- use (starpu_cpu_func_t) 1 trick, same as cuda_func
    - cpu funtions are not defined anymore avoiding the dependency to coreblas
    - add #if !defined(CHAMELEON_SIMULATION) where it is needed
    - remove dependency to the coreblas library (become useless)
    - remove useless simucblas, simulapacke libraries
    - remove CHAMELEON_SIMULATION_MAGMA cmake variable and definition
      - keep using CHAMELEON_USE_CUDA and CHAMELEON_USE_MAGMA to consider CUDA kernels
      - this avoid to introduce useless new variables
    - work on messages

don't force calibration in simulation mode. It does not make sense, and hides the StarPU detailed warning about missing calibration

to change the default values for tag_width(=31) and tag_sep(=24).
Today, it serves only with starPU.

chameleon: enrich the dependencies between chameleon_parsec lib and parsec libs with the _DEP variable coming from morse finds

chameleon: enrich the dependencies between the runtime interface libs of chameleon and the runtime libs with the _DEP variable coming from morse finds

MPI tag upper bound: MPI_TAG_UB is included (so on most platform the default values tag_width=31, tag_sep=24 are ok)

To use your own progress indicator,
- Define a function with prototype "void my_update_progress(int currentValue, int maximumValue)"
- Pass it to chameleon with "ierr=MORSE_Set_update_progress_callback(my_update_progress)"
- Activate progress indicator with MORSE_Enable(MORSE_PROGRESS)