Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

CDA architecture > Chap 1 - PART 2 - Cont'd > Flashcards

Chap 1 - PART 2 - Cont'd Flashcards

1
Q

Describe the characteristics of:

Volatile Main Memory (Primary Memory)

A
  • Loses instructions and data when powered off
  • Storage such as DRAM, that retains data only if it is receiving power
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Describe the characteristics of:

Non-Volatile Secondary Memory

A
  • A form of memory that retains data even in the absence of a power source and that is used to store programs between runs
    • eg:
      • Magnetic disk
      • Flash Memory
      • Optical Disk(CDROM, DVD)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Explain RAM and list the two major types of RAM:

A

RAM = Random Access Memory

  • all data can be read equally quickly

Two types:

  • Static RAM (SRAM)
    • uses a flip-flop combination per memory bit
    • uses less power, but comes at a higher cost
  • Dynamic RAM (DRAM)
    • Cheaper than SRAM
    • Combination of transistor + capacitor for every memory bit
    • Uses more Power due to constant refresh by the capacitor
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Major Comparison between:

SSD VS HDD

These are secondary memory.

Image

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What happens when Electronic technology continues to evolve?

A
  • Increased capacity and performance
  • Reduced cost duh
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Describe:

Networks

Also list the three types of general Networks

A

Communication, resource sharing, and nonlocal access

  • Local Area Network (LAN) : ethernet
  • Wide Area Network (WAN): The Internet
  • Wireless Network: WIFI, Bluetooth, RFID, NFC etc
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Define Die:

A

These are individual rectangular sections that are cut from a wafer, more informally known as chips

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Define Wafer:

A

This is a slice from a silicon ingot that is no more than 0.1 inches thick, which is used for making chips

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Define Silicon Crystal ingot

A

This is a rod composed of a silicon crystal that is between 8 to 12 inches in DIA and about 12 to 24 inches in length

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Define Silicon

A

This is a natural element that is a semiconductor

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Define semiconductor

A

This is a substance or material that does not conduct electricity very well like metal.

EG. Silicon and Graphite are semiconductors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Define Yield

A

This is the percentage of good dies from the total number of dies on a wafer.

yield = (good dies/total number of dies) * 100

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Define Transistor:

A

This is an ON/OFF switch controlled by an electrical signal

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Define Bonding:

A

This is a process in which it connects the good dies to the input/output pins of a package.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Image Conveying the Manufacturing Process of the Integrated Circuit (IC)

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Information on the :

Intel Core i7 Wafer

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Formula for Calculating:

The Integrated Circuit Cost

A
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Regarding the Integrated Circuit Cost;

What are the NonLinear relation to area and defect rate?

A
  • Wafer cost and area are fixed
  • Defect rate determined by manufacturing process
  • Die area determined by architecture and circuit design
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Define response time

A

Response time is also known as Execution Time

  • It is how long it takes a computer to do a task.
  • This includes disk accesses, memory accesses, I/O activities/ OS overhead, CPU execution time, and so on….
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Define Throughput

A

This is also known as bandwidth

  • This is another measure of performance
  • it is the “N” of tasks completed per unit of time
  • eg. tasks/ transactions/ per hour
21
Q

Research this question or watch Professor’s video:

Chap 1 Part 2:

How are response time and throughput affected by:

  1. replacing the processor with a faster version?
  2. Adding more processors?
A

Research it

22
Q

Formula for the calculation of:

Relative Performance

A
23
Q

Using the formula for:

Relative Performance:

Solve the following example:

If PC A runs a program in 10s and PC B runs the same program in 15s, how much faster is A than B?

A

10s on A

15s on B

Formula: Execution Time[B] /Execution Time[A]

= 15/10

= 1.5

Therefore, PC A is 1.5 times faster than PC B

24
Q

Measuring Execution Time:

Describe:

Elapsed time

A
  • This is the total response time, including all aspects
    • processing, I/O, OS overhead, idle time, etc
  • This determines system performance
25
Q

Measuring Execution Time:

Describe the characteristics of CPU Time:

A

This is the:

  • Time spent on processing a given job
    • discounts I/O time, other jobs’ share [meaning substract those time spent]
  • Comprises user CPU time and system CPU time
  • Different programs are affected differently by CPU and System performance. Which makes sense
26
Q

What is meant by CPU Clocking?

A

The Operation of digital hardware is governed by a constant-rate clock. This is known as CPU Clocking.

eg.

27
Q

Define:

Clock Period

A

This is the duration of a clock cycle

eg. 250ps =0.25ns = 250 E-9 s

28
Q

Define:

Clock Frequency (Rate)

A

This is the cycle per second

eg. 4.0GHz = 4000MHz = 4.0 E9 Hz

Also known as the inverse of the clock period

29
Q

Formula for:

CPU Time

State the factors that will improve performance

A
30
Q

CPU Time Example:

Computer A:

  • 2GHz Clock, 10s CPU Time

When designing Computer B:

  • Aim for 6s CPU Time
  • Can do faster clock, but causes 1.2 x clock cycles

Question: How fast must Computer B’s Clock be?

A
31
Q

What determines the instruction count for a program?

A

It is determined by:

  • Program
  • ISA
  • Compiler
32
Q

What determines the average cycles per instruction

A

Determined by:

  • CPU Hardware
  • IF different instructions have different CPI
    • Then Average CPI affected by instruction mix
33
Q

Formula:

Instruction Count AND

Clock Cycles Per Instruction ( CPI)

A
34
Q

Define:

CPI (Clock Cycles Per Instruction)

A

This is the average number of clock cycles per instruction for a program or program fragment

Usage:

Provides one way of comparing two different implementations of the same instruction set architecture (ISA)

Formula:

35
Q

CPI Example:

PC A:

  • Cycle time = 250ps ; CPI = 2.0

PC B:

  • Cycle time = 500ps ; CPI = 1.2

Question:

Assume both PCs have the same ISA; which is faster and by how much?

A
36
Q

CPI Example:

A
37
Q

Formula:

Performance Summary

A
38
Q

List:

the factors in which performance depends:

A
39
Q

Formula:

Power Trends

A
40
Q

Reducing Power Example:

Suppose a new CPU has:

  • 85% of Capacitive load of old CPU
  • 15% voltage and 15% frequency reduction

What is the impact on dynamic power?

A
41
Q

The Power Wall Issue:

We cannot reduce voltage any further because:

  • Many transistors to leak like water faucets that cannot be completely shut off
  • Today, about 40% of the power consumption in server chips is due to leakage

How else can we improve performance?

A
  • Designers have attached large devices to increase cooling
  • Turn off parts of the chip that are not used in a given cycle
42
Q

The Memory Wall issue:

  • Describe what this issue means and what does it mainly refers to in terms of latency?
  • Memory speed improves at a much slower rate than that of the CPU. Therefore, Memory is a _____ in computer perfomance.
A

This refers to the disparity of speed between the CPU and Memory outside of the CPU (external drives).

This mainly refers to the latency in bringing data from memory to the CPU

  • bottleneck:
    • A bottleneck is a point of congestion in a production system (such as an assembly line or a computer network) that occurs when workloads arrive too quickly for the production process to handle
43
Q

What does multiprocessor mean?

A
44
Q

What is SPEC and what is it for?

A

Standard Performance Evaluation Corp

  • Develops benchmark for CPU, I/O, WEB…
  • Elapsed time to execute a selection of programs; negligible I/O, so focuses on CPU performance
  • Normalize relative to reference machine
  • Summarize as geometric mean of performance ratios
    • CINT2006 (integer)
    • CFP2006 (floating point)
45
Q

Explain the Pitfall for Amdahl’s Law:

  • Note that: A rule stating that the performance enhancement possible with a given improvement is limited by the amount that the improved feature is used.
  • Show the formula that finds the max improvement possible by improving a particular part of a system
A
  • Formula:
    • execution time after improvement = ((exe time affected by impr) / (amt of impr)) + exec time unaffected
      • we can use this law to estimate performance impr when we know the time consumed for some function and its potential speedup
46
Q

Pitfall: Amdahl’s Law : Example

Suppose a program runs in 100s on a computer, with multiply operations responsible for 80s of this time.

  • how much improvement in multiply performance to get 5x overall speedup?
A

Using formula:

  • Exe time after imprv = (exe time affected/ amt of imprv) + exe time unaffected
  • Exe time after imprv = (80s/n) + (100-80)
  • Exe time after imprv = (80s/n) + 20
    • if we want the program to run 5 times faster, that means the new execution time must be 100s/5 = 20 seconds
  • Therefore; 20s = (80/n) + 20
  • 0 = (80/n)….
  • This is UNREALISTIC and cannot be achieved by improving the multiply operation
47
Q

Define MIPS:

A
  • MIPS: refers to a measurement of program execution speed based on the number of millions of instructions. It is used as a performance metric.
  • MIPS is computed as the instruction count divided by the product of the exec time and 10⁶
  • MIPS: Millions of Instructions Per Second
    • Doesn’t account for:
      • Differences in ISAs between computers
      • Differences in complexity between instructions
48
Q

Explaining the Pitfall for: MIPS as a Performance Metric

Show the MIPS formula

A
49
Q
A

CDA architecture (11 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions