Computer Architecture Test 1 (Ch. 1 & Ch. 2)

List the main structural components of a computer

CPU, Main Memory, I/O, and System Interconnection

List the main structural components of a processor

Control Unit, Arithmetic and Logic unit, Registers, and CPU interconnection

what is a CPU?

controls the operation of the computer and performs its data processing functions

what is the main memory?

stores data

What is I/O?

moves data between the computer and its external environment

what is system interconnection?

some mechanism that provides for communication among CPU, main memory, and I/O

what is a control unit?

Controls the operation of the CPU and hence the computer

what is the arithmetic and logic unit?

Performs the computer’s data processing function

what is a register?

Provide storage internal to the CPU

what is CPU interconnection?

Some mechanism that provides for communication among the control unit, ALU, and registers

what are some techniques used to speed up a processor?

Pipelining, Branch Prediction, Superscalar Execution, Data Flow Analysis, Speculative Execution

What is Pipelining?

enables a processor to work simultaneously on multiple instructions by performing a different phase for each of the multiple instructions at the same time.

What is Branch Prediction?

• The processor looks ahead in the instruction code fetched from memory

• predicts which branches, or groups of instructions, are likely to be processed next

What is Superscalar Execution?

the ability to issue more than one instruction in every processor clock cycle. In effect, multiple parallel pipelines are used

What is Data Flow Analysis?

• The processor analyzes which instructions are dependent on each other’s results, or data, to create an optimized schedule of instructions.

• In fact, instructions are scheduled to be executed when ready, independent of the original program order. This prevents unnecessary delay

What is Speculative Execution?

• Using branch prediction and data flow analysis,

• some processors speculatively execute instructions ahead of their actual appearance in the program execution, holding the results in temporary locations.

• This enables the processor to keep its execution engines as busy as possible by executing instructions that are likely to be needed.

What is Amdahls Law?

states that overall system speedup remains constrained by the fraction of execution time belonging to the strictly sequential code that cannot be run in parallel.

What is computer architecture?

refers to those attributes of a system visible to a programmer

What is Computer Organization?

describes how the physical hardware components of a computer system are arranged, to execute instructions and implement a given architecture

What is computer structure?

The way in which the components are interrelated.

What is computer function?

The operation of each individual component as part of the structure

What is a Core?

An individual processing unit on a processor chip

What is a stored program computer?

a computer that reads the program instructions it is executing directly from fast electronic storage

List and explain the key characteristics of a computer family

1. Similar or identical instruction set

2. Increasing speed

3. Increasing memory size

4. Similar or identical operating system

5. Increasing number of I/O ports

6. Increasing cost

What is the key distinguishing feature of a microprocessor

the integration of multiple functions on a single chip

Explain Moore’s law

the observation that the number of transistors on a microchip doubles about every two years while the cost of computers drops

Explain the concept of performance balance

designing a system so that all major components—such as the CPU, memory, storage, and I/O interfaces—have matching capabilities and speeds

Briefly characterize Little’s law

• Lambda = avg arrival rate

• W = avg unit of time

• L = avg of unit

• L = lambda(W)

Explain multicore systems

• Feature a small number of powerful, complex, general-purpose cores (typically 2 to 32) optimized for sequential instruction speed and low latency.

• Feature thousands of tiny, specialized cores built for massive data throughput rather than complex logic

Explain GPGPUs

• Feature thousands of tiny, specialized cores built for massive data throughput rather than complex logic

• Originally designed for rendering images, now widely repurposed for machine learning, deep neural networks, and massive mathematical simulations

What is a MIC (many integrated core)

• Contain a large number (50+) of simpler, lower-power, CPU-like cores on a single chip.

• Built for heavy parallel data processing and high-performance scientific or enterprise computing without needing graphics hardware

Define MIPS

• millions of instructions per second

• f / CPI * 10^6

Define FLOPS

• millions of floating-point operations per second

• Number of executed floating - point operations in a program / Execution time * 106

what is Arithmetic mean

What is Geometric Mean?

What is Harmonic Mean?

List the desirable characteristics of a benchmark program

1. It is written in a high-level language, making it portable across different machines.

2. It is representative of a particular kind of programming domain or paradigm, such as systems programming, numerical programming, or commercial programming.

3. It can be measured easily.

4. It has wide distribution.

What are the SPEC benchmarks?

What are the differences among base metric, peak metric, speed metric, and rate metric

What is a Peak Metric?

This enables users to attempt to optimize system performance by optimizing the compiler output. For example, different compiler options may be used on each benchmark, and feedback-directed optimization is allowed.

What is a speed metric

This is simply a measurement of the time it takes to execute a compiled benchmark.

What is a Rate metric

This is a measurement of how many tasks a computer can accomplish in a certain amount of time