Logo AND Algorithmique Numérique Distribuée

Public GIT Repository
simgrid.git
5 years agoallow to cancel a s4u::Exec
Frederic Suter [Sat, 28 Jul 2018 22:23:50 +0000 (00:23 +0200)]
allow to cancel a s4u::Exec

5 years agofiltered_libraries++
Arnaud Giersch [Fri, 27 Jul 2018 22:05:41 +0000 (00:05 +0200)]
filtered_libraries++

5 years agoFix memory errors.
Arnaud Giersch [Fri, 27 Jul 2018 22:02:02 +0000 (00:02 +0200)]
Fix memory errors.

5 years agoSpurious 'n'.
Arnaud Giersch [Thu, 26 Jul 2018 09:48:11 +0000 (11:48 +0200)]
Spurious 'n'.

5 years agoKeep list of filtered libraries sorted.
Arnaud Giersch [Thu, 26 Jul 2018 08:28:50 +0000 (10:28 +0200)]
Keep list of filtered libraries sorted.

5 years agoRemove useless thread_local.
Arnaud Giersch [Thu, 19 Jul 2018 19:34:46 +0000 (21:34 +0200)]
Remove useless thread_local.

It doesn't make any difference if context/factory is not "thread".

5 years agoas the comment was saying, that was unsafe, and flang was doing something else
Augustin Degomme [Thu, 26 Jul 2018 17:08:05 +0000 (19:08 +0200)]
as the comment was saying, that was unsafe, and flang was doing something else

5 years agoDon't free there for intel compiler, it breaks.
Augustin Degomme [Thu, 26 Jul 2018 16:17:46 +0000 (18:17 +0200)]
Don't free there for intel compiler, it breaks.
Yes, that means leaking.

5 years ago[HostLoad] And lastly: Update the hooks used
Christian Heinrich [Thu, 26 Jul 2018 09:34:43 +0000 (11:34 +0200)]
[HostLoad] And lastly: Update the hooks used

5 years ago[HostLoad] Update the update() method to use ExecImplPtrs
Christian Heinrich [Thu, 26 Jul 2018 09:34:26 +0000 (11:34 +0200)]
[HostLoad] Update the update() method to use ExecImplPtrs

These ptrs are stored in the class, see the previous commit

5 years ago[HostLoad] Add method HostLoad::add_activity(ExecImplPtr)
Christian Heinrich [Thu, 26 Jul 2018 09:22:22 +0000 (11:22 +0200)]
[HostLoad] Add method HostLoad::add_activity(ExecImplPtr)

The HostLoad plugin keeps track of all the computations that are going on
and does no longer have to rely on calculations of the sort time_passed*speed.

Instead, we can now access the total cost of the computation and keep track
of how much is still remaining. Like this, we always account for exactly
the cost of that calculation.

5 years ago[HostLoad] Update when calling getters
Christian Heinrich [Thu, 26 Jul 2018 09:16:41 +0000 (11:16 +0200)]
[HostLoad] Update when calling getters

This will allow us to remove the CpuAction hook and replace it with
hooks that are only used after a calculation has completed.

If for instance a daemon (dvfs, load balancer, ...) wants to get
up-to-date information, this is now assured through the update call.

5 years ago[HostLoad] Update comments + add debug statement
Christian Heinrich [Thu, 26 Jul 2018 09:12:55 +0000 (11:12 +0200)]
[HostLoad] Update comments + add debug statement

5 years ago[HostLoad] Elaborate on comment
Christian Heinrich [Thu, 26 Jul 2018 07:48:37 +0000 (09:48 +0200)]
[HostLoad] Elaborate on comment

5 years ago[HostLoad] Remove wrong 'was_prev_idle' notion
Christian Heinrich [Mon, 23 Jul 2018 13:07:01 +0000 (15:07 +0200)]
[HostLoad] Remove wrong 'was_prev_idle' notion

The load is only updated after a call to LMM; this means, that
we get the real load the action caused by querying the constraint
and we don't need to have a variable for that state.

5 years ago[ENERGY] Remove HostLoad-plugin dependency
Christian Heinrich [Thu, 26 Jul 2018 14:38:26 +0000 (16:38 +0200)]
[ENERGY] Remove HostLoad-plugin dependency

5 years ago[SURF] Cosmetics for CpuAction
Christian Heinrich [Mon, 23 Jul 2018 09:40:44 +0000 (11:40 +0200)]
[SURF] Cosmetics for CpuAction

5 years agomissed one
Augustin Degomme [Thu, 26 Jul 2018 13:08:48 +0000 (15:08 +0200)]
missed one

5 years agomake a copy of args for each process
Augustin Degomme [Thu, 26 Jul 2018 12:52:17 +0000 (14:52 +0200)]
make a copy of args for each process
Not optimal as it's only for fortran (ifort) that it's useful.
Done this way to see if it helps flang as well

5 years agoadd another library to excludes to please mc
Augustin Degomme [Thu, 26 Jul 2018 09:18:43 +0000 (11:18 +0200)]
add another library to excludes to please mc

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Thu, 26 Jul 2018 08:22:49 +0000 (10:22 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agoadd libraries to excludes to please mc
Augustin Degomme [Thu, 26 Jul 2018 08:22:13 +0000 (10:22 +0200)]
add libraries to excludes to please mc

5 years agosonar
Frederic Suter [Thu, 26 Jul 2018 07:51:00 +0000 (09:51 +0200)]
sonar

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Thu, 26 Jul 2018 07:09:02 +0000 (09:09 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agoSometimes C and fortran compiler family differs...
Augustin Degomme [Wed, 25 Jul 2018 23:57:28 +0000 (01:57 +0200)]
Sometimes C and fortran compiler family differs...
Try to get around that.. Ugly for now.

5 years agoflang also does need some help
Augustin Degomme [Wed, 25 Jul 2018 23:52:29 +0000 (01:52 +0200)]
flang also does need some help

5 years agoforgot to change here
Augustin Degomme [Wed, 25 Jul 2018 23:14:07 +0000 (01:14 +0200)]
forgot to change here

5 years agointel somehow also matches __GNUC__
Augustin Degomme [Wed, 25 Jul 2018 22:57:34 +0000 (00:57 +0200)]
intel somehow also matches __GNUC__

5 years agoadd test for fortran params ... Not with MPI, but it should not change anything
Augustin Degomme [Wed, 25 Jul 2018 22:19:03 +0000 (00:19 +0200)]
add test for fortran params ... Not with MPI, but it should not change anything

5 years agothese were not used since ... well .. a long time
Augustin Degomme [Wed, 25 Jul 2018 22:17:55 +0000 (00:17 +0200)]
these were not used since ... well .. a long time

5 years agosend argv and argc to fortran runtimes, to allow using getarg
Augustin Degomme [Wed, 25 Jul 2018 22:09:08 +0000 (00:09 +0200)]
send argv and argc to fortran runtimes, to allow using getarg

5 years agosimplifications
Frederic Suter [Wed, 25 Jul 2018 14:48:43 +0000 (16:48 +0200)]
simplifications

5 years agoremove another call to simcall_execution_start
Frederic Suter [Wed, 25 Jul 2018 14:33:59 +0000 (16:33 +0200)]
remove another call to simcall_execution_start

5 years agochanging the way the tracing category is passed to ExecImpl
Frederic Suter [Wed, 25 Jul 2018 14:00:38 +0000 (16:00 +0200)]
changing the way the tracing category is passed to ExecImpl

the former version implied to set the category AFTER the start()
because the ExecImpl had to exist. It was against the idea of "do all
the sets and then starts". Now, the category is set at user level and
then passed to the Impl within the start simcall. Setting a category
after the start is now forbidden.

5 years agoreduce test size
Augustin Degomme [Tue, 24 Jul 2018 19:55:51 +0000 (21:55 +0200)]
reduce test size

5 years agoRework SMPI initialization to handle argc and argv earlier than in MPI_Init when...
Augustin Degomme [Tue, 24 Jul 2018 19:55:19 +0000 (21:55 +0200)]
Rework SMPI initialization to handle argc and argv earlier than in MPI_Init when possible.
Add support for MPI_Init(NULL,NULL).
Might break MC for now.

5 years agofix the (unoticed) mess I made
Frederic Suter [Tue, 24 Jul 2018 11:15:04 +0000 (13:15 +0200)]
fix the (unoticed) mess I made

5 years agoplease clang
Frederic Suter [Sat, 21 Jul 2018 15:19:34 +0000 (17:19 +0200)]
please clang

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Sat, 21 Jul 2018 15:05:41 +0000 (17:05 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agoremove direct call to simcall
Frederic Suter [Sat, 21 Jul 2018 15:03:49 +0000 (17:03 +0200)]
remove direct call to simcall
modify order in replay example
set the tracing category breaks examples/smpi/tracing but do not seem
to be needed so comment it for now. Further simplifications in tracing
may help to understand and/or fix.

5 years agodo not use simcall_execution_start directly
Frederic Suter [Sat, 21 Jul 2018 15:02:33 +0000 (17:02 +0200)]
do not use simcall_execution_start directly

5 years agoallow to set a tracing category for an Exec
Frederic Suter [Sat, 21 Jul 2018 13:25:17 +0000 (15:25 +0200)]
allow to set a tracing category for an Exec

5 years agostringify tracing category
Frederic Suter [Sat, 21 Jul 2018 12:34:27 +0000 (14:34 +0200)]
stringify tracing category

5 years ago[KERNEL] struct -> class to match it's declaration
Christian Heinrich [Fri, 20 Jul 2018 21:20:25 +0000 (23:20 +0200)]
[KERNEL] struct -> class to match it's declaration

This was previously declared as a class, so just
do the same here.

5 years agoboolification
Frederic Suter [Fri, 20 Jul 2018 19:58:42 +0000 (21:58 +0200)]
boolification

5 years agoallow to name an Exec
Frederic Suter [Fri, 20 Jul 2018 18:34:49 +0000 (20:34 +0200)]
allow to name an Exec

5 years agofix comment in example
Frederic Suter [Fri, 20 Jul 2018 18:29:57 +0000 (20:29 +0200)]
fix comment in example

5 years agoa bit more merging
Frederic Suter [Fri, 20 Jul 2018 17:36:22 +0000 (19:36 +0200)]
a bit more merging

5 years agowhen an activity is complete, nothing remains...
Frederic Suter [Fri, 20 Jul 2018 12:29:05 +0000 (14:29 +0200)]
when an activity is complete, nothing remains...

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Fri, 20 Jul 2018 11:51:11 +0000 (13:51 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agouse our new toys
Frederic Suter [Fri, 20 Jul 2018 11:48:14 +0000 (13:48 +0200)]
use our new toys

5 years agoCall ExecImpl::on_completion() before starting to destroy it
Martin Quinson [Fri, 20 Jul 2018 11:16:42 +0000 (13:16 +0200)]
Call ExecImpl::on_completion() before starting to destroy it

5 years ago[noci] fix #111
Frederic Suter [Fri, 20 Jul 2018 07:36:20 +0000 (09:36 +0200)]
[noci] fix #111

5 years ago[S4U] Cosmetics
Christian Heinrich [Thu, 19 Jul 2018 09:25:56 +0000 (11:25 +0200)]
[S4U] Cosmetics

5 years ago[KERNEL] Check if surf_action_ is nullptr
Christian Heinrich [Thu, 19 Jul 2018 12:17:08 +0000 (14:17 +0200)]
[KERNEL] Check if surf_action_ is nullptr

This is also done in the other methods, so we
should do that here as well.

5 years agoDisable mpich3 tests with valgrind on jenkins.
Arnaud Giersch [Thu, 19 Jul 2018 12:16:54 +0000 (14:16 +0200)]
Disable mpich3 tests with valgrind on jenkins.

They're taking too long (1h 47min and still counting...).

5 years agoEnable valgrind on mpich3 tests.
Arnaud Giersch [Thu, 19 Jul 2018 08:56:27 +0000 (10:56 +0200)]
Enable valgrind on mpich3 tests.

5 years agoAdd option -wrapper to mpich3 runtests.
Arnaud Giersch [Thu, 19 Jul 2018 08:54:02 +0000 (10:54 +0200)]
Add option -wrapper to mpich3 runtests.

5 years agoAllow other libraries to react to the --help flag, too
Martin Quinson [Wed, 18 Jul 2018 23:08:10 +0000 (01:08 +0200)]
Allow other libraries to react to the --help flag, too

When finding --help on the command line, simgrid usually stops right
after displaying its help message but some libraries using SimGrid
want to display their own help message before the end of the world.

Now, they can use the little sg_config_continue_after_help() function
to have SimGrid not stopping after dealing with the --help flag.

(fix #93)

5 years agothis is a boolean
Martin Quinson [Wed, 18 Jul 2018 22:54:05 +0000 (00:54 +0200)]
this is a boolean

5 years agosnake_case simix::contextes
Martin Quinson [Wed, 18 Jul 2018 20:47:08 +0000 (22:47 +0200)]
snake_case simix::contextes

5 years agocut some useless includes
Martin Quinson [Wed, 18 Jul 2018 20:40:44 +0000 (22:40 +0200)]
cut some useless includes

5 years agos/xbt_os_get_numcores()/std::thread::hardware_concurrency()/
Martin Quinson [Wed, 18 Jul 2018 20:32:44 +0000 (22:32 +0200)]
s/xbt_os_get_numcores()/std::thread::hardware_concurrency()/

5 years agoget rid of xbt_os_thread_yield() using C++11
Martin Quinson [Wed, 18 Jul 2018 20:28:45 +0000 (22:28 +0200)]
get rid of xbt_os_thread_yield() using C++11

5 years agoRemove portability wrapper to condition variables
Martin Quinson [Wed, 18 Jul 2018 20:25:14 +0000 (22:25 +0200)]
Remove portability wrapper to condition variables

5 years agoreimplement parmap with C++11 mutex and cond
Martin Quinson [Wed, 18 Jul 2018 20:19:37 +0000 (22:19 +0200)]
reimplement parmap with C++11 mutex and cond

5 years agouse std::mutex instead of xbt_os_mutex_t in simix
Martin Quinson [Wed, 18 Jul 2018 20:03:26 +0000 (22:03 +0200)]
use std::mutex instead of xbt_os_mutex_t in simix

5 years agofix makedist
Martin Quinson [Wed, 18 Jul 2018 19:34:02 +0000 (21:34 +0200)]
fix makedist

5 years agowe don't need thread_specific anymore
Martin Quinson [Wed, 18 Jul 2018 19:21:33 +0000 (21:21 +0200)]
we don't need thread_specific anymore

5 years agoreimplement the parallel contextes with C++11 w/o xbt_os_thread_set_specific()
Martin Quinson [Wed, 18 Jul 2018 19:08:40 +0000 (21:08 +0200)]
reimplement the parallel contextes with C++11 w/o xbt_os_thread_set_specific()

5 years agothread_local is part of C++11, nowadays
Martin Quinson [Wed, 18 Jul 2018 18:46:28 +0000 (20:46 +0200)]
thread_local is part of C++11, nowadays

5 years ago[SMPI/LB] Add XBT_PUBLIC to load_balancer.h declarations
Christian Heinrich [Wed, 16 May 2018 13:23:15 +0000 (15:23 +0200)]
[SMPI/LB] Add XBT_PUBLIC to load_balancer.h declarations

5 years ago[ENERGY] Don't halt, just emit warning in special case
Christian Heinrich [Tue, 17 Jul 2018 08:29:21 +0000 (10:29 +0200)]
[ENERGY] Don't halt, just emit warning in special case

Even though 'AllCores' and 'OneCore' are the same in the
special case of #cores == 1, just go with the OneCore value.

This makes it much simpler to play around with the platform
without having to change the power profile each time.

5 years ago[XBT] Config::get_name -> Make 'this' const
Christian Heinrich [Wed, 18 Jul 2018 10:51:03 +0000 (12:51 +0200)]
[XBT] Config::get_name -> Make 'this' const

This is not the return value that is const'ed,
but just shows that this method does not change the object.

5 years ago[KERNEL] Fix grammar in a comment
Christian Heinrich [Wed, 18 Jul 2018 09:07:41 +0000 (11:07 +0200)]
[KERNEL] Fix grammar in a comment

5 years ago[HostLoad] Add total idle time
Christian Heinrich [Tue, 17 Jul 2018 11:56:33 +0000 (13:56 +0200)]
[HostLoad] Add total idle time

The 'normal' idle time can (and does) get reset, but
it is interesting to know how much a host idled until
now in total.

5 years ago[SMPI/REPLAY] Fix issues with daemons
Christian Heinrich [Tue, 17 Jul 2018 11:44:52 +0000 (13:44 +0200)]
[SMPI/REPLAY] Fix issues with daemons

When daemons are running, process-id's of the ranks don't
start at 1. Here, we insert the pid's of the actual actors.

5 years agoBe less specific in valgrind suppression.
Arnaud Giersch [Wed, 18 Jul 2018 11:47:14 +0000 (13:47 +0200)]
Be less specific in valgrind suppression.

5 years agoSimplify memory handling.
Arnaud Giersch [Wed, 18 Jul 2018 09:45:44 +0000 (11:45 +0200)]
Simplify memory handling.

5 years agoMemory leak.
Arnaud Giersch [Wed, 18 Jul 2018 09:21:17 +0000 (11:21 +0200)]
Memory leak.

5 years agosnake_case s4u API in the example documentation
Martin Quinson [Wed, 18 Jul 2018 06:09:00 +0000 (08:09 +0200)]
snake_case s4u API in the example documentation

5 years agodoxygen: rework the s4u header
Martin Quinson [Tue, 17 Jul 2018 23:58:56 +0000 (01:58 +0200)]
doxygen: rework the s4u header

5 years agodoxygen: uniformity in command markers (@ vs. \)
Martin Quinson [Tue, 17 Jul 2018 23:51:00 +0000 (01:51 +0200)]
doxygen: uniformity in command markers (@ vs. \)

5 years agodoxygen: better handling of deprecated symbols
Martin Quinson [Tue, 17 Jul 2018 22:26:36 +0000 (00:26 +0200)]
doxygen: better handling of deprecated symbols

5 years agomy_valgrind.pl: pass keep-temps to smpirun so that valgrind can analyse the binaries...
Martin Quinson [Tue, 17 Jul 2018 21:36:03 +0000 (23:36 +0200)]
my_valgrind.pl: pass keep-temps to smpirun so that valgrind can analyse the binaries on memleaks

5 years agocmake: stop patching tesh in FindValgrind, that's too ugly
Martin Quinson [Tue, 17 Jul 2018 21:18:13 +0000 (23:18 +0200)]
cmake: stop patching tesh in FindValgrind, that's too ugly

5 years agosonar: unused parameter
Martin Quinson [Tue, 17 Jul 2018 21:11:27 +0000 (23:11 +0200)]
sonar: unused parameter

5 years agoinstall smpimain in /usr/lib/simgrid
Martin Quinson [Tue, 17 Jul 2018 09:03:14 +0000 (11:03 +0200)]
install smpimain in /usr/lib/simgrid

It's not meant to be used directly by the user

5 years agoCOPYING: align with the package content
Martin Quinson [Mon, 16 Jul 2018 21:24:03 +0000 (23:24 +0200)]
COPYING: align with the package content

5 years agoCosmetic indentation.
Arnaud Giersch [Tue, 17 Jul 2018 12:25:33 +0000 (14:25 +0200)]
Cosmetic indentation.

5 years agoAdd dependencies.
Arnaud Giersch [Tue, 17 Jul 2018 12:20:43 +0000 (14:20 +0200)]
Add dependencies.

5 years agoFiles were regenerated with maintainer_mode on.
Arnaud Giersch [Tue, 17 Jul 2018 12:19:31 +0000 (14:19 +0200)]
Files were regenerated with maintainer_mode on.

5 years agoinitialize value to finalize (-1)
Frederic Suter [Tue, 17 Jul 2018 08:17:45 +0000 (10:17 +0200)]
initialize value to finalize (-1)

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Tue, 17 Jul 2018 07:39:09 +0000 (09:39 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agoMSG to S4U conversion.
Frederic Suter [Mon, 16 Jul 2018 14:53:18 +0000 (16:53 +0200)]
MSG to S4U conversion.
This example is currently broken, hence not tested

5 years ago[ENERGY] Updated some debug messages
Christian Heinrich [Mon, 16 Jul 2018 08:54:26 +0000 (10:54 +0200)]
[ENERGY] Updated some debug messages

5 years ago[SMPI/LB] Remove smpi/plugin/lb/migration-frequency option
Christian Heinrich [Mon, 16 Jul 2018 14:21:17 +0000 (16:21 +0200)]
[SMPI/LB] Remove smpi/plugin/lb/migration-frequency option

This option was erroneously added in 1caa54629d706bd2b086297bef7e61295755b762,
even though the load balancing is not yet published.

This option was moved to the right location in the LB code and will
not be required here.

5 years agoMerge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid
Frederic Suter [Mon, 16 Jul 2018 13:43:21 +0000 (15:43 +0200)]
Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/simgrid/simgrid

5 years agoif the deque is empty, remove it from the map
Frederic Suter [Mon, 16 Jul 2018 13:30:45 +0000 (15:30 +0200)]
if the deque is empty, remove it from the map

5 years agoVERSION_GREATER_EQUAL is not available with older cmake.
Arnaud Giersch [Mon, 16 Jul 2018 13:22:59 +0000 (15:22 +0200)]
VERSION_GREATER_EQUAL is not available with older cmake.