added README

MUMPS/README.md

+Description:
+============
+
+Presentation
+------------
+
+MUMPS : a parallel sparse direct solver
+
+Technical information:
+----------------------
+
+* website : http://mumps.enseeiht.fr/index.php?page=home 
+* Scientific domain : Sparse Matrix
+* Language : Fortran
+* Parallelism : MPI + OpenMP
+* GPU acceleration : No  
+* Scalability : high
+* Vectorization: high
+
+
+Compilation and simulation:
+===========================
+
+Download:
+---------
+
+Sources can be requested here: http://mumps.enseeiht.fr/index.php?page=dwnld#form 
+
+For the test, we will use a specific release. To download this release, run:
+
+```
+./download.sh
+```
+
+Compile:
+--------
+
+Compile the code using for instance:
+```
+./compile.sh occigen-bdw
+```
+
+`machines/occigen-bdw/env` contains the information for compilation (module load gcc openmpi lapack hdf5 ...)
+
+You can create your own machine directory under `machines` to define the appropriate environment.
+
+Run and validate the simulation:
+--------------------------------
+
+For each test case, given in a separate folder (e.g. testcase_small), you can find three scripts:
+
+*  prepare.sh: prepare the simulation (move data to the right location, recompile some minor changes, ...)
+*  run.sh : run the application and print out the evaluated metric
+*  validate.sh: validation of the simulation on a scientific point of view
+
+For running and validating the simulation, one should be able to do:
+```
+cd testcase_XXX
+./prepare.sh occigen-bdw
+./run.sh
+./validate.sh
+```
+And getting no error code returned.
+Those steps can also be used in a batch file for running the simulation using a job scheduler.
+
+
+
+

MUMPS/testcase_charge/README.md

+Test case presentation
+======================
+
+The charge test case is running 32 system resolutions using 200 nodes. 
+
+Each instance of system resolution is distributed over the 200 nodes, using one MPI per node per instance, and as many OpenMP thread as possible.  
+

MUMPS/testcase_scale/README.md

+Test case presentation
+======================
+
+The scale test case is running from 1 to 32 system resolutions using 200 nodes. 
+
+Each instance of system resolution is distributed over the 200 nodes, using one MPI per node per instance, and as many OpenMP thread as possible.  
+