fix use of cuda+magma in simulation mode: size of workspace must be consistent between real and simu modes

The new codelet is added for all 3 runtimes but only tested with starpu ;-)
An example test7 is added : it is a copy of test6 that uses the new function to build the matrices

add a priority scheme for getrf_nopiv_tile (with dmdas) and an efficient restriction optimization (tested on sirocco)

Fix a large bunch of warnings, and there are still mistakes that should be fixed before the SC release

delete this target dependency - why was it here? The target runtime_starpu_include does not even exist at this level

change the way we include our own header files --> relative to the root - when plasma is in the same env, chameleon can take some headers not belonging to it (ex: #include descriptor.h, this file states in plasma install dir also) which make compilation errors

change copyright - correct whitespace - place cmake module depending on chameleon in cmake_modules and no more in cmake_modules/morse