Princeton architecture

E412983

Princeton architecture is a computer design model in which program instructions and data share the same memory and bus system, more commonly known as the von Neumann architecture.

All labels observed (1)

Label Occurrences
Princeton architecture canonical 1

How this entity was disambiguated

Statements (47)

Predicate Object
instanceOf computer architecture
von Neumann architecture
advantage easier programming model
lower hardware cost
simpler memory organization
alternativeName von Neumann architecture
basedOnConcept stored-program computer
busType shared program and data bus
comparedTo modified Harvard architecture
contrastsWith Harvard architecture
designGoal flexible general-purpose computation
enables programs to be treated as data
self-modifying code
firstDescribedIn 1940s
hasCharacteristic instruction and data fetch contention
potential memory bottleneck
sequential instruction execution model
simpler hardware design
single data path for code and data
stored-program concept
unified address space
hasComponent central processing unit
shared system bus
single main memory
historicalOrigin John von Neumann’s stored-program design
influenced early mainframe computer designs
many educational computer models
limitation throughput limited by single memory bus
von Neumann architecture
surface form: von Neumann bottleneck
memoryAccessPattern instructions and data fetched over same bus
memoryType shared program and data memory
performanceImplication cache hierarchies used to mitigate bottleneck
risk code and data corruption if not protected
securityImplication requires memory protection for isolation
sharesMemoryFor program instructions and data
supports dynamic code loading
runtime code generation
typicalImplementationDetail instruction and data caches may be logically separate but share main memory
typicalUse desktop computers
general-purpose computers
laptop computers
many microcontrollers
servers
usedIn many operating systems designs
most modern CPUs
uses single bus for instructions and data
single memory for instructions and data

How these facts were elicited

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Harvard architecture contrastsWith Princeton architecture