/*
* This file is part of the StarPU Handbook.
* Copyright (C) 2009--2011 Universit@'e de Bordeaux 1
* Copyright (C) 2010, 2011, 2012, 2013 Centre National de la Recherche Scientifique
* Copyright (C) 2011, 2012 Institut National de Recherche en Informatique et Automatique
* See the file version.doxy for copying conditions.
*/
/*! \page performanceFeedback Performance Feedback
\section Using_the_Temanejo_task_debugger Using the Temanejo task debugger
StarPU can connect to Temanejo (see
http://www.hlrs.de/temanejo), to permit
nice visual task debugging. To do so, build Temanejo's libayudame.so,
install Ayudame.h to e.g. /usr/local/include, apply the
tools/patch-ayudame to it to fix C build, re-./configure, make
sure that it found it, rebuild StarPU. Run the Temanejo GUI, give it the path
to your application, any options you want to pass it, the path to libayudame.so.
Make sure to specify at least the same number of CPUs in the dialog box as your
machine has, otherwise an error will happen during execution. Future versions
of Temanejo should be able to tell StarPU the number of CPUs to use.
Tag numbers have to be below 4000000000000000000ULL to be usable for
Temanejo (so as to distinguish them from tasks).
\section On-line_performance_feedback On-line performance feedback
\subsection Enabling_on-line_performance_monitoring Enabling on-line performance monitoring
In order to enable online performance monitoring, the application can call
starpu_profiling_status_set(STARPU_PROFILING_ENABLE). It is possible to
detect whether monitoring is already enabled or not by calling
starpu_profiling_status_get(). Enabling monitoring also reinitialize all
previously collected feedback. The STARPU_PROFILING environment variable
can also be set to 1 to achieve the same effect.
Likewise, performance monitoring is stopped by calling
starpu_profiling_status_set(STARPU_PROFILING_DISABLE). Note that this
does not reset the performance counters so that the application may consult
them later on.
More details about the performance monitoring API are available in section
@ref{Profiling API}.
\subsection Per-Task_feedback Per-task feedback
If profiling is enabled, a pointer to a struct starpu_profiling_task_info
is put in the .profiling_info field of the starpu_task
structure when a task terminates.
This structure is automatically destroyed when the task structure is destroyed,
either automatically or by calling starpu_task_destroy().
The struct starpu_profiling_task_info indicates the date when the
task was submitted (submit_time), started (start_time), and
terminated (end_time), relative to the initialization of
StarPU with starpu_init(). It also specifies the identifier of the worker
that has executed the task (workerid).
These date are stored as timespec structures which the user may convert
into micro-seconds using the starpu_timing_timespec_to_us() helper
function.
It it worth noting that the application may directly access this structure from
the callback executed at the end of the task. The starpu_task structure
associated to the callback currently being executed is indeed accessible with
the starpu_task_get_current() function.
\subsection Per-codelet_feedback Per-codelet feedback
The per_worker_stats field of the struct starpu_codelet structure is
an array of counters. The i-th entry of the array is incremented every time a
task implementing the codelet is executed on the i-th worker.
This array is not reinitialized when profiling is enabled or disabled.
\subsection Per-worker_feedback Per-worker feedback
The second argument returned by the starpu_profiling_worker_get_info()
function is a struct starpu_profiling_worker_info that gives
statistics about the specified worker. This structure specifies when StarPU
started collecting profiling information for that worker (start_time),
the duration of the profiling measurement interval (total_time), the
time spent executing kernels (executing_time), the time spent sleeping
because there is no task to execute at all (sleeping_time), and the
number of tasks that were executed while profiling was enabled.
These values give an estimation of the proportion of time spent do real work,
and the time spent either sleeping because there are not enough executable
tasks or simply wasted in pure StarPU overhead.
Calling starpu_profiling_worker_get_info() resets the profiling
information associated to a worker.
When an FxT trace is generated (see \ref Generating_traces_with_FxT), it is also
possible to use the starpu_workers_activity script (see \ref Monitoring_activity) to
generate a graphic showing the evolution of these values during the time, for
the different workers.
\subsection Bus-related_feedback Bus-related feedback
TODO: ajouter STARPU_BUS_STATS
\internal
how to enable/disable performance monitoring
what kind of information do we get ?
\endinternal
The bus speed measured by StarPU can be displayed by using the
starpu_machine_display tool, for instance:
\verbatim
StarPU has found:
3 CUDA devices
CUDA 0 (Tesla C2050 02:00.0)
CUDA 1 (Tesla C2050 03:00.0)
CUDA 2 (Tesla C2050 84:00.0)
from to RAM to CUDA 0 to CUDA 1 to CUDA 2
RAM 0.000000 5176.530428 5176.492994 5191.710722
CUDA 0 4523.732446 0.000000 2414.074751 2417.379201
CUDA 1 4523.718152 2414.078822 0.000000 2417.375119
CUDA 2 4534.229519 2417.069025 2417.060863 0.000000
\endverbatim
\subsection StarPU-Top_interface StarPU-Top interface
StarPU-Top is an interface which remotely displays the on-line state of a StarPU
application and permits the user to change parameters on the fly.
Variables to be monitored can be registered by calling the
starpu_top_add_data_boolean(), starpu_top_add_data_integer(),
starpu_top_add_data_float() functions, e.g.:
\code{.c}
starpu_top_data *data = starpu_top_add_data_integer("mynum", 0, 100, 1);
\endcode
The application should then call starpu_top_init_and_wait() to give its name
and wait for StarPU-Top to get a start request from the user. The name is used
by StarPU-Top to quickly reload a previously-saved layout of parameter display.
\code{.c}
starpu_top_init_and_wait("the application");
\endcode
The new values can then be provided thanks to
starpu_top_update_data_boolean(), starpu_top_update_data_integer(),
starpu_top_update_data_float(), e.g.:
\code{.c}
starpu_top_update_data_integer(data, mynum);
\endcode
Updateable parameters can be registered thanks to starpu_top_register_parameter_boolean(), starpu_top_register_parameter_integer(), starpu_top_register_parameter_float(), e.g.:
\code{.c}
float alpha;
starpu_top_register_parameter_float("alpha", &alpha, 0, 10, modif_hook);
\endcode
modif_hook is a function which will be called when the parameter is being modified, it can for instance print the new value:
\code{.c}
void modif_hook(struct starpu_top_param *d) {
fprintf(stderr,"%s has been modified: %f\n", d->name, alpha);
}
\endcode
Task schedulers should notify StarPU-Top when it has decided when a task will be
scheduled, so that it can show it in its Gantt chart, for instance:
\code{.c}
starpu_top_task_prevision(task, workerid, begin, end);
\endcode
Starting StarPU-Top (StarPU-Top is started via the binary
starpu_top.) and the application can be done two ways:
- The application is started by hand on some machine (and thus already
waiting for the start event). In the Preference dialog of StarPU-Top, the SSH
checkbox should be unchecked, and the hostname and port (default is 2011) on
which the application is already running should be specified. Clicking on the
connection button will thus connect to the already-running application.
- StarPU-Top is started first, and clicking on the connection button will
start the application itself (possibly on a remote machine). The SSH checkbox
should be checked, and a command line provided, e.g.:
\verbatim
$ ssh myserver STARPU_SCHED=dmda ./application
\endverbatim
If port 2011 of the remote machine can not be accessed directly, an ssh port bridge should be added:
\verbatim
$ ssh -L 2011:localhost:2011 myserver STARPU_SCHED=dmda ./application
\endverbatim
and "localhost" should be used as IP Address to connect to.
\section Off-line_performance_feedback Off-line performance feedback
\subsection Generating_traces_with_FxT Generating traces with FxT
StarPU can use the FxT library (see
https://savannah.nongnu.org/projects/fkt/) to generate traces
with a limited runtime overhead.
You can either get a tarball:
\verbatim
$ wget http://download.savannah.gnu.org/releases/fkt/fxt-0.2.11.tar.gz
\endverbatim
or use the FxT library from CVS (autotools are required):
\verbatim
$ cvs -d :pserver:anonymous\@cvs.sv.gnu.org:/sources/fkt co FxT
$ ./bootstrap
\endverbatim
Compiling and installing the FxT library in the $FXTDIR path is
done following the standard procedure:
\verbatim
$ ./configure --prefix=$FXTDIR
$ make
$ make install
\endverbatim
In order to have StarPU to generate traces, StarPU should be configured with
the --with-fxt option:
\verbatim
$ ./configure --with-fxt=$FXTDIR
\endverbatim
Or you can simply point the PKG_CONFIG_PATH to
$FXTDIR/lib/pkgconfig and pass --with-fxt to ./configure
When FxT is enabled, a trace is generated when StarPU is terminated by calling
starpu_shutdown()). The trace is a binary file whose name has the form
prof_file_XXX_YYY where XXX is the user name, and
YYY is the pid of the process that used StarPU. This file is saved in the
/tmp/ directory by default, or by the directory specified by
the STARPU_FXT_PREFIX environment variable.
\subsection Creating_a_Gantt_Diagram Creating a Gantt Diagram
When the FxT trace file filename has been generated, it is possible to
generate a trace in the Paje format by calling:
\verbatim
$ starpu_fxt_tool -i filename
\endverbatim
Or alternatively, setting the STARPU_GENERATE_TRACE environment variable
to 1 before application execution will make StarPU do it automatically at
application shutdown.
This will create a paje.trace file in the current directory that
can be inspected with the ViTE trace
visualizing open-source tool. It is possible to open the
paje.trace file with ViTE by using the following command:
\verbatim
$ vite paje.trace
\endverbatim
To get names of tasks instead of "unknown", fill the optional name field
of the codelets, or use a performance model for them.
In the MPI execution case, collect the trace files from the MPI nodes, and
specify them all on the starpu_fxt_tool command, for instance:
\verbatim
$ starpu_fxt_tool -i filename1 -i filename2
\endverbatim
By default, all tasks are displayed using a green color. To display tasks with
varying colors, pass option -c to starpu_fxt_tool.
Traces can also be inspected by hand by using the fxt_print tool, for instance:
\verbatim
$ fxt_print -o -f filename
\endverbatim
Timings are in nanoseconds (while timings as seen in vite are in milliseconds).
\subsection Creating_a_DAG_with_graphviz Creating a DAG with graphviz
When the FxT trace file filename has been generated, it is possible to
generate a task graph in the DOT format by calling:
\verbatim
$ starpu_fxt_tool -i filename
\endverbatim
This will create a dag.dot file in the current directory. This file is a
task graph described using the DOT language. It is possible to get a
graphical output of the graph by using the graphviz library:
\verbatim
$ dot -Tpdf dag.dot -o output.pdf
\endverbatim
\subsection Monitoring_activity Monitoring activity
When the FxT trace file filename has been generated, it is possible to
generate an activity trace by calling:
\verbatim
$ starpu_fxt_tool -i filename
\endverbatim
This will create an activity.data file in the current
directory. A profile of the application showing the activity of StarPU
during the execution of the program can be generated:
\verbatim
$ starpu_workers_activity activity.data
\endverbatim
This will create a file named activity.eps in the current directory.
This picture is composed of two parts.
The first part shows the activity of the different workers. The green sections
indicate which proportion of the time was spent executed kernels on the
processing unit. The red sections indicate the proportion of time spent in
StartPU: an important overhead may indicate that the granularity may be too
low, and that bigger tasks may be appropriate to use the processing unit more
efficiently. The black sections indicate that the processing unit was blocked
because there was no task to process: this may indicate a lack of parallelism
which may be alleviated by creating more tasks when it is possible.
The second part of the activity.eps picture is a graph showing the
evolution of the number of tasks available in the system during the execution.
Ready tasks are shown in black, and tasks that are submitted but not
schedulable yet are shown in grey.
\section Performance_of_codelets Performance of codelets
The performance model of codelets (see \ref Performance_model_example) can be examined by using the
starpu_perfmodel_display tool:
\verbatim
$ starpu_perfmodel_display -l
file:
file:
file:
file:
file:
\endverbatim
Here, the codelets of the lu example are available. We can examine the
performance of the 22 kernel (in micro-seconds), which is history-based:
\verbatim
$ starpu_perfmodel_display -s starpu_slu_lu_model_22
performance model for cpu
# hash size mean dev n
57618ab0 19660800 2.851069e+05 1.829369e+04 109
performance model for cuda_0
# hash size mean dev n
57618ab0 19660800 1.164144e+04 1.556094e+01 315
performance model for cuda_1
# hash size mean dev n
57618ab0 19660800 1.164271e+04 1.330628e+01 360
performance model for cuda_2
# hash size mean dev n
57618ab0 19660800 1.166730e+04 3.390395e+02 456
\endverbatim
We can see that for the given size, over a sample of a few hundreds of
execution, the GPUs are about 20 times faster than the CPUs (numbers are in
us). The standard deviation is extremely low for the GPUs, and less than 10% for
CPUs.
This tool can also be used for regression-based performance models. It will then
display the regression formula, and in the case of non-linear regression, the
same performance log as for history-based performance models:
\verbatim
$ starpu_perfmodel_display -s non_linear_memset_regression_based
performance model for cpu_impl_0
Regression : #sample = 1400
Linear: y = alpha size ^ beta
alpha = 1.335973e-03
beta = 8.024020e-01
Non-Linear: y = a size ^b + c
a = 5.429195e-04
b = 8.654899e-01
c = 9.009313e-01
# hash size mean stddev n
a3d3725e 4096 4.763200e+00 7.650928e-01 100
870a30aa 8192 1.827970e+00 2.037181e-01 100
48e988e9 16384 2.652800e+00 1.876459e-01 100
961e65d2 32768 4.255530e+00 3.518025e-01 100
...
\endverbatim
The same can also be achieved by using StarPU's library API, see
@ref{Performance Model API} and notably the starpu_perfmodel_load_symbol()
function. The source code of the starpu_perfmodel_display tool can be a
useful example.
The starpu_perfmodel_plot tool can be used to draw performance models.
It writes a .gp file in the current directory, to be run in the
gnuplot tool, which shows the corresponding curve.
When the flops field of tasks is set, starpu_perfmodel_plot can
directly draw a GFlops curve, by simply adding the -f option:
\verbatim
$ starpu_perfmodel_display -f -s chol_model_11
\endverbatim
This will however disable displaying the regression model, for which we can not
compute GFlops.
When the FxT trace file filename has been generated, it is possible to
get a profiling of each codelet by calling:
\verbatim
$ starpu_fxt_tool -i filename
$ starpu_codelet_profile distrib.data codelet_name
\endverbatim
This will create profiling data files, and a .gp file in the current
directory, which draws the distribution of codelet time over the application
execution, according to data input size.
This is also available in the starpu_perfmodel_plot tool, by passing it
the fxt trace:
\verbatim
$ starpu_perfmodel_plot -s non_linear_memset_regression_based -i /tmp/prof_file_foo_0
\endverbatim
It will produce a .gp file which contains both the performance model
curves, and the profiling measurements.
If you have the R statistical tool installed, you can additionally use
\verbatim
$ starpu_codelet_histo_profile distrib.data
\endverbatim
Which will create one pdf file per codelet and per input size, showing a
histogram of the codelet execution time distribution.
\section Theoretical_lower_bound_on_execution_time Theoretical lower bound on execution time
StarPU can record a trace of what tasks are needed to complete the
application, and then, by using a linear system, provide a theoretical lower
bound of the execution time (i.e. with an ideal scheduling).
The computed bound is not really correct when not taking into account
dependencies, but for an application which have enough parallelism, it is very
near to the bound computed with dependencies enabled (which takes a huge lot
more time to compute), and thus provides a good-enough estimation of the ideal
execution time.
\ref Theoretical_lower_bound_on_execution_time provides an example on how to
use this.
\section Memory_feedback Memory feedback
It is possible to enable memory statistics. To do so, you need to pass the option
--enable-memory-stats when running configure. It is then
possible to call the function starpu_display_memory_stats() to
display statistics about the current data handles registered within StarPU.
Moreover, statistics will be displayed at the end of the execution on
data handles which have not been cleared out. This can be disabled by
setting the environment variable STARPU_MEMORY_STATS to 0.
For example, if you do not unregister data at the end of the complex
example, you will get something similar to:
\verbatim
$ STARPU_MEMORY_STATS=0 ./examples/interface/complex
Complex[0] = 45.00 + 12.00 i
Complex[0] = 78.00 + 78.00 i
Complex[0] = 45.00 + 12.00 i
Complex[0] = 45.00 + 12.00 i
\endverbatim
\verbatim
$ STARPU_MEMORY_STATS=1 ./examples/interface/complex
Complex[0] = 45.00 + 12.00 i
Complex[0] = 78.00 + 78.00 i
Complex[0] = 45.00 + 12.00 i
Complex[0] = 45.00 + 12.00 i
#---------------------
Memory stats:
#-------
Data on Node #3
#-----
Data : 0x553ff40
Size : 16
#--
Data access stats
/!\ Work Underway
Node #0
Direct access : 4
Loaded (Owner) : 0
Loaded (Shared) : 0
Invalidated (was Owner) : 0
Node #3
Direct access : 0
Loaded (Owner) : 0
Loaded (Shared) : 1
Invalidated (was Owner) : 0
#-----
Data : 0x5544710
Size : 16
#--
Data access stats
/!\ Work Underway
Node #0
Direct access : 2
Loaded (Owner) : 0
Loaded (Shared) : 1
Invalidated (was Owner) : 1
Node #3
Direct access : 0
Loaded (Owner) : 1
Loaded (Shared) : 0
Invalidated (was Owner) : 0
\endverbatim
\section Data_statistics Data statistics
Different data statistics can be displayed at the end of the execution
of the application. To enable them, you need to pass the option
--enable-stats when calling configure. When calling
starpu_shutdown() various statistics will be displayed,
execution, MSI cache statistics, allocation cache statistics, and data
transfer statistics. The display can be disabled by setting the
environment variable STARPU_STATS to 0.
\verbatim
$ ./examples/cholesky/cholesky_tag
Computation took (in ms)
518.16
Synthetic GFlops : 44.21
#---------------------
MSI cache stats :
TOTAL MSI stats hit 1622 (66.23 %) miss 827 (33.77 %)
...
\endverbatim
\verbatim
$ STARPU_STATS=0 ./examples/cholesky/cholesky_tag
Computation took (in ms)
518.16
Synthetic GFlops : 44.21
\endverbatim
\internal
TODO: data transfer stats are similar to the ones displayed when
setting STARPU_BUS_STATS
\endinternal
*/