Document running the simgrid-available examples

doc/doxygen/chapters/01building.doxy

@@ -341,4 +341,29 @@ multiplication using BLAS and cuBLAS. They output the obtained GFlops.
 
 <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/ , then configure StarPU with \ref enable-simgrid "--enable-simgrid"
+and rebuild and install it, and then you can simulate the performance for a
+couple of virtualized system shipped along StarPU: attila and mirage.
+
+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
+\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, and for stencil with block size 128x128x128, 192x192x192, and
+256x256x256.
+
 */

doc/doxygen/chapters/21simgrid.doxy

@@ -121,6 +121,11 @@ case. Since during simgrid execution, the functions of the codelet are actually
 not called, one can use dummy functions such as the following to still permit
 CUDA or OpenCL execution:
 
+\section SimulationExamples Simulation examples
+
+StarPU ships a few performance models for a couple of systems: attila and
+mirage. See section \ref SimulatedBenchmarks for the details.
+
 \section Tweaking simulation
 
 The simulation can be tweaked, to be able to tune it between a very accurate