Types Of Processor Flashcards
What does the von Neumann architecture specify?
The basic components of the computer and processor in which a shared memory and bus is used for both data and instructions
Define the ‘stored program concept’?
Machine code instructions are fetched and executed serially by a processor that performs arithmetic and logical operations, a program must be resident in main memory to be executed, the machine code instruction are fetched from memory one at a time, decoded and executed in the processor
What is the Harvard architecture?
A computer architecture with physically separated memories for instructions and data
What is Harvard architecture extensively used with?
embedded Digital Signal Processing (DSP)
Why can Harvard architecture be faster than von Neumann architecture?
Because data and instructions can be fetched in parallel instead of competing for the same bus
What architecture do modern high-performance CPU chips incorporate?
Aspects of both von Neumann and Harvard architecture
What does CISC stand for?
Complex Instruction Set Computer
What is CISC built into?
The machine hardware
What us the distinguishing feature of a CISC instruction?
Is that it combines a ‘load/save’ instruction with the instruction that carries out the actual calculation
Why does CISC use a large instruction set?
To accomplish task in as few lines as possible
What is an advantages of CISC in term of the complier?
The complier has very little work to do to translate a high-level language statement into machine code, leading to very little RAM required to store the instructions
What is a disadvantage of CISC in terms of hardware?
That many specialised instruction had to be built into hardware even though only about 20% ig them err used in the average program
What does RISC stand for?
Reduced Instruction Set Computer
How does RISC take the opposite approach of CISC?
By having only simple instructions, each taking one clock cycle, can be executed
What is a disadvantage of RISC in terms of the complier?
The complier has to do more work to translate, high-level code into machine code and more RAM is required to store the machine code instructions
What is an advantage of of RISC having each instruction take the same amount of time?
Because each instruction is one clock cycle, pipelining is possible and the four instructions will execute at least as fast as the single CISC instruction
Which processor design is more popular?
RISC has largely replaced CISC as a processor design, but CISC is still used for microcontrollers and embedded systems
What is a co-processor?
An extra processor used to supplement the functions of the primary processor, the CPU
What can a co-processor be used for?
It may be used to perform floating point arithmetic, graphics processing, digital signal processing and other functions
What can a co-processor not be sued for?
May not be used for general-purpose processor with the ability to fetch its own instructions, do inputs and output operations and so on, generally carries a limited range of functions
What do multi-core CPUs do?
distribute workload across multiple CPU cores, thus achieving significantly higher perforce
How many cores to many personal computers have?
dual-core or quad-core
What is the performance gained by using a multi-core processor dependent on?
The software being able to take advantage of the parallel processing capabilities
What dies GPU stand for?
Graphics Processing Unit
What us a GPU
A specialised electronic circuit which is very efficient at manipulating computer graphics and image-processing
What is the architecture of a GPU normally?
Consists of thousands of smaller, more efficient cores designed for handling multiple task simultaneously
In a personal computer where may a GPU be present?
On a graphics card or embedded on the motheword
What are some of the applications that uses the GPU?
Machine learning, oil exploration, image processing and financial transactions
What is a GPU a form of?
Co-processor
How does the GPU work with a CPU?
The GPU takes on the compute-intensive parts of an application while the remainder of the code runs of the CPU