Found a great article discussing the needs of virtualization in the telecom space. The blog posting provides a good overview of technical capabilities that are needed for a virtualization layer in the multicore space.
I agree with many of the points that the author brings forward: Isolation, separation, performance (both algorithmic as well as I/O), size, stability, inter-VM communication, flexibility. Many of these attributes are what differentiate an embedded hypervisor from IT-level hypervisors.
Keep in mind that an embedded hypervisor can service small systems such as multifunctional printers, or small automative application. However, embedded does not always mean that systems are small. A telecom node can be a large rack with many different processing elements each with many cores and large pools of memory.
Interestingly enough, in these large systems, a compact hypervisor is still a requirement, as per the author's words 'This requirement relies on well-known statistics that the module stability is proportional to its code size. Simply speaking, larger the code, more bugs it will have. At the same time, the hypervisor becomes a single point of failure in the system, and the hypervisor failure cannot be tolerated in highly available telecommunication products.'