The von Neumann architecture vs Harvard architecture

Harvard Architecture is where program and data stored separately, which is a more expensive architecture but less bottlenecks and hence faster. In the Von Neumann Architecture they are stored together in memory which is cheaper and simpler but causes bottle necks.

Worth reading this summary too: Von-Neumann vs Harvard Architecture | Differences & Uses (teachcomputerscience.com)

Harvard — program and data stored separately, which is a more expensive architecture but less bottlenecks and hence faster. Von Neumann they are stored together in memory which is cheaper and simpler but causes bottle necks

John von Neumann was associated with, he was known for his work with the EDVAC (Electronic Discrete Variable Automatic Computer). The EDVAC was one of the earliest electronic computers and utilized the stored-program architecture that von Neumann detailed in his First Draft of a Report on the EDVAC. This architecture later became known as the von Neumann architecture.

Harvard Mark I computer and is sometimes attributed to the work of Howard Aiken in cooperation with engineers at IBM during the development of the Mark I in the 1940s.

John von Neumann (pictured right) was associated with, he was known for his work with the EDVAC (Electronic Discrete Variable Automatic Computer). The EDVAC was one of the earliest electronic computers and utilized the stored-program architecture that von Neumann detailed in his First Draft of a Report on the EDVAC. This architecture later became known as the von Neumann architecture.

The von Neumann machine

In a von Neumann machine, the same address bus is used to transfer both data and instructions, and the same data bus is used to transfer whether it transfers data or instructions. The store or memory holds both the data and the instructions in the same memory space.

Harvard architecture

The Harvard architecture is a computer architecture with physically separate memories for instructions and data. Harvard architecture is used extensively with embedded Digital Signal Processing (DSP) systems. DSP applications include audio and speech signal processing, sonar and radar signal processing, biomedical signal processing, seismic data processing, and digital image processing.

• The two different memories can have different characteristics; for example, in embedded systems instructions may be held in read-only memory while data memory requires read-write memory.
• In some systems, there is much more instruction memory than data memory so a larger word size is used for instructions.
• The instruction address bus may be wider than the data bus.
• Embedded systems include special-purpose computers built into devices often operating in real-time, such as those used in navigation systems, traffic lights, aircraft flight control systems, and simulators.
• Harvard architecture can be faster than von Neumann architecture because data and instructions can be fetched in parallel instead of competing for the same bus.

Question:

Why do you think Von Neumann won out over Harvard? Research some reasons.