porting work to Maxeler DFE

Samuel Thibault 7a566f4749 fix memory coherency of spin_unlock: else loads/stores to memory may be done after the release hace 16 años
build-aux 5f681d3938 remove file that autoreconf can install by itself hace 16 años
doc 2d85f60494 Fix some typos in the documentation (thanks to Olivier Aumage for that patch) hace 16 años
examples 4739b7a73d forgot to include the sgemm dynamically loadable kernel hace 16 años
include c071c55eb5 Use RW-locks instead of a lock to protect the history-based models. This has 2 hace 16 años
scripts fc22dad676 create a trunk/, branches/ and a tags/ directory hace 17 años
src 7a566f4749 fix memory coherency of spin_unlock: else loads/stores to memory may be done after the release hace 16 años
tests 395d7cbd95 Include the dynamically loaded ELF code in the distribution. hace 16 años
tools cee209b7e4 Display the number of tasks available to the scheduler in the Paje trace. hace 16 años
AUTHORS fc22dad676 create a trunk/, branches/ and a tags/ directory hace 17 años
COPYING.LGPL fc22dad676 create a trunk/, branches/ and a tags/ directory hace 17 años
Makefile.am ec8baec6b1 Do not reimplement spinlocks, use pthread_spin_t instead. hace 16 años
README afbeddc8b3 proofread hace 16 años
acinclude.m4 446f18f835 test if __sync_* GCC built-in are available hace 17 años
configure.ac 5cdd7aec2f (re)implement a spinlock in case pthread_spinlock_t is not available. hace 16 años
libstarpu.pc.in fc22dad676 create a trunk/, branches/ and a tags/ directory hace 17 años

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 (eg. to implement BLAS kernels on GPUs or on Cell's
SPUs), StarPU not only takes care of offloading such kernels (and implementing
data coherency accross 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 langage, and it does not extends existing langages 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 >= 2.0)
* CUBLAS (version >= 2.0)
* extra requirements for the svn version
* autoconf (version >= 2.60)
* automake

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

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

It is also possible to access the latest svn version:
$ svn checkout svn://scm.gforge.inria.fr/svn/starpu/trunk/
or via http (DAV):
$ svn checkout https://scm.gforge.inria.fr/svn/starpu/trunk/

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

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

$ autoreconf

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

$ ./configure
$ make
$ make install

++============++
|| V. Contact ||
++============++

For any questions regarding StarPU, please contact Cédric Augonnet
(cedric.augonnet@inria.fr).