report relevant changes in the tracing system
schnorr [Fri, 11 May 2012 14:09:30 +0000 (16:09 +0200)]
[trace] update ChangeLog to report relevant changes in the tracing system

11 years agoUpdate tesh for 32 bit
navarro [Thu, 10 May 2012 15:36:15 +0000 (17:36 +0200)]
Update tesh for 32 bit

11 years agoJust hack the Bconnection to be sure test succed on 32 and 64 bit platform
navarro [Thu, 10 May 2012 15:24:55 +0000 (17:24 +0200)]
Just hack the Bconnection to be sure test succed on 32 and 64 bit platform
HAVE TO BE FIX AFTER SIMGRID v3.7

11 years agoUpdate tesh file
navarro [Thu, 10 May 2012 15:18:45 +0000 (17:18 +0200)]
Update tesh file

11 years agoimprove a comment on my way
Martin Quinson [Thu, 10 May 2012 14:41:18 +0000 (16:41 +0200)]
improve a comment on my way

11 years agoMore debugs around process suspension
Martin Quinson [Thu, 10 May 2012 12:49:15 +0000 (14:49 +0200)]
More debugs around process suspension

11 years agoallow a process blocked on a communication that didn't start yet to get suspended
Martin Quinson [Thu, 10 May 2012 12:48:50 +0000 (14:48 +0200)]
allow a process blocked on a communication that didn't start yet to get suspended

11 years agotypo
Martin Quinson [Thu, 10 May 2012 12:47:07 +0000 (14:47 +0200)]
typo

11 years agonew function xbt_dynar_search_or_negative()
Martin Quinson [Thu, 10 May 2012 08:40:10 +0000 (10:40 +0200)]
new function xbt_dynar_search_or_negative()

It is useful when you have less than 2 million elements in your dynar
and don't want of the extra complexity of catching exceptions when the
element is not found.

11 years agodoc : misc : documented that the numeric sep in trace file depends on system locale.
Laurent Bobelin [Thu, 10 May 2012 12:43:54 +0000 (14:43 +0200)]
doc : misc : documented that the numeric sep in trace file depends on system locale.

11 years agoMake simgrid doc with new logo name
navarro [Thu, 10 May 2012 12:36:58 +0000 (14:36 +0200)]
Make simgrid doc with new logo name

11 years agoAdd explanation in MSG_task_irecv documentation
Samuel Lepetit [Thu, 10 May 2012 11:41:57 +0000 (13:41 +0200)]
Add explanation in MSG_task_irecv documentation

11 years agoMerge cpu and network for action functions.
navarro [Thu, 10 May 2012 10:29:31 +0000 (12:29 +0200)]
Merge cpu and network for action functions.

11 years agoPut those variables private
navarro [Wed, 9 May 2012 14:59:10 +0000 (16:59 +0200)]
Put those variables private

11 years agoTODO for cache friendly
navarro [Wed, 9 May 2012 14:18:41 +0000 (16:18 +0200)]
TODO for cache friendly

11 years agoPrepare network.c and cpu_cas01.c for net and cpu merge.
navarro [Wed, 9 May 2012 12:51:07 +0000 (14:51 +0200)]
Prepare network.c and cpu_cas01.c for net and cpu merge.

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Samuel Lepetit [Wed, 9 May 2012 15:30:29 +0000 (17:30 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoLittle mistake in MSG_task_set_name javadoc
Samuel Lepetit [Wed, 9 May 2012 15:30:23 +0000 (17:30 +0200)]
Little mistake in MSG_task_set_name javadoc

11 years agoUse -DBL_MAX for MIN_KEY_VALUE.
Arnaud Giersch [Fri, 27 Apr 2012 13:31:55 +0000 (15:31 +0200)]
Use -DBL_MAX for MIN_KEY_VALUE.

11 years agoTypo.
Arnaud Giersch [Fri, 27 Apr 2012 13:13:12 +0000 (15:13 +0200)]
Typo.

11 years agoAdd a real new ico ;)
unknown [Fri, 4 May 2012 15:32:36 +0000 (17:32 +0200)]
Add a real new ico ;)

11 years agoAdded an ico as Pierre also wants this format.
Laurent Bobelin [Fri, 4 May 2012 14:22:26 +0000 (16:22 +0200)]
Added an ico as Pierre also wants this format.

11 years agoAdd new icon for doc
navarro [Fri, 4 May 2012 14:00:27 +0000 (16:00 +0200)]
Add new icon for doc

11 years agoUpdate list of headers to install for nsis
unknown [Fri, 4 May 2012 14:55:19 +0000 (16:55 +0200)]
Update list of headers to install for nsis

11 years agoFix compilation error if don't have MMAP like win32
unknown [Fri, 4 May 2012 14:32:31 +0000 (16:32 +0200)]
Fix compilation error if don't have MMAP like win32

11 years agoRewrite function net_update_action_remaining_lazy like in cpu.
navarro [Fri, 4 May 2012 11:22:24 +0000 (13:22 +0200)]
Rewrite function net_update_action_remaining_lazy like in cpu.

11 years agoGet rid of intrusive check now that suspend, resume and kill have been cleaned up.
Arnaud Legrand [Fri, 4 May 2012 11:05:44 +0000 (13:05 +0200)]
Get rid of intrusive check now that suspend, resume and kill have been cleaned up.

11 years agoBetter coverage of SIMIX_process_suspend and resume.
Arnaud Legrand [Fri, 4 May 2012 11:00:50 +0000 (13:00 +0200)]
Better coverage of SIMIX_process_suspend and resume.

11 years agoA priori, no need to propagate modifications when the variable has no impact on the...
navarro [Thu, 3 May 2012 17:15:46 +0000 (19:15 +0200)]
A priori, no need to propagate modifications when the variable has no impact on the constraint.

11 years agoRevisit lazy_remaining_update that was completely broken.
navarro [Thu, 3 May 2012 17:14:53 +0000 (19:14 +0200)]
Revisit lazy_remaining_update that was completely broken.
Unfortunately, this requires to save the previous variable value
since we know when an action requires a remaining_update only
after having thrashed the variable value with lmm_solve. Hence,
function call order is completely changed but now, we only
update needed variables whereas before almost all variables got
updated everytime.

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Samuel Lepetit [Thu, 3 May 2012 12:18:57 +0000 (14:18 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

11 years agoBugfix in masterslave_arg
Samuel Lepetit [Thu, 3 May 2012 12:18:51 +0000 (14:18 +0200)]
Bugfix in masterslave_arg

11 years agoRevalidate output after my recent modifications in simix
Arnaud Legrand [Thu, 3 May 2012 10:55:40 +0000 (12:55 +0200)]
Revalidate output after my recent modifications in simix

The execution order of process at a given timestep may have changed but
if your code really depends on this, this means it was already producing
bogus results.

11 years agoMake the suspend/resume work while a process is in a syscall.
Arnaud Legrand [Thu, 3 May 2012 10:47:04 +0000 (12:47 +0200)]
Make the suspend/resume work while a process is in a syscall.

11 years agoUse this variable so that gcc does not warn anymore.
Arnaud Legrand [Thu, 3 May 2012 10:45:34 +0000 (12:45 +0200)]
Use this variable so that gcc does not warn anymore.

11 years agoadd SIMIX_host_get/set_data declaration in simix.h and include simix.h in msg_host...
Marion Guthmuller [Thu, 3 May 2012 10:23:33 +0000 (12:23 +0200)]
add SIMIX_host_get/set_data declaration in simix.h and include simix.h in msg_host.c (compilation warnings)

11 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid
Marion Guthmuller [Thu, 3 May 2012 08:54:19 +0000 (10:54 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot//simgrid/simgrid

11 years agomodel-checker : new comparison of region (program data and libsimgrid data)
Marion Guthmuller [Thu, 3 May 2012 08:54:14 +0000 (10:54 +0200)]
model-checker : new comparison of region (program data and libsimgrid data)

11 years ago[trace] always set initial value for variables, if not, we get an invalid trace file
schnorr [Wed, 2 May 2012 15:46:41 +0000 (17:46 +0200)]
[trace] always set initial value for variables, if not, we get an invalid trace file

11 years agoThis file does not exist.
navarro [Wed, 2 May 2012 11:04:01 +0000 (13:04 +0200)]
This file does not exist.

11 years agoStop using SMX host->data to store MSG host
Martin Quinson [Mon, 30 Apr 2012 23:29:48 +0000 (01:29 +0200)]
Stop using SMX host->data to store MSG host

- that's useless since we have the lib to retrieve the MSG_host data
  directly
- it would break java bindings since it stores java object in there

Pretty fucking bug, I've lost my day on this one.

11 years agoI forgot to update my tree before commiting (once again), and got conflicts as punishment
Martin Quinson [Sat, 28 Apr 2012 07:48:39 +0000 (09:48 +0200)]
I forgot to update my tree before commiting (once again), and got conflicts as punishment

11 years agoremoving the channels would really make the structures simpler
Martin Quinson [Fri, 27 Apr 2012 21:03:00 +0000 (23:03 +0200)]
removing the channels would really make the structures simpler

11 years agoRemove the public field msg_host_t->name. Use MSG_host_get_name()
Martin Quinson [Fri, 27 Apr 2012 20:47:02 +0000 (22:47 +0200)]
Remove the public field msg_host_t->name. Use MSG_host_get_name()

11 years agosimplify msg_host_t by inlining the simdata field
Martin Quinson [Fri, 27 Apr 2012 20:35:49 +0000 (22:35 +0200)]
simplify msg_host_t by inlining the simdata field

11 years agosave one pointer per MSG host
Martin Quinson [Fri, 27 Apr 2012 20:25:31 +0000 (22:25 +0200)]
save one pointer per MSG host

11 years agoMerge all public simix headers, and distribute them in simgrid directory
Martin Quinson [Fri, 27 Apr 2012 20:09:38 +0000 (22:09 +0200)]
Merge all public simix headers, and distribute them in simgrid directory

Actually, I think I never understood why we have a separate
datatypes.h header: what's the harm of declaring the functions too?

I kinda prefer one directory with all files instead of 12 directories
with 2 files each.

11 years agoEnhance the communication filtering mechanism
Martin Quinson [Fri, 27 Apr 2012 19:51:05 +0000 (21:51 +0200)]
Enhance the communication filtering mechanism

* Add an extra argument to the filter: a smx_action_t describing the
  other side's communication. That's useful to write filters on other
  side's identity
* Ensure that if no comm matches the filters, the filter function gets
  saved in the comm object that gets created and stored in rdv point.
  Later on, when someone else tries to make a match, use that stored
  function to ensure that the stored filter accepts to match the new
  commer.

Thanks to Sorina Camarasu for exploring all this.

11 years agomodel-checker : remove meta-data of heap in comparison algorithm
Marion Guthmuller [Fri, 27 Apr 2012 14:43:29 +0000 (16:43 +0200)]
model-checker : remove meta-data of heap in comparison algorithm

11 years agoWorkaround problem with excess precision on i387 FPU.
Arnaud Giersch [Fri, 27 Apr 2012 12:16:18 +0000 (14:16 +0200)]
Workaround problem with excess precision on i387 FPU.

See http://gcc.gnu.org/PR323.

11 years agoUse existing xbt_swag_reset().
Arnaud Giersch [Fri, 27 Apr 2012 12:16:18 +0000 (14:16 +0200)]
Use existing xbt_swag_reset().

11 years agoAjout de tests pour kill et start time
navarro [Fri, 27 Apr 2012 11:16:03 +0000 (13:16 +0200)]
Ajout de tests pour kill et start time

11 years agoUpdate tesh for kill start time.
navarro [Fri, 27 Apr 2012 11:09:41 +0000 (13:09 +0200)]
Update tesh for kill start time.

11 years agoRewrite the kill_time mecanism.
navarro [Fri, 27 Apr 2012 10:57:25 +0000 (12:57 +0200)]
Rewrite the kill_time mecanism.

11 years agoRevert "got a "might be clobbered by ‘longjmp’ or ‘vfork’" error when compiled"
Arnaud Giersch [Fri, 27 Apr 2012 10:41:32 +0000 (12:41 +0200)]
Revert "got a "might be clobbered by ‘longjmp’ or ‘vfork’" error when compiled"

This reverts commit 34b3794d5a8de6a9258a6144f67de4fc38c960f1.

AFAICT, this is not needed after commit 1128245fc5ccac68ce1f696aab780e15ff9f735a.

11 years agoUseless free, and other cosmetics.
Arnaud Giersch [Fri, 27 Apr 2012 10:03:58 +0000 (12:03 +0200)]
Useless free, and other cosmetics.

Dynar is already free'd by xbt_dynar_merge.
The FIXME looks obsolete.

11 years agoPass 'res->link_list' and 'lat' directly to routing_get_route_and_latency().
Arnaud Giersch [Fri, 27 Apr 2012 10:03:58 +0000 (12:03 +0200)]
Pass 'res->link_list' and 'lat' directly to routing_get_route_and_latency().

11 years agoPut links in right order in tesh file.
Arnaud Giersch [Fri, 27 Apr 2012 10:03:58 +0000 (12:03 +0200)]
Put links in right order in tesh file.

11 years agoMake floyd_get_route_and_latency cleaner, and hopefully right.
Arnaud Giersch [Fri, 27 Apr 2012 10:03:58 +0000 (12:03 +0200)]
Make floyd_get_route_and_latency cleaner, and hopefully right.

Stack the links before processing them, and avoid costly dynar_unshift/
dynar_insert_at.

11 years agoCosmetics: a switch..case is clearer here.
Arnaud Giersch [Fri, 27 Apr 2012 10:03:58 +0000 (12:03 +0200)]
Cosmetics: a switch..case is clearer here.

11 years agoRework xbt_dynar_three_way_partition.
Arnaud Giersch [Fri, 27 Apr 2012 10:03:57 +0000 (12:03 +0200)]
Rework xbt_dynar_three_way_partition.

* use existing _xbt_dynar_elm() to retrieve elements;
* swap elements only when needed.