- name: Create the success Message
if: ${{ success() }}
run: |
- ver=$(grep set.SIMGRID_VERSION_MINOR CMakeLists.txt|sed 's/[^"]*"//'|sed 's/".*$//') echo "{\"attachments\": [{\"color\": \"#00FF00\", \"text\":\"Simgrid built successfully on ${{ matrix.config.name }}! ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} \"}]}" > mattermost.json
+ ver=$(grep set.SIMGRID_VERSION_MINOR CMakeLists.txt|sed 's/[^"]*"//'|sed 's/".*$//') echo "{\"attachments\": [{\"color\": \"#00FF00\", \"text\":\"SimGrid built successfully on ${{ matrix.config.name }}! ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }} \"}]}" > mattermost.json
- uses: komarnitskyi/action-mattermost-notification@v0.1.2-beta
if: ${{ always() }}
env:
-Simgrid Core Team
+SimGrid Core Team
_________________
SimGrid is a joint project. Its main authors are (alphabetic order):
message(" Graphviz mode ...............: ${HAVE_GRAPHVIZ}")
message(" Mallocators .................: ${enable_mallocators}")
message("")
-message(" Simgrid dependencies ........: ${SIMGRID_DEP}")
+message(" SimGrid dependencies ........: ${SIMGRID_DEP}")
message("")
execute_process(COMMAND ${CMAKE_COMMAND} -E make_directory ${PROJECT_BINARY_DIR}/Testing/Notes/)
- Synchronize the MBI tests with upstream.
- Show the full actor bactraces when replaying a MC trace (with model-check/replay)
and the status of all actors on deadlocks in MC mode.
- - The safety/stateless aspects of the MC are now enabled by default in all simgrid builds.
+ - The safety/stateless aspects of the MC are now enabled by default in all SimGrid builds.
Liveness and stateful aspects are still controled by the enabling_model-checking
configuration option.
- Stateless model-checking is now usable on any system, including Mac OSX and ARM processors.
New plugin: the Chaos Monkey (killing actors at any time)
- Along with the new simgrid-monkey script, it tests whether your simulation
resists resource failures at any possible timestamp in your simulation.
- - It is mostly intended to test the simgrid core in extreme conditions,
+ - It is mostly intended to test the SimGrid core in extreme conditions,
but some users may find it interesting too.
Models:
- Network model 'NS3' was renamed into 'ns-3'.
Python:
- - Simgrid can now hopefully be installed with pip.
+ - SimGrid can now hopefully be installed with pip.
S4U:
- wait_any can now be used for asynchronous executions too.
- InfiniBand network model added: Based on the works of Jerome Vienne
http://mescal.imag.fr/membres/jean-marc.vincent/index.html/PhD/Vienne.pdf
- When smpi/display_timing is set, also display global simulation time and application times
- - Have smpirun, smpicc and friends display the simgrid git hash version on --git-version
+ - Have smpirun, smpicc and friends display the SimGrid git hash version on --git-version
* Collective communications
- SMP-aware algorithms are now dynamically handled. An internal communicator is created for each node, and an external one to handle communications between "leaders" of each node
- MVAPICH2 (1.9) collective algorithms selector: normal and SMP algorithms are handled, and selection logic is based on the one used on TACC's Stampede cluster (https://www.tacc.utexas.edu/stampede/).
Portability
* Create an installer for windows with nsis (amd64 and win32)
- - Add an hello world project to illustrate simgrid project creation.
- - Embed libpcre into the Simgrid installer to avoid
+ - Add an hello world project to illustrate SimGrid project creation.
+ - Embed libpcre into the SimGrid installer to avoid
its compilation burden
* The raw execution contexts should work on Apple now
* Port to Windows 64 bits
SimGrid-java (3.6) unstable; urgency=low
* Initial release.
- * Split of every thing from simgrid v3.5 into a separate package.
+ * Split of every thing from SimGrid v3.5 into a separate package.
-- 2011-10-05 Da SimGrid team <simgrid-devel@lists.gforge.inria.fr>
* Greatly improved our cdash/ctest interactions
Check http://cdash.inria.fr/CDash/index.php?project=Simgrid
* Added memory checking tests with valgrind; lot of memleak fixing.
- This may be the first release of simgrid with so few memory issues
+ This may be the first release of SimGrid with so few memory issues
* Added code coverage tests.
Our coverage is still improvable, but at least we see it on cdash.
Timing report of this version:
This version seem to be more than 5% faster than 3.3.1 (on linux
- 64bits with contextes). The gain is less than expected, we are
+ 64bits with contexts). The gain is less than expected, we are
investigating this for next release.
-- Da SimGrid team <simgrid-devel@lists.gforge.inria.fr> Wed, 19 Aug 2009 17:07:12 +0200
- Linux(debian)/amd64/context
- Linux(debian)/amd64/pthreads
These targets fail about 1/10 of times on gras/pmm, but we believe
- that this is because of the test, not because of simgrid.
+ that this is because of the test, not because of SimGrid.
amok/saturate_sg fails even more rarely, and the test may not be
the problem.
is really less memory-demanding, which should allow you to use
larger files in SimGrid [AL].
- * Inform valgrind about our contextes, so that it becomes usable
+ * Inform valgrind about our contexts, so that it becomes usable
with the default (and more effecient) version of SimGrid
[contributed by Sékou Diakite, many thanks]
@li I want to trace the resource utilization of all hosts
and links of the platform, and my simulator <b>does not</b> use
the tracing API. For that, you can run a uncategorized trace
-with the following parameters (it will work with <b>any</b> Simgrid
+with the following parameters (it will work with <b>any</b> SimGrid
simulator):
@verbatim
./your_simulator @
Simulating DAG
==============
-This tutorial presents the basics to understand how DAG are represented in Simgrid and how to simulate their workflow.
+This tutorial presents the basics to understand how DAG are represented in SimGrid and how to simulate their workflow.
Definition of a DAG
-------------------
In this DAG we want ``c1`` to compute 1e9 flops, ``c2`` to compute 5e9 flops and ``c3`` to compute 2e9 flops.
There is also a data transfer of 5e8 bytes between ``c1`` and ``c3``.
-First of all, include the Simgrid library and define the log category.
+First of all, include the SimGrid library and define the log category.
.. literalinclude:: ../../examples/cpp/dag-tuto/s4u-dag-tuto.cpp
:language: cpp
Lab 2: Import a DAG from a file
-------------------------------
-In this lab we present how to import a DAG into you Simgrid simulation, either using a DOT file, a JSON file, or a DAX file.
+In this lab we present how to import a DAG into you SimGrid simulation, either using a DOT file, a JSON file, or a DAX file.
The files presented in this lab describe the following DAG:
.. literalinclude:: ../../examples/cpp/dag-from-dot-simple/dag.dot
:language: dot
-It can be imported as a vector of Activities into Simgrid using :cpp:func:`simgrid::s4u::create_DAG_from_DOT`. Then, you have to assign hosts to your Activities.
+It can be imported as a vector of Activities into SimGrid using :cpp:func:`simgrid::s4u::create_DAG_from_DOT`. Then, you have to assign hosts to your Activities.
.. literalinclude:: ../../examples/cpp/dag-from-dot-simple/s4u-dag-from-dot-simple.cpp
:language: cpp
.. literalinclude:: ../../examples/cpp/dag-from-json-simple/dag.json
:language: json
-It can be imported as a vector of Activities into Simgrid using :cpp:func:`simgrid::s4u::create_DAG_from_json`.
+It can be imported as a vector of Activities into SimGrid using :cpp:func:`simgrid::s4u::create_DAG_from_json`.
.. literalinclude:: ../../examples/cpp/dag-from-json-simple/s4u-dag-from-json-simple.cpp
:language: cpp
.. literalinclude:: ../../examples/cpp/dag-from-dax-simple/dag.xml
:language: xml
-It can be imported as a vector of Activities into Simgrid using :cpp:func:`simgrid::s4u::create_DAG_from_DAX`.
+It can be imported as a vector of Activities into SimGrid using :cpp:func:`simgrid::s4u::create_DAG_from_DAX`.
.. literalinclude:: ../../examples/cpp/dag-from-dax-simple/s4u-dag-from-dax-simple.cpp
:language: cpp
{
...
-First, we initialize the Simgrid Engine.
+First, we initialize the SimGrid Engine.
.. code-block:: cpp
The following errors denote a problem in the SimGrid tool itself. Most of the time, you should let these
exception go, so that the simulation stops. But you may want to catch them, for example when you launch
- simgrid from a python notebook and want to handle the problem accordingly.
+ SimGrid from a python notebook and want to handle the problem accordingly.
.. doxygenclass:: simgrid::AssertionError
.. doxygenclass:: simgrid::ParseError
The following errors denote a problem in the SimGrid tool itself. Most of the time, you should let these
exception go, so that the simulation stops. But you may want to catch them, for example when you launch
- simgrid from a python notebook and want to handle the problem accordingly.
+ SimGrid from a python notebook and want to handle the problem accordingly.
.. autoclass:: simgrid.AssertionError
SimGrid. Some crashes can be expected while trying these algorithms
with unusual sizes/parameters
-To retrive the full list of implemented algorithms in your version of SimGrid, simply use ``smpirun --help-coll``.
+To retrieve the full list of implemented algorithms in your version of SimGrid, simply use ``smpirun --help-coll``.
MPI_Alltoall
^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^
To add a new algorithm, one should check in the src/smpi/colls folder
-how other algorithms are coded. Using plain MPI code inside Simgrid
+how other algorithms are coded. Using plain MPI code inside SimGrid
can't be done, so algorithms have to be changed to use smpi version of
the calls instead (MPI_Send will become smpi_mpi_send). Some functions
may have different signatures than their MPI counterpart, please check
- To register the new version of the algorithm, simply add a line to the corresponding macro in src/smpi/colls/cools.h ( add a "COLL_APPLY(action, COLL_ALLTOALL_SIG, pair)" to the COLL_ALLTOALLS macro ). The algorithm should now be compiled and be selected when using --cfg=smpi/alltoall:pair at runtime.
- - To add a test for the algorithm inside Simgrid's test suite, juste add the new algorithm name in the ALLTOALL_COLL list found inside teshsuite/smpi/CMakeLists.txt . When running ctest, a test for the new algorithm should be generated and executed. If it does not pass, please check your code or contact us.
+ - To add a test for the algorithm inside SimGrid's test suite, juste add the new algorithm name in the ALLTOALL_COLL list found inside teshsuite/smpi/CMakeLists.txt . When running ctest, a test for the new algorithm should be generated and executed. If it does not pass, please check your code or contact us.
- Please submit your patch for inclusion in SMPI, for example through a pull request on GitHub or directly per email.
executable. It makes perfectly sense in the general case, but we need
to circumvent this rule of thumb in our case. To that extend, the
binary is copied in a temporary file before being re-linked against.
-``dlmopen()`` cannot be used as it only allows 256 contextes, and as it
-would also duplicate simgrid itself.
+``dlmopen()`` cannot be used as it only allows 256 contexts, and as it
+would also duplicate SimGrid itself.
This approach greatly speeds up the context switching, down to about
-40 CPU cycles with our raw contextes, instead of requesting several
+40 CPU cycles with our raw contexts, instead of requesting several
syscalls with the ``mmap()`` approach. Another advantage is that it
permits one to run the SMPI contexts in parallel, which is obviously not
possible with the ``mmap()`` approach. It was tricky to implement, but
Also, currently, only the binary is copied and dlopen-ed for each MPI
rank. We could probably extend this to external dependencies, but for
now, any external dependencies must be statically linked into your
-application. As usual, simgrid itself shall never be statically linked
+application. As usual, SimGrid itself shall never be statically linked
in your app. You don't want to give a copy of SimGrid to each MPI rank:
that's ways too much for them to deal with.
r-cran-plyr \
r-cran-jsonlite \
r-cran-gridextra \
-# simgrid dependencies
+# SimGrid dependencies
g++ \
gcc \
git \
RUN mkdir /source && cd /source && \
git clone https://github.com/msnoigrs/ox-rst.git ox-rst.git
-# compile install simgrid
+# compile install SimGrid
RUN cd /source && git clone --depth=1 https://framagit.org/simgrid/simgrid.git simgrid.git && \
cd simgrid.git && \
cmake -DCMAKE_INSTALL_PREFIX=/usr/ -Denable_documentation=OFF -Denable_smpi=ON -Denable_compile_optimizations=ON . && \
r-cran-dplyr \
r-cran-irkernel \
r-cran-quantreg \
-# simgrid dependencies
+# SimGrid dependencies
g++ \
gcc \
git \
papermill==2.3.3 \
ipywidgets==7.6.5
-# simgrid
+# SimGrid
RUN mkdir -p /source && cd /source && git clone --depth=1 https://framagit.org/simgrid/simgrid.git simgrid.git && \
cd simgrid.git && \
cmake -DCMAKE_INSTALL_PREFIX=/usr/ -Denable_documentation=OFF -Denable_smpi=ON -Denable_compile_optimizations=ON . && \
*
* @param latency_base The base latency for this calibration (user-defined)
* @param seg Segmentation (user-defined)
- * @param size Message size (simgrid)
+ * @param size Message size (SimGrid)
*/
static double latency_factor_cb(double latency_base, const SegmentedRegression& seg, double size,
const sg4::Host* /*src*/, const sg4::Host* /*dst*/,
*
* @param bw_base The base bandwidth for this calibration (user-defined)
* @param seg Segmentation (user-defined)
- * @param size Message size (simgrid)
+ * @param size Message size (SimGrid)
*/
static double bw_factor_cb(double bw_base, const SegmentedRegression& seg, double size, const sg4::Host* /*src*/,
const sg4::Host* /*dst*/, const std::vector<sg4::Link*>& /*links*/,
*
* @param latency_base The base latency for this calibration (user-defined)
* @param seg Segmentation (user-defined)
- * @param size Message size (simgrid)
+ * @param size Message size (SimGrid)
*/
static double latency_factor_cb(double latency_base, const SegmentedRegression& seg, double size,
const sg4::Host* /*src*/, const sg4::Host* /*dst*/,
*
* @param bw_base The base bandwidth for this calibration (user-defined)
* @param seg Segmentation (user-defined)
- * @param size Message size (simgrid)
+ * @param size Message size (SimGrid)
*/
static double bw_factor_cb(double bw_base, const SegmentedRegression& seg, double size, const sg4::Host* /*src*/,
const sg4::Host* /*dst*/, const std::vector<sg4::Link*>& /*links*/,
"import json\n",
"\n",
"def plot_compare(df):\n",
- " \"\"\" Auxiliary function to compare simgrid and reality \"\"\"\n",
+ " \"\"\" Auxiliary function to compare SimGrid and reality \"\"\"\n",
" func = list(df['op'].unique())\n",
" assert len(func) == 1\n",
" func = func[0]\n",
}
],
"source": [
- "# simgrid has fewer executions than real life, keep the same amount of samples for better visualization\n",
+ "# SimGrid has fewer executions than real life, keep the same amount of samples for better visualization\n",
"N = df_smpi_send.groupby(\"msg_size\").size().iloc[0]\n",
"\n",
"tmp = pandas.concat([df_send.groupby(\"msg_size\").sample(N), df_smpi_send, df_isend.groupby(\"msg_size\").sample(N), df_smpi_isend, df_recv.groupby(\"msg_size\").sample(N), df_smpi_recv, df_pingpong.groupby(\"msg_size\").sample(N), df_smpi_pingpong])\n",
}
],
"source": [
- "# simgrid has fewer executions than real life, keep the same amount of samples for better visualization\n",
+ "# SimGrid has fewer executions than real life, keep the same amount of samples for better visualization\n",
"N = df_smpi_send.groupby(\"msg_size\").size().iloc[0]\n",
"\n",
"tmp = pandas.concat([df_send.groupby(\"msg_size\").sample(N), df_smpi_send, df_isend.groupby(\"msg_size\").sample(N), df_smpi_isend, df_recv.groupby(\"msg_size\").sample(N), df_smpi_recv, df_pingpong.groupby(\"msg_size\").sample(N), df_smpi_pingpong])\n",
You can execute the notebook `network_calibration_tutorial.ipynb <https://framagit.org/simgrid/simgrid/tree/master/docs/source/tuto_network_calibration/network_calibration_tutorial.ipynb>`_) by yourself using the docker image
available at: `Dockerfile <https://framagit.org/simgrid/simgrid/tree/master/docs/source/tuto_network_calibration/Dockerfile>`_. For that, run the
-following commands in the tutorial folder inside simgrid's code source (``docs/source/tuto_network_calibration``):
+following commands in the tutorial folder inside SimGrid's code source (``docs/source/tuto_network_calibration``):
.. code-block::
# Load and relabel the data
df = pajeng_read(args[1])
df$state %>%
- # rename some columns to use simgrid terminology
+ # rename some columns to use SimGrid terminology
rename(Actor = Container,
State = Value) %>%
# do the plot
-.. S4U (Simgrid for you) is the modern interface of SimGrid, which new project should use.
+.. S4U (SimGrid for you) is the modern interface of SimGrid, which new project should use.
..
.. This file follows the ReStructured syntax to be included in the
.. documentation, but it should remain readable directly.
/* Become one of the simulated actors (must be done after the platform creation, or the host won't exist). */
sg_actor_attach("sender", nullptr, e.host_by_name("Tremblay"), nullptr);
- ensure_root_tid(); // Only useful in this test: we ensure that simgrid is not broken and that this code is executed in
+ ensure_root_tid(); // Only useful in this test: we ensure that SimGrid is not broken and that this code is executed in
// the correct system thread
// Execute the sender code. The root thread was actually turned into a regular actor
* in collective operations. But it doesn't happen in this example
*
* @param op MPI Operation (set by user at cb registering below)
- * @param size Message size (set by simgrid)
- * @param src Source host (set by simgrid)
- * @param dst Source host (set by simgrid)
+ * @param size Message size (set by SimGrid)
+ * @param src Source host (set by SimGrid)
+ * @param dst Source host (set by SimGrid)
*/
static double smpi_cost_cb(SmpiOperation op, size_t /*size*/, const sg4::Host* src, const sg4::Host* dst)
{
MPI_Send(&msg, 1, MPI_INT, dst, tag1, MPI_COMM_WORLD);
/* Inject five seconds of fake computation time */
- /* We are in a public file, not internal to simgrid, so _benched flavour is preferred, as it protects against accidental skip */
- /* smpi_execute_benched here is mostly equivalent to sleep, which is intercepted by smpi and turned into smpi_sleep */
+ /* We are in a public file, not internal to SimGrid, so _benched flavour is preferred, as it protects against
+ * accidental skip */
+ /* smpi_execute_benched here is mostly equivalent to sleep, which is intercepted by smpi and turned into smpi_sleep
+ */
/* Difference with sleep is only for energy consumption */
smpi_execute_benched(5.0);
msg++;
/* Inject 762.96 Mflops of computation time - Host Jupiter is 76.296Mf per second, so this should amount to 10s */
- /* We are in a public file, not internal to simgrid, so _benched flavour is preferred, as it protects against accidental skip */
+ /* We are in a public file, not internal to SimGrid, so _benched flavour is preferred, as it protects against
+ * accidental skip */
smpi_execute_flops_benched(762960000);
printf("[%d] After a nap, increment message's value to '%d'\n", rank, msg);
/** @brief 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.
- * If you are writing a library using simgrid, you may want to display your own help message before everything stops.
- * If so, just call this function before having simgrid parsing the command line, and you will be given the control
+ * When finding --help on the command line, SimGrid usually stops right after displaying its help message.
+ * If you are writing a library using SimGrid, you may want to display your own help message before everything stops.
+ * If so, just call this function before having SimGrid parsing the command line, and you will be given the control
* even if the user is asking for help.
*/
XBT_PUBLIC void sg_config_continue_after_help();
typedef const s4u_Actor* const_sg_actor_t;
/** @ingroup m_datatypes_management_details
- * @brief Type for any simgrid size
+ * @brief Type for any SimGrid size
*/
typedef unsigned long long sg_size_t;
/** @ingroup m_datatypes_management_details
- * @brief Type for any simgrid offset
+ * @brief Type for any SimGrid offset
*/
typedef long long sg_offset_t;
#include <xbt/base.h>
namespace simgrid {
-/** Returns the ns3 node from a simgrid host */
+/** Returns the ns3 node from a SimGrid host */
XBT_PUBLIC ns3::Ptr<ns3::Node> get_ns3node_from_sghost(const simgrid::s4u::Host* host);
}; // namespace simgrid
/** @brief set a configuration variable
*
* @beginrst
- * Do --help on any simgrid binary to see the list of currently existing configuration variables
+ * Do --help on any SimGrid binary to see the list of currently existing configuration variables
* (see also :ref:`options`).
* @endrst
*
-/* xbt.h - Public interface to the xbt (simgrid's toolbox) */
+/* xbt.h - Public interface to the xbt (SimGrid's toolbox) */
/* Copyright (c) 2004-2023. The SimGrid Team. All rights reserved. */
-/* xbt.h - Public interface to the xbt (simgrid's toolbox) */
+/* xbt.h - Public interface to the xbt (SimGrid's toolbox) */
/* Copyright (c) 2004-2023. The SimGrid Team. All rights reserved. */
SG_BEGIN_DECL
#ifdef XBT_LOG_LOCALLY_DEFINE_XBT_CHANNEL
-XBT_LOG_NEW_CATEGORY(xbt, "All XBT categories (simgrid toolbox)");
+XBT_LOG_NEW_CATEGORY(xbt, "All XBT categories (SimGrid toolbox)");
XBT_LOG_NEW_SUBCATEGORY(xbt_help, xbt, "Help messages");
#else
XBT_LOG_EXTERNAL_CATEGORY(xbt);
if not os.path.exists("MANIFEST.in"):
raise RuntimeError(
- "Please generate a MANIFEST.in file (configure simgrid, and copy it here if you build out of tree)")
+ "Please generate a MANIFEST.in file (configure SimGrid, and copy it here if you build out of tree)")
for ext in self.extensions:
self.build_extension(ext)
}
double ns3_time = ns3::Simulator::GetNextEventTime().GetSeconds();
- XBT_DEBUG("NS3 tells that the next occuring event is at %f (it's %f in simgrid), so NS3 returns a delta of %f.",
+ XBT_DEBUG("NS3 tells that the next occuring event is at %f (it's %f in SimGrid), so NS3 returns a delta of %f.",
ns3_time, sg_time, ns3_time - sg_time);
return ns3_time - sg_time;
}
* in which vector clocks are typically used).
*
* Support, however, needs to be added to clock vectors since
- * Simgrid permits the *creation* of new actors during execution.
+ * SimGrid permits the *creation* of new actors during execution.
* Since we don't know this size before-hand, we have to allow
* clock vectors to behave as if they were "infinitely" large. To
* do so, all newly mapped elements, if not assigned a value, are
/**
* @brief Computes the backtrack set for this state
- * according to its definition in Simgrid.
+ * according to its definition in SimGrid.
*
* The backtrack set as it appears in DPOR, SDPOR, and ODPOR
* in SimGrid consists of those actors marked as `todo`
* The recorded path is written in the log output and can be replayed with MC disabled
* (even with a non-MC build) using `--cfg=model-check/replay:$replayPath`.
*
- * The same version of Simgrid should be used and the same arguments should be
+ * The same version of SimGrid should be used and the same arguments should be
* passed to the application (without the MC specific arguments).
*/
#include <algorithm>
#include <string>
-XBT_LOG_NEW_CATEGORY(s4u, "Log channels of the S4U (Simgrid for you) interface");
+XBT_LOG_NEW_CATEGORY(s4u, "Log channels of the S4U (SimGrid for you) interface");
XBT_LOG_NEW_DEFAULT_SUBCATEGORY(s4u_engine, s4u, "Logging specific to S4U (engine)");
static simgrid::kernel::actor::ActorCode maestro_code;
/** @brief 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.
- * If you are writing a library using simgrid, you may want to display your own help message before everything stops.
- * If so, just call this function before having simgrid parsing the command line, and you will be given the control
+ * When finding --help on the command line, SimGrid usually stops right after displaying its help message.
+ * If you are writing a library using SimGrid, you may want to display your own help message before everything stops.
+ * If so, just call this function before having SimGrid parsing the command line, and you will be given the control
* even if the user is asking for help.
*/
void sg_config_continue_after_help()
-/* selector with default/naive Simgrid algorithms. These should not be trusted for performance evaluations */
+/* selector with default/naive SimGrid algorithms. These should not be trusted for performance evaluations */
/* Copyright (c) 2009-2023. The SimGrid Team. All rights reserved. */
for (const auto& elem : (action)) { \
ss << elem << " "; \
} \
- ss << "\nPlease contact the Simgrid team if support is needed"; \
+ ss << "\nPlease contact the SimGrid team if support is needed"; \
throw std::invalid_argument(ss.str()); \
} \
}
MPI_Op op_;
std::unique_ptr<smpi_mpi_generalized_request_funcs_t> generalized_funcs;
std::vector<MPI_Request> nbc_requests_;
- s4u::Host* src_host_ = nullptr; //!< save simgrid's source host since it can finished before the recv
+ s4u::Host* src_host_ = nullptr; //!< save SimGrid's source host since it can finished before the recv
static bool match_common(MPI_Request req, MPI_Request sender, MPI_Request receiver);
static bool match_types(MPI_Datatype stype, MPI_Datatype rtype);
#include <valgrind/valgrind.h>
#endif
-/* We don't want to intercept pthread within simgrid. Instead we should provide the real implem to simgrid */
+/* We don't want to intercept pthread within SimGrid. Instead we should provide the real implem to SimGrid */
static int (*raw_pthread_create)(pthread_t*, const pthread_attr_t*, void* (*)(void*), void*);
static int (*raw_pthread_join)(pthread_t, void**);
static int (*raw_mutex_init)(pthread_mutex_t*, const pthread_mutexattr_t*);
* This function must be called once the framework configuration is done. mallocators will not get used until it's
* called (check the implementation notes above for more info).
*
- * sg_config uses this function to inform the mallocators when simgrid is configured, and whether lock protection is
+ * sg_config uses this function to inform the mallocators when SimGrid is configured, and whether lock protection is
* needed.
*/
void xbt_mallocator_initialization_is_done(int need_protection)
* It is not written to be pleasant to read, but instead to resist the aggressions of the monkey:
* - Workers keep going until after a global variable `todo` reaches 0.
* - The master is a daemon that just sends infinitely tasks
- * (simgrid simulations stop as soon as all non-daemon actors are done).
+ * (SimGrid simulations stop as soon as all non-daemon actors are done).
* - The platform is created programmatically to remove path issues and control the problem size.
*
* Command-line configuration items:
It is not written to be pleasant to read, but instead to resist the aggressions of the monkey:
- Workers keep going until after a global variable `todo` reaches 0.
- The master is a daemon that just sends infinitely tasks
- (simgrid simulations stop as soon as all non-daemon actors are done).
+ (SimGrid simulations stop as soon as all non-daemon actors are done).
- The platform is created programmatically to remove path issues and control the problem size.
See the simgrid-monkey script for more information.
add_dependencies(tests tests-mbi)
add_dependencies(tests-mbi simgrid-mc smpimain)
- # Remove Concurrency tests that are out of reach because simgrid does not intercept local modifications yet
+ # Remove Concurrency tests that are out of reach because SimGrid does not intercept local modifications yet
# An idea could be to use ASan on the verified application, along with https://github.com/google/sanitizers/wiki/AddressSanitizerManualPoisoning
# But currently, ASan is not usable at all, since the Checker dislikes this trick when it tries to read the memory of the app.
# We should change the checker to not read the app when verifying safty properties
# Smpi Allreduce collectives tests
! output sort
-p Test allreduce with papi events activated - needs papi installed, simgrid compiled with it, and sudo or sudo sh -c "echo 0 > /proc/sys/kernel/perf_event_paranoid"
+p Test allreduce with papi events activated - needs papi installed, SimGrid compiled with it, and sudo or sudo sh -c "echo 0 > /proc/sys/kernel/perf_event_paranoid"
$ ${bindir:=.}/../../../smpi_script/bin/smpirun -map -hostfile ../hostfile_coll -platform ${platfdir:=.}/small_platform.xml -np 16 -trace --log=xbt_cfg.thres:critical ${bindir:=.}/coll-allreduce --log=smpi_config.thres:warning --log=smpi_coll.thres:error --log=smpi_mpi.thres:error --log=smpi_pmpi.thres:error --cfg=smpi/papi-events:default:PAPI_L1_TCM:PAPI_TOT_CYC
> [0.000000] [smpi/INFO] [rank 0] -> Tremblay
> [0.000000] [smpi/INFO] [rank 1] -> Tremblay
src/kernel/context/ContextUnix.cpp)
endif()
-### Simgrid Lib sources
+### SimGrid Lib sources
set(simgrid_sources
${S4U_SRC}
${SIMGRID_SRC}
# NOTE: Do *not* introduce parameters to "make it work" here.
# Things should "just work" with default parameters!
- # Users should not have to tinker to get starpu working on top of simgrid, that is precisely why we have this CI
+ # Users should not have to tinker to get starpu working on top of SimGrid, that is precisely why we have this CI
if [ $i = master ]; then
# On master, fail if we use deprecated functions, so that StarPU people know they have to stop using them, fix it, and thus make CI happy again
prefix=getcwd()+"/install"
#Add the condition testing to run tests and includes PyYaml
conditions.add("testing")
-conditions.add("simulation") #to include simgrid compilation
+conditions.add("simulation") #to include SimGrid compilation
#List the module the this rcfile will build
modules = ['spred',]
#example of the potentialities of the python syntax in this file
#! /usr/bin/env python3
-# The goal is to introduce random failures in a simulation, to test simgrid under extreme conditions.
+# The goal is to introduce random failures in a simulation, to test SimGrid under extreme conditions.
#
# It is made of several components.
#
# Kill the link #0 after 42 seconds (using a kernel::Timer)
#
# * a python script: tools/simgrid-monkey (this file)
-# * It takes a regular simgrid simulation as a parameter, use the cmonkey plugin to get the information about it,
+# * It takes a regular SimGrid simulation as a parameter, use the cmonkey plugin to get the information about it,
# and then restart many runs, with one resource being turn_off() + turn_on() in each run.
# * Each resource gets killed between each timestamps, and on each timestamp.
# * So the amount of simulations is: 1 + (host_c+link_c) * timestamps * 2
#print(f"hosts:{host_count} links:{link_count} timestamps:{' '.join(([str(i) for i in timestamps]))}")
return (host_count, link_count, timestamps)
-parser = argparse.ArgumentParser(description='Run a simgrid simulation, and turn off/on resources at random.')
+parser = argparse.ArgumentParser(description='Run a SimGrid simulation, and turn off/on resources at random.')
parser.add_argument('--valgrind', help="Run the simulations in valgrind")
parser.add_argument('command', nargs='*')
args = parser.parse_args()
'''
This script is intended to convert SMPI time independent traces (TIT) from the
-old format (simgrid version <= 3.19) to the new format.
+old format (SimGrid version <= 3.19) to the new format.
On the previous format each MPI_wait calls were associated to the last ISend of
IRecv call arbitrarily.
This new that includes tags field that links MPI_wait calls to the
MPI_ISend or MPI_IRecv associated to this wait.
-This script reproduce the old behavior of simgrid because information are
+This script reproduce the old behavior of SimGrid because information are
missing to add the tags properly. It also lower case all the mpi calls.
It takes in input (as argument or in stdin) the trace list file that is only a
eval 'exec perl -S $0 ${1+"$@"}'
if $running_under_some_shell;
-# This script updates the simgrid XML file passed as argument (modification in place)
+# This script updates the SimGrid XML file passed as argument (modification in place)
# It is built to do the conversion incrementally.
# Copyright (c) 2006-2023. The SimGrid Team.
=head1 NAME
-simgrid_update_xml - updates simgrid XML files to latest version
+simgrid_update_xml - updates SimGrid XML files to latest version
=head1 SYNOPSIS
=head1 DESCRIPTION
-simgrid_update_xml updates the simgrid XML file passed as argument. The file
+simgrid_update_xml updates the SimGrid XML file passed as argument. The file
is modified in place, without any kind of backup. You may want to save a copy
before running the script.
