Commit 5ff92d6a authored by Ludovic Courtès's avatar Ludovic Courtès

index.html: Features: Mention the GCC plug-in.

git-svn-id: svn+ssh://scm.gforge.inria.fr/svn/starpu/website@7565 176f6dd6-97d6-42f4-bd05-d3db9ad07c7a
parent 5141b6e1
......@@ -164,10 +164,22 @@ will automatically determine which MPI node should execute which task, and
<b>generate all required MPI communications</b> accordingly.
</p>
<h4>Extensions to the C Language</h4>
<p>
StarPU comes with a GCC plug-in
that <a href="starpu.html#C-Extensions">extends the C programming
language</a> with pragmas and attributes that make it easy
to <b>annotate a sequential C program to turn it into a parallel
StarPU program</b>.
</p>
<h4>All in all</h4>
<p>
All that means that the following sequential source code of a tiled version of the classical Cholesky factorization algorithm
using BLAS:
All that means that, with the help
of <a href="starpu.html#C-Extensions">StarPU's extensions to the C
language</a>, the following sequential source code of a tiled version of
the classical Cholesky factorization algorithm using BLAS is also valid
StarPU code, possibly running on several processing units:
</p>
<tt><pre>
......@@ -182,12 +194,6 @@ for (k = 0; k < tiles; k++) {
gemm(A[m,k], A[n,k], A[m,n])
}</pre></tt>
<p>
by redefining the portf, trsm, syrk gemm macros into submitting
StarPU tasks is also a task-parallel version, and given a data distribution
over MPI nodes, it is even a distributed version !
</p>
<h4>Supported Architectures</h4>
<ul>
<li>SMP/Multicore Processors (x86, PPC, ...) </li>
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment