GitLab

Made some improvements into the cost model to take into account blockwise reshuffle and try to do it more often

available memory for now.

Conflicts:
	src/dist_tensor/dist_tensor_internal.cxx

Fixed support for padded scalapack, and made tensors allocate on stack, though currently have a memory leak in parallel

Made timer profile MPI, fixed some memory leaks (not all when running in parallel), implemented some initial code for internal stack

Fixed a bug with the code which zeros out symmetric padded portions. fast_sym now gets correct answer in parallel, still issues with mapping the 4D version.

Addec a couple of unit tests and turned on diagonal rescaling. SCF may be incorrect currently though