(This is the older material - click here - for current specification content)

8. Problems with Von Neumann (3)

Another issue is that the rate at which data needs to be fetched and the rate at which instructions need to be fetched are often very different. And yet they share the same bottlenecked data bus.

Partial answer: The Harvard Architecture

The idea of the Harvard Architecture is to split the memory into two parts. One part for data and another part for programs. Each part is accessed with a different bus. This means the CPU can be fetching both data and instructions at the same time. There is also less chance of program corruption.

This architecture is sometimes used within the CPU to handle its caches, but it is less used with main memory because of complexity and cost.