Flashcards
Section 1 Chapter 3
Cards in this deck (10)
- 1Von Neumann architecturesame data bus is used to transfer both data and instructions. Single address bus is used to transfer the addresses of data and instructions. Same word length is sued whether it holds data or instructions
- 2Harvard architecturephysically sperate memories for instructions and data. Used extensively with embedded Digital Signal Processing (DSP) systems. 2 different memories can have different characteristics. Sometimes more instruction than data memory so larger word size is used for instructions. Address bus may be wider than data bus.
- 3stored program conceptmachine code instructions are fetched and executed serially by a processor that performs arithmetic and logical operations.
- 4embedded systemsspecial-purpose computers built into devices often operating in real time, such as navigation systems, traffic lights... their code cannot be changed
- 5contemporary processor architrcturesmix of von Neumann and Harvard. There is one main memory for holding both data and instructions, but CPU cache memory is divided into an instruction cache and data cache. Harvard architecture is used as the CPU accesses the cache.
- 6Complex Instruction Set Computer (CISC)single instruction that will do the loading, multiplication and storing the result. Very little work required to translate a high-level language statement into machine code. Consists of many specialised instructions though only ~20% of them were used in the average program.
- 7Reduced Instruction Set Computers (RISC)opposite of CISC. Only simple instructions, each taking one clock cycle, can be executed. Compiler has to do more work to translate high-level code + more RAM is required to store the machine code instructions. Pipelining is possible. Four instructions will execute at least as fast as one CISC instruction.
- 8Co-processor systemsextra processor used to supplement the functions of the primary processor. Used to perform floating point arithmetic, graphics processing, digital signal processing... Not a general-purpose processor that can fetch own instructions.
- 9Parallel and Multi-core systemsimproved performance gained by using a multi-core processor is depended on the software being able to take advantage of the parallel processing capabilities. Aim is to divide program instructions between multiple cores.
- 10Graphics processing unit (GPU)specialised electronic unit which is very efficient at manipulating computer graphics. Has massively parallel architecture consisting of thousands of smaller, more efficient cores designed for handling multiple tasks simultaneously. Its structure makes it suitable for tasks where processing large blocks of visual data is done simultaneously.
Information
- Description
- A level Computing (Section 1) Flashcards on Section 1 Chapter 3, created by Nathan Shapero on 13/09/2022.
- Created by
- Nathan Shapero
- Views
- 0
- Rating