starpu-max/doc/doxygen/chapters/101_building.doxy

/*
 * This file is part of the StarPU Handbook.
 * Copyright (C) 2009--2011  Universit@'e de Bordeaux
 * Copyright (C) 2010, 2011, 2012, 2013, 2014, 2016  CNRS
 * Copyright (C) 2011, 2012 INRIA
 * See the file version.doxy for copying conditions.
 */

/*! \page BuildingAndInstallingStarPU Building and Installing StarPU

\section InstallingABinaryPackage Installing a Binary Package

One of the StarPU developers being a Debian Developer, the packages
are well integrated and very uptodate. To see which packages are
available, simply type:

\verbatim
$ apt-cache search starpu
\endverbatim

To install what you need, type for example:

\verbatim
$ sudo apt-get install libstarpu-1.3 libstarpu-dev
\endverbatim

\section InstallingFromSource Installing from Source

StarPU can be built and installed by the standard means of the GNU
autotools. The following chapter is intended to briefly remind how these tools
can be used to install StarPU.

\subsection OptionalDependencies Optional Dependencies

The <c>hwloc</c> (http://www.open-mpi.org/software/hwloc) topology
discovery library is not mandatory to use StarPU but strongly
recommended.  It allows for topology aware scheduling, which improves
performance.  <c>libhwloc</c> is available in major free operating system
distributions, and for most operating systems.

If <c>libhwloc</c> is not available on your system, the option
\ref without-hwloc "--without-hwloc" should be explicitely given when calling the
<c>configure</c> script. If <c>libhwloc</c> is installed in a standard
location, no option is required, it will be detected automatically,
otherwise \ref with-hwloc "--with-hwloc=<directory>" should be used to specify its
location.

\subsection GettingSources Getting Sources

StarPU's sources can be obtained from the download page of
the StarPU website (http://starpu.gforge.inria.fr/files/).

All releases and the development tree of StarPU are freely available
on INRIA's gforge under the LGPL license. Some releases are available
under the BSD license.

The latest release can be downloaded from the INRIA's gforge (http://gforge.inria.fr/frs/?group_id=1570) or
directly from the StarPU download page (http://starpu.gforge.inria.fr/files/).

The latest nightly snapshot can be downloaded from the StarPU gforge website (http://starpu.gforge.inria.fr/testing/).

\verbatim
$ wget http://starpu.gforge.inria.fr/testing/starpu-nightly-latest.tar.gz
\endverbatim

And finally, current development version is also accessible via svn.
It should be used only if you need the very latest changes (i.e. less
than a day!). Note that the client side of the software Subversion can
be obtained from http://subversion.tigris.org. If you
are running on Windows, you will probably prefer to use TortoiseSVN (http://tortoisesvn.tigris.org/).

\verbatim
$ svn checkout svn://scm.gforge.inria.fr/svn/starpu/trunk StarPU
\endverbatim

\subsection ConfiguringStarPU Configuring StarPU

Running <c>autogen.sh</c> is not necessary when using the tarball
releases of StarPU.  If you are using the source code from the svn
repository, you first need to generate the configure scripts and the
Makefiles. This requires the availability of <c>autoconf</c> and
<c>automake</c> >= 2.60.

\verbatim
$ ./autogen.sh
\endverbatim

You then need to configure StarPU. Details about options that are
useful to give to <c>./configure</c> are given in \ref CompilationConfiguration.

\verbatim
$ ./configure
\endverbatim

If <c>configure</c> does not detect some software or produces errors, please
make sure to post the contents of the file <c>config.log</c> when
reporting the issue.

By default, the files produced during the compilation are placed in
the source directory. As the compilation generates a lot of files, it
is advised to put them all in a separate directory. It is then
easier to cleanup, and this allows to compile several configurations
out of the same source tree. For that, simply enter the directory
where you want the compilation to produce its files, and invoke the
<c>configure</c> script located in the StarPU source directory.

\verbatim
$ mkdir build
$ cd build
$ ../configure
\endverbatim

By default, StarPU will be installed in <c>/usr/local/bin</c>,
<c>/usr/local/lib</c>, etc. You can specify an installation prefix
other than <c>/usr/local</c> using the option <c>--prefix</c>, for
instance:

\verbatim
$ ../configure --prefix=$HOME/starpu
\endverbatim

\subsection BuildingStarPU Building StarPU

\verbatim
$ make
\endverbatim

Once everything is built, you may want to test the result. An
extensive set of regression tests is provided with StarPU. Running the
tests is done by calling <c>make check</c>. These tests are run every night
and the result from the main profile is publicly available (http://starpu.gforge.inria.fr/testing/).

\verbatim
$ make check
\endverbatim

\subsection InstallingStarPU Installing StarPU

In order to install StarPU at the location that was specified during
configuration:

\verbatim
$ make install
\endverbatim

Libtool interface versioning information are included in
libraries names (<c>libstarpu-1.3.so</c>, <c>libstarpumpi-1.3.so</c> and
<c>libstarpufft-1.3.so</c>).

\section SettingUpYourOwnCode Setting up Your Own Code

\subsection SettingFlagsForCompilingLinkingAndRunningApplications Setting Flags for Compiling, Linking and Running Applications

StarPU provides a <c>pkg-config</c> executable to obtain relevant compiler
and linker flags. As compiling and linking an application against
StarPU may require to use specific flags or libraries (for instance
<c>CUDA</c> or <c>libspe2</c>).

If StarPU was not installed at some standard location, the path of StarPU's
library must be specified in the environment variable <c>PKG_CONFIG_PATH</c> so
that <c>pkg-config</c> can find it. For example if StarPU was installed in
<c>$STARPU_PATH</c>:

\verbatim
$ PKG_CONFIG_PATH=$PKG_CONFIG_PATH:$STARPU_PATH/lib/pkgconfig
\endverbatim

The flags required to compile or link against StarPU are then
accessible with the following commands:

\verbatim
$ pkg-config --cflags starpu-1.3  # options for the compiler
$ pkg-config --libs starpu-1.3    # options for the linker
\endverbatim

Note that it is still possible to use the API provided in the version
1.0 of StarPU by calling <c>pkg-config</c> with the <c>starpu-1.0</c> package.
Similar packages are provided for <c>starpumpi-1.0</c> and <c>starpufft-1.0</c>.
It is also possible to use the API provided in the version
0.9 of StarPU by calling <c>pkg-config</c> with the <c>libstarpu</c> package.
Similar packages are provided for <c>libstarpumpi</c> and <c>libstarpufft</c>.

Make sure that <c>pkg-config --libs starpu-1.3</c> actually produces some output
before going further: <c>PKG_CONFIG_PATH</c> has to point to the place where
<c>starpu-1.3.pc</c> was installed during <c>make install</c>.

Also pass the option <c>--static</c> if the application is to be
linked statically.

It is also necessary to set the environment variable <c>LD_LIBRARY_PATH</c> to
locate dynamic libraries at runtime.

\verbatim
$ LD_LIBRARY_PATH=$STARPU_PATH/lib:$LD_LIBRARY_PATH
\endverbatim

When using a Makefile, the following lines can be added to set the
options for the compiler and the linker:

\verbatim
CFLAGS          +=      $$(pkg-config --cflags starpu-1.3)
LDFLAGS         +=      $$(pkg-config --libs starpu-1.3)
\endverbatim

\subsection RunningABasicStarPUApplication Running a Basic StarPU Application

Basic examples using StarPU are built in the directory
<c>examples/basic_examples/</c> (and installed in
<c>$STARPU_PATH/lib/starpu/examples/</c>). You can for example run the example
<c>vector_scal</c>.

\verbatim
$ ./examples/basic_examples/vector_scal
BEFORE: First element was 1.000000
AFTER: First element is 3.140000
\endverbatim

When StarPU is used for the first time, the directory
<c>$STARPU_HOME/.starpu/</c> is created, performance models will be stored in
that directory (\ref STARPU_HOME).

Please note that buses are benchmarked when StarPU is launched for the
first time. This may take a few minutes, or less if <c>libhwloc</c> is
installed. This step is done only once per user and per machine.

\subsection RunningABasicStarPUApplicationOnMicrosoft Running a Basic StarPU Application on Microsoft Visual C

Batch files are provided to run StarPU applications under Microsoft
Visual C. They are installed in <c>$STARPU_PATH/bin/msvc</c>.

To execute a StarPU application, you first need to set the environment
variable \ref STARPU_PATH.

\verbatim
c:\....> cd c:\cygwin\home\ci\starpu\
c:\....> set STARPU_PATH=c:\cygwin\home\ci\starpu\
c:\....> cd bin\msvc
c:\....> starpu_open.bat starpu_simple.c
\endverbatim

The batch script will run Microsoft Visual C with a basic project file
to run the given application.

The batch script <c>starpu_clean.bat</c> can be used to delete all
compilation generated files.

The batch script <c>starpu_exec.bat</c> can be used to compile and execute a
StarPU application from the command prompt.

\verbatim
c:\....> cd c:\cygwin\home\ci\starpu\
c:\....> set STARPU_PATH=c:\cygwin\home\ci\starpu\
c:\....> cd bin\msvc
c:\....> starpu_exec.bat ..\..\..\..\examples\basic_examples\hello_world.c
\endverbatim

\verbatim
MSVC StarPU Execution
...
/out:hello_world.exe
...
Hello world (params = {1, 2.00000})
Callback function got argument 0000042
c:\....>
\endverbatim

\subsection KernelThreadsStartedByStarPU Kernel Threads Started by StarPU

StarPU automatically binds one thread per CPU core. It does not use
SMT/hyperthreading because kernels are usually already optimized for using a
full core, and using hyperthreading would make kernel calibration rather random.

Since driving GPUs is a CPU-consuming task, StarPU dedicates one core
per GPU.

While StarPU tasks are executing, the application is not supposed to do
computations in the threads it starts itself, tasks should be used instead.

TODO: add a StarPU function to bind an application thread (e.g. the main thread)
to a dedicated core (and thus disable the corresponding StarPU CPU worker).

\subsection EnablingOpenCL Enabling OpenCL

When both CUDA and OpenCL drivers are enabled, StarPU will launch an
OpenCL worker for NVIDIA GPUs only if CUDA is not already running on them.
This design choice was necessary as OpenCL and CUDA can not run at the
same time on the same NVIDIA GPU, as there is currently no interoperability
between them.

To enable OpenCL, you need either to disable CUDA when configuring StarPU:

\verbatim
$ ./configure --disable-cuda
\endverbatim

or when running applications:

\verbatim
$ STARPU_NCUDA=0 ./application
\endverbatim

OpenCL will automatically be started on any device not yet used by
CUDA. So on a machine running 4 GPUS, it is therefore possible to
enable CUDA on 2 devices, and OpenCL on the 2 other devices by doing
so:

\verbatim
$ STARPU_NCUDA=2 ./application
\endverbatim

\section BenchmarkingStarPU Benchmarking StarPU

Some interesting benchmarks are installed among examples in
<c>$STARPU_PATH/lib/starpu/examples/</c>. Make sure to try various
schedulers, for instance <c>STARPU_SCHED=dmda</c>.

\subsection TaskSizeOverhead Task Size Overhead

This benchmark gives a glimpse into how long a task should be (in µs) for StarPU overhead
to be low enough to keep efficiency.  Running
<c>tasks_size_overhead.sh</c> generates a plot
of the speedup of tasks of various sizes, depending on the number of CPUs being
used.

\image html tasks_size_overhead.png
\image latex tasks_size_overhead.eps "" width=\textwidth

\subsection DataTransferLatency Data Transfer Latency

<c>local_pingpong</c> performs a ping-pong between the first two CUDA nodes, and
prints the measured latency.

\subsection MatrixMatrixMultiplication Matrix-Matrix Multiplication

<c>sgemm</c> and <c>dgemm</c> perform a blocked matrix-matrix
multiplication using BLAS and cuBLAS. They output the obtained GFlops.

\subsection CholeskyFactorization Cholesky Factorization

<c>cholesky_*</c> perform a Cholesky factorization (single precision). They use different dependency primitives.

\subsection LUFactorization LU Factorization

<c>lu_*</c> perform an LU factorization. They use different dependency primitives.

\subsection SimulatedBenchmarks Simulated benchmarks

It can also be convenient to try simulated benchmarks, if you want to give a try
at CPU-GPU scheduling without actually having a GPU at hand. This can be done by
using the simgrid version of StarPU: first install the simgrid simulator from
http://simgrid.gforge.inria.fr/ (we tested with simgrid 3.11, 3.12 and 3.13, other versions
may have compatibility issues), then configure StarPU with \ref enable-simgrid
"--enable-simgrid" and rebuild and install it, and then you can simulate the performance for a
few virtualized systems shipped along StarPU: attila, mirage, idgraf, and sirocco.

For instance:

\verbatim
$ export STARPU_PERF_MODEL_DIR=$STARPU_PATH/share/starpu/perfmodels/sampling
$ export STARPU_HOSTNAME=attila
$ $STARPU_PATH/lib/starpu/examples/cholesky_implicit -size $((960*20)) -nblocks 20
\endverbatim

Will show the performance of the cholesky factorization with the attila
system. It will be interesting to try with different matrix sizes and
schedulers.

Performance models are available for cholesky_*, lu_*, *gemm, with block sizes
320, 640, or 960 (plus 1440 for sirocco), and for stencil with block size 128x128x128, 192x192x192, and
256x256x256.

*/