Is there technical information on this somewhere? How is this different from AWS and from a traditional supercomputer? If I write a shared-memory parallel computation could I just run it on their platform (assuming I've done the work to make sure it can scale), or do I need to use MPI/a special language to make it all work?
As for the comparison with supercomputing: this falls decidedly in the abstracted/virtualized/cloud category, which is basically the opposite of a supercomputer, where you're very close to the metal (i.e. C/C++ or Fortran). Efficient supercomputer usage requires hard thinking about communications (both between nodes with MPI and between the RAM and the CPU on each node), avoiding cache thrashing at all cost, and making use of all the performance intrinsics you can.