porting work to Maxeler DFE

Cédric Augonnet c25ff2e248 Various bug fixes/cleanup in the parallel heft scheduling strategy 14 år sedan
build-aux 6cefcf8c2b revert r1973 (it seems like build-aux is a 'standard' name) 15 år sedan
doc 4752e60676 make it clear that performance models are per size 14 år sedan
examples de0facd291 examples: distribute opencl kernel source 14 år sedan
include 7b59581779 include/: when compiling with visual studio, do not include pthread.h, do not define functions using pthread types, and define pthread variables as void * (followup to #3304) 14 år sedan
m4 f7bad4ed84 Add a pkg.m4 file for autogen.sh to successfully generate the configure file on machines which have a crappy version of autotools and pkgconfig 15 år sedan
mpi ce3c03f914 fix starpu_set_profiling_id call 14 år sedan
src c25ff2e248 Various bug fixes/cleanup in the parallel heft scheduling strategy 14 år sedan
tests 5ccdb011e6 Fix minor warnings 14 år sedan
tools 20cb8f2fef gdbinit: new function to print data's post sync tasks 14 år sedan
AUTHORS 46c026a025 Add Nicolas Collin and François Tessier in the authors 15 år sedan
COPYING.LGPL fc22dad676 create a trunk/, branches/ and a tags/ directory 16 år sedan
ChangeLog e89466adaa feed changelog 14 år sedan
Makefile.am e55f7e46a2 Introduce the notion of task bundles. A task bundle is a set of tasks that the 14 år sedan
README 3e72ea4fa3 harmonize windows build information between README and README.dev 14 år sedan
README.dev 3e72ea4fa3 harmonize windows build information between README and README.dev 14 år sedan
acinclude.m4 788110e7fc fix SYNC_VAL_COMPARE_AND_SWAP name confusion 15 år sedan
autogen.sh d49977bfb2 On Mac OS X, we should look for glibtool, not for libtool 14 år sedan
configure.ac 4143640e28 look for cuda in /usr and /opt 14 år sedan
libstarpu.pc.in fdcffc1dcd The hwloc library is used in the public API so we need hwloc.h in case hwloc is 15 år sedan

README

++=================++
|| I. Introduction ||
++=================++

+---------------------
| I.a. What is StarPU?

StarPU is a runtime system that offers support for heterogeneous multicore
machines. While many efforts are devoted to design efficient computation kernels
for those architectures (e.g. to implement BLAS kernels on GPUs or on Cell's
SPUs), StarPU not only takes care of offloading such kernels (and implementing
data coherency across the machine), but it also makes sure the kernels are
executed as efficiently as possible.

+------------------------
| I.b. What StarPU is not

StarPU is not a new language, and it does not extends existing languages either.
StarPU does not help to write computation kernels.

+---------------------------------
| I.c. (How) Could StarPU help me?

While StarPU will not make it easier to write computation kernels, it does
simplify their actual offloading as StarPU handle most low level aspects
transparently.

Obviously, it is crucial to have efficient kernels, but it must be noted that
the way those kernels are mapped and scheduled onto the computational resources
also affect the overall performance to a great extent.

StarPU is especially helpful when considering multiple heterogeneous processing
resources: statically mapping and synchronizing tasks in such a heterogeneous
environment is already very difficult, making it in a portable way is virtually
impossible. On the other hand, the scheduling capabilities of StarPU makes it
possible to easily exploit all processors at the same time while taking
advantage of their specificities in a portable fashion.

++==================++
|| II. Requirements ||
++==================++

* make
* gcc (version >= 4.1)
* if CUDA support is enabled
* CUDA (version >= 2.2)
* CUBLAS (version >= 2.2)
* if OpenCL support is enabled
* AMD SDK >= 2.3 if AMD driver is used
* CUDA >= 3.2 if NVIDIA driver is used
* extra requirements for the svn version (we usually use the Debian testing
versions)
* autoconf (version >= 2.60)
* automake
* makeinfo

* Remark: It is strongly recommanded that you also install the hwloc library
before installing StarPU. This permits StarPU to actually map the processing
units according to the machine topology. For more details on hwloc, see
http://www.open-mpi.org/projects/hwloc/ .

++=====================++
|| III. Getting StarPU ||
++=====================++

StarPU is available on https://gforge.inria.fr/projects/starpu/.

The project's SVN repository can be checked out through anonymous
access with the following command(s).

$ svn checkout svn://scm.gforge.inria.fr/svn/starpu/trunk
$ svn checkout --username anonsvn https://scm.gforge.inria.fr/svn/starpu/trunk

The password is 'anonsvn'

++=============================++
|| IV. Building and Installing ||
++=============================++

+---------------------------
| IV.a. For svn version only

$ ./autogen.sh

+-----------------------
| IV.b. For all versions

$ ./configure
$ make
$ make install

+---------------------
| IV.c. Windows build:

StarPU can be built using MinGW or Cygwin. To avoid the cygwin dependency,
we provide MinGW-built binaries. The build process produces libstarpu.dll,
libstarpu.def, and libstarpu.lib, which should be enough to use it from e.g.
Microsoft Visual Studio.

Update the video drivers to the latest stable release available for your
hardware. Old ATI drivers (< 2.3) contain bugs that cause OpenCL support in
StarPU to hang or exhibit incorrect behaviour.

For details on the Windows build process, see the README.dev file in the
subversion tree.

++===========++
|| V. Trying ||
++===========++

Some examples ready to run are installed into $prefix/lib/starpu/{examples,mpi}

++=============++
|| VI. Upgrade ||
++=============++

To upgrade your source code from older version (there were quite a few
renamings), use the tools/rename.sh script

++==============++
|| VII. Contact ||
++==============++

For any questions regarding StarPU, please contact the starpu-devel
mailing-list at starpu-devel@lists.gforge.inria.fr .