Harvard architecture is a type of computer architecture that separates its memory into two parts so data and instructions are stored separately. The architecture also has separate buses for data transfers and instruction fetches. This allows the CPU to fetch data and instructions at the same time. Today, processors using Harvard architecture use a modified form so they can achieve a greater performance. Some modified forms allow the support of tasks like loading a program from secondary storage (opposed to RAM) as data then executing it. In some systems, instructions are stored in read-only memory and data in read-write memory.
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. It is used extensively with embedded Digital Signal Processing (DSP) systems. DSP systems include audio and speech signal processing, sonar and radar signal processing machines, biomedical signal processing, seismic data processing and digital image processing. The key features…..
1. The two different memories can have different characteristics: for example, in embedded systems, instructions may be held in read-only memory while data may require read-write memory.
2. In some systems, there is much more instruction memory than data memory, so a larger word size is used for instructions.
3. The instruction address bus may be wider than the data bus.