Unit 2.

Hardware Systems
This unit covers computer hardware the
components that make up a computer system
and how they work together.
– learn about how the computer processes information
and how memory works.
– learn about how data can be moved among
components inside and outside the system unit.
– familiar with different media for storing data.
By the end of this unit, you should
– understand how a computer works.
– also help you become an informed consumer of
computer equipment.
 contents
2.1 Processor and Memory
2.2 Peripherals
2.3 Storage devices
2.4 Putting Together the Hardware Components
2.5 Improving Computer performance

Assessments:
– Exercise 2
Overview of Hardware Components
Microprocessor
(executes instructions)

Main Memory
Storage Devices Chipset (temporarily stores data
(permanently store data (controls data flow) and program instructions
and application programs) while the computer
is running)

Legend
Component
Peripherals s
(input/output)
Data Path
 Hardware Components
The microprocessor( 微处理器 ), also called the
processor,
– is the main component that executes instructions stored in the
main memory.
– The microprocessor is sometimes referred to as the "brain" of
the computer system, making decisions and sending commands
to the other components to complete a set of instructions.
The main memory( 主存，内存 ) stores instructions to
be executed by the microprocessor.
– The data stored in main memory is lost when the computer is
turned off.
In contrast to main memory, storage devices ( 存储设
备)
– such as CD-ROM drives and floppy disk drives
– store data permanently even when the computer is turned off.
 Hardware Components
Peripherals( 周边设备，外设 ) enable data
input and output.
– the monitor, the printer, the keyboard, and the mouse.
– The peripherals also include mechanisms that allow
data to be transferred in and out of a computer
system.
The chipset ( 芯片组 ) acts as the traffic cop
controlling the flow of data and coordinating
interactions among components in the system.
– Components pass data through the chipset, and the
chipset monitors the data flow and passes data to
other components.
1.
How a File is Displayed
The microprocessor sends instructions to the storage devices (via the chipset) requesting the specified file to be loaded
into main memory.
2. The storage devices send the file through the chipset to main memory.

3. The microprocessor fetches

the file contents from main
memory. Microprocessor
3. The microprocessor sends (executes instructions)

the display data to the

monitor via the chipset.

1 Main Memory
Storage Devices 4 3 (temporarily stores data
(permanently store data 2 and program instructions
and application programs) while the computer
Chipset is running)

Legend
Component
Peripherals s
(input/output)
Data Path
Components inside the System
Unit A. Motherboard

B. Power supply

H. Disk drives

C. Microprocessor

(underneath a
cooling fan)

G. IDE cable

D. Expansion slot

E. Expansion card

F. Chipset
Components inside a computer
A. Motherboard
– Provides sockets for microprocessor and memory chips, slots for
circuit boards, and the circuitry that enable electrical signals to
travel from component to component. Most of the hardware
components inside the system unit are attached to the
motherboard.
B. Power supply
– Provides electrical power to the computer system.
C. Microprocessor
– Processes instructions stored in main memory. Sometimes, the
microprocessor is found underneath a cooling fan to prevent it
from overheating.
D. Expansion slot
– Serves as a socket on the motherboard into which an expansion
card maybe inserted.
Components inside a computer
E. Expansion card
– Enables a computer to control peripheral devices such as the
monitor and the microphone.
F. Chipset
– Controls data flow among components.
G. IDE (Integrated Drive Electronics) cable
– Transfers data from storage devices to the motherboard.
H. Disk drives
– Stores data permanently (even after the computer is turned off).
They may be any drives such as floppy disk drive, the CD-
ROM/CD-RW, DVD-ROM/DVD+/-RW drive, and the hard disk
drive.
2.1 Processor and Memory
2.1.1 Processor Basics
2.1.2 Types of Memory
2.1.3 Lab: Benchmarking (Optional)

Assessments:
– Multiple-Choice Quiz 4
 overview
The processor and memory are essential
components that enable a computer to
process commands.
– The processor carries out instructions given to
the computer.
– These instructions are stored in the
computer's memory.
 2.1.1 Processor Basics
Processor
Instruction Execution with the CPU
Performance: Factors and Measures
Types of Processors
 Processor
A computer's processor is usually referred to as the
microprocessor due to its size, which is about the size
of your fingernail.
A microprocessor processes all the instructions given to
the computer (add two numbers, execute program
instructions, or print documents).
Physically, the microprocessor is a single chip known as
an integrated circuit (IC).
– Each chip is made out of silicon and it contains millions of
transistors packed onto a chip.
– The Intel Pentium M Processor, introduced on March 12, 2003,
– has 77 million transistors, and the width of the smallest wire on
the chip is 0.13 micron, or 0.00000013 meter.
– 0.13 micron is about 1/800 of the width of a human hair.
Central Processing Unit (CPU).
The microprocessor is referred to as the
Central Processing Unit (CPU).
– The job of a microprocessor is to execute a
series of machine instructions.
– These instructions are procedures to carry out
a task written in a form that the computer can
understand.
Instruction Execution with the
CPU
Instructions are stored in the computer‘s
memory, RAM (random access memory)
There are two main components of the CPU.
– control unit, which accesses instructions stored in
RAM, interprets what they mean, and then dispatches
them.
– Arithmetic/Logic Unit (ALU) that performs
arithmetic (addition, subtraction, multiplication, division) and
logic (greater than, less than, equal to) operations needed to
process the instructions.
Fetch-Execute Cycle( 指令执行周
期)
There are four steps that the CPU performs
when executing an instruction; they are called
the fetch-execute cycle.
The four steps are as follows:
– 1. Fetch - The control unit gets the instruction from
memory.
– 2. Interpret - The control unit decodes what the
instruction means and directs the necessary data to
be moved from memory to the ALU.
– 3. Execute - The control unit directs the ALU to
perform the necessary arithmetic or logic operations.
– 4. Store - The result of the computation is stored in
memory.
 Fetch-Execute Cycle
Memory
Let R = X + Y Step 1. Control unit
fetches instruction Control Unit
Number 1 (X)

Number 2 (Y)

Result R Step 3. Control

unit executes the
Step 2. Control unit interprets the instruction instruction by
and sends the 2 numbers to be added into the directing the
appropriate registers in the ALU. ALU to add the
Step 4. Result is 2 numbers in the
stored back in registers 1 and 2
memory. ALU then store the
Register 1 Register 2 result in the
(contains Number 1) (contains Number 2) accumulator.

Accumulator
(Result of Number 1 +
Number 2)
 cache
Cache 高速缓冲存储器
– a special high-speed memory that stores most
recently used data in order to speed up the
process of instruction execution.
A cache can speed up data retrieval
because 基于统计的调度策略
– recently used data is likely to be used again
by the computer.
 Level 1/2 cache memory
Level 1 (L1) cache memory or primary cache memory
– is located on the CPU to provide the CPU with the fastest
access to data.
Level 2 (L2) cache memory or secondary cache
– is a slower cache,
– located between the RAM and the CPU (sometimes on the
CPU).
If data cannot be found on either cache, it will be
retrieved from RAM.
Relative to the physical distance between the CPU and
storage areas for data and instructions, data is retrieved
more quickly
– from the L1 cache,
– then the L2 cache, and
– then the RAM.
 The Microprocessor
Microprocessor
CPU
(ALU, Registers, Control unit)
L1 cache
L2 cache
(usually on CPU)

Main Memory
Storage Devices Chipset (temporarily stores data
(permanently store data (controls data flow) and program instructions
and application programs) while the computer
is running)

Legend
Component
Peripherals s
(input/output)
Data Path
 Processor Performance
Rate at which the instructions are processed (clock rate)
– Measured in Hertz
– 1 Hertz - one cycle per second
– Processor clock rate measured in MHz
Machines are compared based on their
– clock speed or
– number of instructions per second (IPS).
This measure depends on
– both the number of cycles per second
– and the mix of instructions executed.
Measure of processor performance is benchmarking.( 基
准测试 )
– ZDNet is organization which has a set of useful benchmarks( 基
准测试程序 )
 Bandwidth( 带宽 )
the volume of data that can be transmitted
within a fixed amount of time between
components in a computer system
– the transfer speed from the disk to the
motherboard or
– through connections to other computers.
Bandwidth is expressed in bits per
second (bps), or sometimes bytes per
second (Bps)
 2.1.2 Types of Memory
RAM
ROM
CMOS Memory
Summary
 Types of Memory( 存储器 ) Main Memory

Microprocessor RAM
(instructions to be
(executes instructions)
executed after computer
is booted)

Boot Memory
ROM
(instructions needed to
boot the computer)
Storage Devices Chipset
(permanently store data CMOS
(controls data flow)
and application programs) (Configuration information
used in the boot process)

Legend
Component
Peripherals s
(input/output)
Data Path

Memory
Types of Memory (continued)
RAM (random access memory) is a
temporary holding area for both data and
instructions. It is also referred to as main
memory.
Data in RAM is lost when the computer is
turned off.
Types of Memory (continued)
Measured by its memory capacity and latency.
– Capacity （容量）
is the maximum number of bits or bytes that can be stored.
The capacity of RAM is typically measured in megabytes
(MB). Many computers have RAM capacity of 128MB or
more.
– Latency ( 响应时间、延迟时间、等待时间 )
is the delay between the time when the memory device
receives an address and the time when the first bit of data is
available from the memory device.
This delay is also referred to as access time （访问时间） .
Latency is typically measured in nanoseconds (ns), billionth
of a second (10-9 sec). Latency measures the speed of
RAM.
 DRAM (Dynamic RAM , 动态
RAM)
a common type of RAM.
– Made of an integrated circuit (IC, 集成电路 ), composed of
millions of transistors( 晶体管 ) and capacitors( 电容器 ).
– A capacitor can hold electrons. An empty capacitor represents a
“0”, and a non-empty capacitor represents a “1”. Each capacitor
can register either a “0” or a “1” for a memory cell, storing one bit
of data.
– The transistor is like a switch that controls whether the
capacitor's state (charged or not charged, 1 or 0) is to be read or
changed.
– However, a capacitor is like a cup that leaks, in order to keep its
charge, the memory control needs to be recharged or refreshed
periodically( 周期性刷新 ). Therefore, it is called the dynamic
RAM because its state is not constant.
– Refreshing capacitors also takes time and slows down memory.
 DRAM (continued)
SDRAM (Synchronous Dynamic RAM)
– Used in many personal computers
– Fast and relatively inexpensive
– Synchronized to the clock so that data can be sent to
the CPU at each tick of the clock, increasing the
number of instructions the processor can execute
within a given time
DDR SDRAM (Double Data Rate SDRAM)
– Transfers twice the amount of data per clock cycle
compared to SDRAM
– Capacity is up to 2 GB
 DRAM (continued)
RDRAM (Rambus Dynamic RAM)
– Higher bandwidth than SDRAM
– More expensive compared to SDRAM
– Enhances the performance of applications that
access large amounts of data through memory, i.e.
real-time video and video editing
SRAM (Static RAM)
– Uses transistors to store data
– Because SRAM does not use capacitors, reading
data from SRAM does not require recharging the
capacitors. Therefore, it is faster than DRAM.
– Holds fewer bits and costs more compared to DRAM
of the same size
– Used in the cache because it is fast and cache does
not require a large memory capacity
 RAM Comparisions

Type of RAM Capacity Price

SDRAM @@ $

DDR SDRAM @@@ $

RDRAM @@@ $$

SRAM @ $$$
 ROM
Read-only memory (ROM) is
programmed with data hard-wired
固化 when it is manufactured.
Data and instructions on a ROM
are permanent( 持久 ), or
nonvolatile, which means they are
not lost when power is turned off.
 Why is ROM needed ？
Why is ROM needed when RAM enables all the
memory operations necessary for a computer?
– Because data in RAM is lost when the computer
is turned off, some instructions are needed for the
CPU to start or boot the computer when the
computer is first turned on.
– Therefore, ROM contains a set of instructions that
is needed to start the computer.
– These instructions tell the computer how to
access the hard disk, find the operating system,
and load it into RAM.
– Then RAM stores all subsequent instructions to
be executed by the CPU.
 Type of ROM
Typically, ROM is hardwired with start-up instructions for
the computer.
At one time, changing the boot instructions (to integrate
a new video card and disable the old one) on a ROM
required replacing the entire ROM chip.
Currently, a type of ROM, electrically erasable
programmable read-only memory (EEPROM),
– can be updated by applying an electrical field changing
instructions stored on the chip one byte at a time.
– This could slow down the update process.
An alternative to EEPROM is flash memory.
– Flash memory is a type of EEPROM that rewrites data in
chunks, usually 512 bytes in size, instead of 1 bit at a time.
 CMOS Memory
Configuration settings of a computer such as
storage capacity, memory capacity (RAM), and
display configurations also need to be stored
permanently.
This information is stored in CMOS
(complementary metal oxide semiconductor ，
互补金属氧化物半导体 ) memory.
The CMOS chip requires very little electrical power
to hold data.
– It can be powered by a small battery on the
motherboard, or packaged with the chip.
– The battery maintains the data on the CMOS
when the computer is turned off.
Summary ： Which Memory Device
to Use?
ROM

no

Need to
Need to
store Need to
maintain yes configura-
no update
Start data when
tion information
power is
information ?
off?
?

no yes yes

EEPROM
RAM CMOS /
Flash
 Comparing memory devices
Memory Cost Capacity Latency Location
Register $$$$ 8-128 bits almost On CPU close to the
instantaneous ALU

L1 Cache $$$ 1-100 KB ~1 ns On the CPU

L2 Cache $$ 100-1000 KB ~1 ns Between the L1 cache

and the RAM

DRAM $ 1-1000 MB ~10 ns Outside the CPU on the

motherboard
 Processor and MemoryMicroprocessor Main Memory
CPU
(ALU, Registers, Control unit)
RAM
L1 cache (instructions to be
L2 cache executed when the
(usually on CPU) computer is running)

Boot Memory
ROM
(instructions needed to
boot the computer)
Storage Devices Chipset
(permanently store data (controls data flow) CMOS
and application programs) (Configuration
information used during
the boot process)

Legend
Component
Peripherals s
(input/output)
Data Path

Memory
 2.2 Peripherals
2.2.1 Connecting Peripherals
2.2.2 Buses
2.2.3 Input/Output Devices

Assessments:
– Multiple-Choice Quiz 5
2.2.1 Connecting Peripherals
Expansion Slots and Cards
Ports
USB and FireWire
Comparing Different Ports
 Peripherals( 外
设)
Microprocessor
(executes instructions)

Main Memory
Storage Devices (temporarily stores data
(permanently store data Chipset and program instructions
and application programs) while the computer
is running)

Peripherals Legend
Parallel
modem Component
PS-2
sound Memory
card
PCI Slots Port
Expansion
video Card
card USB Expansion
AGP Slot FireWire
Slot
Peripheral
Device
Modem Monitor Digital camera Camcorder Printer
Bus
Speaker Scanner Mouse Disk drive
 Expansion Slot, Card, and Port
An expansion slot is a
slit-like socket on the
motherboard into which a
circuit board can be
inserted.
The circuit board is called
the expansion card.
– Used to extend the
capability of a computer
– sound / video card
– Also provides port(s), which
are connector(s) between
the expansion card and the
peripheral device.
 Expansion Slots
The two most common types of expansion slots are
Peripheral Component Interconnect (PCI) and Accelerated
Graphics Port (AGP).
PCI (Peripheral Component Interconnect , 互连外围设备 ) slot
– Can hold a variety of expansion cards such as a sound
card or an Ethernet card
AGP (Accelerated Graphics Port, 图形加速接口 ) slot
– Primarily used for graphics cards
PCMCIA (personal computer memory card international
association, 个人计算机存储卡国际协会 ) slot
– Used for laptops in place of PCI slots on desktop
computers
– Relatively smaller than a PCI slot
 Expansion Cards
Small circuit boards that control the peripheral devices
– Graphics Cards
Takes signals from the processor and displays the graphics,
images in the monitor
– Sound Cards
Converts analog sound signals to digital and vice versa
– Modem
Transmits data over phone or cable lines
– Ethernet card
Serves as the interface to a Local Area Network (LAN), a
common network technology allowing users access to
network resources such as the Internet, email, shared
printers, etc.
Transfers data at a rate of 10 Mb/s
Newer versions of Ethernet called "Fast Ethernet" and
"Gigabit Ethernet" support data rates of 100 Mb/s and 1 Gb/s
(1000 Mb/s).
Ethernet cards for PCMCIA slot
and PCI slot, respectively
 Expansion Ports
Ports are connectors
that enable signals to
be passed in and out
of a computer or
peripheral device.
Cables from
peripheral devices
connect to ports of a
computer system.
 Different Types of Ports
PS/2 port, also known as serial port
– Transfers data one bit at a time
– Uses a 6-pin, mini-DIN configuration, which look like a small,
round port
– Used to be the standard for keyboard and mouse
connections, however, they are gradually being replaced by
USB ports.
DB-9 port
– Also becoming obsolete ( 废弃 )
– Used to connect PDA devices before the advent of USB
ports
– Connects external modem, barcode scanner, and other older
electronic devices
DB-25F, also known as Parallel port
– Transfers data one byte at a time
– Requires a 25-pin male connector (DB-25M) on the cable
– Can be used for printers or external drives
 USB and FireWire
USB (Universal Serial Bus, 通用串行总线 ) port
– Appears on desktop systems and laptops
– Can connect up to 127 devices via a USB hub, which
provides multiple USB ports (e.g. mouse, keyboard,
scanner, printer, digital camera, and hard disk drive)
– Supports "hot connectivity," which allows peripherals to
be connected to the system, configured, and used without
restarting the machine
– Replacing serial and parallel ports
FireWire
– Faster data transfer rate and more expensive compared to
USB (50MBps versus 1.5 MBps)
– Supports up to 63 devices
– Intended for data-intensive devices such as DVD players
and digital camcorders
– Peripheral devices can be connected via chaining.
– Supports hot connectivity
 USB v.s. FireWire
In response to FireWire's fast data transfer rate,
USB-2 is developed with a data transfer rate of
60 MBps.
To compete with USB, FireWire 2 is developed
with a data transfer rate of 100 MBps.
 Comparing Different Ports
Port Usage Status
FireWire Camcorder and Becoming the standard
external mass storage for digital video devices
(e.g. CD-ROM, hard
drive, etc.)

USB Most devices Becoming the standard

for most peripheral
ports

Parallel Printer Becoming obsolete

Serial Modem Becoming obsolete

PS/2 Keyboard, mouse Becoming obsolete

 2.2.2 Buses
several ways to transfer information
– To / from the CPU.
While some information transfers are
– completely internal to the CPU
– between the CPU and RAM
– between the CPU and peripheral devices
Go through some type of bus.
 Microprocessor
(executes instructions)
Buses ( 总
线)
F
r
s
i
o
d
n
e
t
Main Memory
Storage Devices (temporarily stores data
(permanently store data PCI Chipset Memory and program instructions
and application programs) while the computer
is running)
F
Peripherals i Legend
P
r Parallel
modem C U Component
I S e PS-2
sound A W
B Memory
card G i
PCI Slots
P r Port
e Expansion
video Card
card USB Expansion
AGP Slot FireWire
Slot
Peripheral
Device
Phone line Monitor Digital camera Camcorder Printer
Bus
Speaker, microphone Scanner Mouse, keyboard
Disk drive
 Bus
A bus is a pathway through which data is transferred from one part
of a computer to another.
Consists of the data bus and the address bus.
– The data bus transfers the data itself,
– while the address bus transfers information about where the
data is to go.
Has a width, a speed, and a transfer rate.
– The width, also called the word size （字长） , of a bus is
measured in bits.
– The speed of a bus is measured in hertz (Hz), or cycles per
second.
– Transfer rate is the measure of how much data may be moved
from one device to another in one second （ bps ） .
Transfer rate can be increased by transferring data multiple
times during a cycle or increasing the number of channels
used to transfer data.
 Different Types of Buses
Front Side bus
– Bus on the motherboard that transfers data
between the CPU and the chipset
Memory Buses: RAM bus and DRAM bus
– Usually transfers data multiple times during a
clock cycle or uses multiple channels to
transmit data to increase data transfer rate to
match that of the CPU.
ISA (Industry Standard Architecture)
– Becoming obsolete
– Word size or width of the data path is 16 bits,
running at a mere 8 MHz
 Different Types of Buses
PCI (Peripheral Component Interconnect)
– Predominant bus for newer systems
– 32 bits (standard), running at 33 MHz—giving PCI up to
133MBps of bandwidth
AGP (Accelerated Graphics Port)
– Bus architecture similar to that of PCI
– Provides video cards with rapid access to the system
memory
– To date, only used for graphics cards, especially those
that perform texture-mapping onto three-dimensional
renderings
– Very fast, running at 66 MHz with a 32-bit word size, and
transferring 266 MBps
IDE bus
– Transfers data between storage devices and the chipset
 Different Types of Buses
(continued)
USB (Universal Serial Bus) / FireWire (IEEE 1394)
– Transfer data one bit at a time at a variable pace
– Not rated with a MHz speed; rated by peak transfer
rate( 最高传输率 ).
– USB
Faster than standard serial connections, with a peak
transfer rate of 1.5 MBps.
Considered a low-speed bus and is designed to handle
low to medium-speed peripherals
An extension to USB-1 is USB-2, which supports data
rates up to 60 MBps versus the 1.5 MBps in USB-1;
USB-2 is fully compatible with USB-1.
– FireWire
High transfer rate designed for high-speed external
peripherals such as DVD-ROM and hard disk drives
FireWire 2 (IEEE 1394b) emerged with data rates up to
100 MBps, double that of FireWire 1 (IEEE 1394).
2.2.3 Input/Output Devices
Input Devices
– Cameras
– Digital Camcorders
– Scanners
Output Devices: Monitors and Projectors
– CRT Monitors
– LCD Monitors
– Projectors
Output Devices: Printers
– Ink Printers
– Dye-Sublimation Printers
– Laser Printers
– Comparing Printers
 Input Devices
Cameras
– Digital Camera
Enables photos taken to be stored in digital form, which can uploaded onto a
computer.
– Web Camera (webcam)
Captures live video and sends the compressed image stream to the
computer or to other computers via the Internet
Digital Camcorders
– Record video in digital form, which can be uploaded onto a computer
without further loss in image quality
– Recorded video can be edited using movie-editing software
– Images are more clear than those captured by a webcam, but requires
more bandwidth
– Uses fireWire jack/interface to enable host computers to provide enough
bandwidth for the camcorder
Scanners
– Convert a 2-D physical image (a photograph or a paper copy of an
image) into a digital image that can be viewed and edited on your
computer
 Output Devices: Monitors and
Projectors
CRT (cathode ray tube) monitors
– Used to be the most common type of computer monitors until
LCD monitors began to gain popularity
– Use three electron beams to create colors, red, green, and blue.
To generate the color white, all three beams are fired
simultaneously. To create the color black, all three beams are
turned off. Other colors are created using different mixtures of
these three color beams.
– Inexpensive and dependable for displaying images on screen.
– Also found in conventional TV sets.
LCD (liquid crystal display) monitors
– Produce images by manipulating light within a layer of liquid
crystal cells
– Also known as flat-panel screens （平板）
– Compact, lightweight, easy-to-read, and emit less radiation
compared to CRT monitors
– Used in notebook computers and desktop computers
 Projectors 投影仪
Enable images on the computer screen to be magnified
and projected onto a bigger screen
Use two types of technologies
– LCD (liquid crystal display) system
Images are projected as light shines through a
layer of liquid crystal cells
– DLP (digital light processing) system
Uses tiny mirrors that reside on a special microchip
called the Digital Micromirror Device (DMD)
Images are smoother and have better contrast
than those created using LCD
 Printers 打印机
Ink Printers
– Works by spraying and dyeing the page with color
– Rated according to their resolution and color depth
Color depth is the range of colors that any given drop may
represent
Resolution is measured in dpi, the number of dots per inch
(horizontally or vertically) that a printer can place on a page.
Sometimes the dpi is the same both horizontally and
vertically, such as 1200 dpi. Other times, the horizontal and
vertical dpi differ—as in1440x720 dpi.
– Use a four-color process, CMYK (cyan, magenta, yellow, and
black), to produce various colors. Sometimes the color black is
excluded because it can be produced by mixing the other three
colors.
– Multiple drops of colors can also be placed on a single dot to
produce more colors.
 Printers (continued)
Dye-Sublimation Printers ( 热升华 )
– Used to print high-quality images like those at a photo lab
– Use solid dyes consisting of the four colors, cyan, magenta,
yellow, and black.
– Varying mixtures of CMYK color dyes can be used to represent
different colors, achieving photo-like quality
– The print head heats and vaporizes the dyes to allow them to
permeate the glossy surface of the printing paper before they
solidify
Laser Printers
– Use toner cartridges that contain toner, a colored powder
– Uses laser beams to charge the image of the page onto a
photoelectric drum
– When the paper runs through the printer in between the drum
and the toner cartridge, the electro-magnetic charge of the drum
picks up the toner and then transfers it to the paper. A heat and
pressure system then fuses the powder to the page.
dot matrix printer
 Comparing Printers
Printer Technology Price of Price of Quality Quality Speed Typical Usage
Machine Supplies of Text of
(for example, Printouts Image
ink and paper) Printout
s

Ink (black/white) $ ## ** * medium Home

Ink (color) $ ### *** *** slow Home

Dye-Sublimation $$$$$ #### ** **** slow- Photo labs

medium
Laser (black/white) $$-$$$$ # **** * fast- Small Office/
very fast Home Office
Laser (color) $$$- ## *** ** - medium- Office (for
$$$$$ *** fast example,
marketing
department)
 How to select a printer
In general, you should select a printer based on
your usage.
For a home office, a laser printer will offer the
lowest cost per page (cpp) of all printers,
making them economical in the long run, but
with a large up front cost for the equipment.
But, if you will not be printing many pages at
home, you might want to consider getting an ink-
jet printer.
 2.3 Storage Devices
2.3.1 Disk Controller Interfaces
2.3.2 Mass Storage

Assessments:
– Multiple-Choice Quiz 6
 Whys?
Why does a computer need to store files on a hard disk
drive?
Why not keep everything in RAM memory?
There are two reasons.
– RAM memory is volatile: the data is represented by electric
charges and is lost when the power is turned off. A hard disk
drive stores information as magnetized patches on the disk
surface, so the data persists even when power is removed.
– hard disk drives are useful is that they have a much larger
capacity than RAM. A typical personal computer today will have
at least 512 megabytes of RAM memory and 120 gigabytes of
disk storage. That disk capacity is more than 200 times what can
fit in RAM! So, even though hard disk drives are slow as
compared to RAM, they are an important component of your
computer system.
2.3.1 Disk Controller Interfaces
IDE Interface
EIDE Master/Slave
 common interfaces
There are many common interfaces to connect a storage
device to a computer.
– Universal Serial Bus (USB)
– FireWire.
Another common interface is Integrated Drive
Electronics (IDE ，集成驱动装置 ).
An IDE is the interface that enables data to transfer
between storage devices and the chipset.
IDE is designed specifically as disk interface
USB and FireWire can interface with other devices
besides storage devices such as digital cameras and
printers.
 Disk Controller Interfaces
Storage Devices
Microprocessor
(executes instructions)

Hard drive

I
CD-ROM D
Disk
E Main Memory
Controller (temporarily stores data
Chipset
PCI and program instructions
DVD-ROM (controls data flow)
while the computer
is running)

Legend

Component
Peripherals s
(input/output)
Data Path

Bus
 IDE Interface
Provides a standard way for storage devices to
connect to a computer
The controller for the IDE is
– usually integrated into the disk or CD-ROM drive, and
– the controller directs how the hard drive stores and
accesses data.
IDE was created as a way to standardize( 标准
化 ) the use of hard drives in computers by
combining the controller and the hard drive
– because having separate controllers and hard drives
resulted in poor signal quality and performance.
 IDE Interface
In 1984, IBM introduced the AT computer with a
hard drive had a combined drive and controller.
– A ribbon cable from the drive/controller combination is
used to connect to the system unit, creating the AT
Attachment (ATA) interface.
Soon, other vendors( 制造商 ) started offering
IDE drives based on the ATA standard
developed by IBM.
Thus, IDE became the term that covered the
entire range of integrated drive/controller
devices.
Because almost all IDE drives are ATA-based,
the two terms are used interchangeably.
EIDE is Enhanced IDE.
EIDE
Provides a set of two IDE (Integrated Device Electronics)
ports.
– Primary port and secondary port
– Each port attaches to a cable containing two plugs, and each plug
can connect to a device.
– Total of four devices can be accommodated: two on the primary,
and two on the secondary.

Primary Master Device

Primary IDE Port

Primary Slave Device

Secondary Master Device

Secondary IDE Port

Secondary Slave Device
2.3.2 Mass Storage 大容量存储
器
How Mass Storage Devices Differ from
RAM
Disk Drive Reliability
Optical Media: CDs versus DVDs
Magnetic Media
Optical v.s. Magnetic
Solid State
Comparing Storages
How Mass Storage Devices Differ
from RAM
Slowest access times
Low transfer rates
Located farther from processor
– Magnetic disks (Hard discs, floppy discs)
– Optical disks (CD-ROM)
– Magnetic tapes
Advantages of Mass storage devices:
– Non-volatile (data remains even after power is turned
off)
– High storage capacity (billions or trillions of bytes)
– Cost per bit is lower than RAM
– Use removable media in some cases
 Disk Drive Reliability
In order to achieve high data transfer
rates, a hard disk drive has to spin very
fast: from 4,000 to 15,000 rpm (revolutions
per minute).
Also, magnetic patches( 磁片 ) that
– store data bits on the hard disk
– tend to be small and packed closely together.
Therefore, in order to read these tiny little
bits spinning at such high speed
accurately, the read/write head has to be
very, very close to the disk surface.
 Disk Drive Reliability
The head rides on a cushion of air( 空气垫 ), and
the distance between it and the disk surface is
– far less than the width of a human hair —
– less than the size of a single dust particle.
In fact, if a head encounters a dust particle( 尘
粒 ) sitting on the surface of a disk while the disk
is spinning at several thousand rpm, the head
will crash into the disk, damaging itself and the
magnetic coating on the disk.
It is important to
– back up all data onto tape or another disk regularly.
 MTBF (Mean Time between
Failures, 平均无故障时间 )
Reliability of the computer component is
expressed as MTBF
Calculated by dividing the number of failures by
the total hours of observation.
MTBF is somewhat misleading to most
consumers. 不要光考虑 MTBF ，看看导致的后
果的严重性
– Effect of Hardware depends on the component fails.
– If RAM , monitor or microprocessor fails they can be
replaced.
– Hard Disc drive failure is serious as all the data are
lost.
 Optical Media( 光学介质 ):
CDs and DVDs
Advantages of optical technologies:
– Reliability: they are less prone to
environmental damages.
Usually used as a medium for multimedia
presentations that combine sound with
graphics, such as movies
A DVD is an enhanced form of a CD.
The two types of disks are physically the
same size, but they differ in format.
 DVDs
Greater capacity
Narrower tracks
– Use blue laser, which has a shorter wavelength than the
red laser used by CDs, allowing it to focus on the tinier
tracks of the DVD.
Use multiple layers of tracks
– Blue laser beams can penetrate( 穿透 ) the plastic and
focus at different depths
– Some are dual-layered- two sets of tracks on one side of
the disk, one beneath the other.
– This doubles the capacity of one side of a DVD disk.
A double layer double side (DLDS) DVD drive uses double
layers and can read double-sided disks, giving it four times
the capacity of a single layer single side (SLSS) drive.
 CDs
Two recordable formats, CD-R and CD-RW
Less expensive and have less capacity than a
DVD
Most expensive of the CD drives, are priced
about the same as a read-only DVD drive.
The more capable DVD-RW drives can be four
times the cost of a standard DVD drive.
Many computers (desktops and laptops) today
are equipped with CD-RWs and read-only DVD
combo drives.
 Magnetic Media( 磁介质 ): Zip
Disks
Magnetic media range from some of the smallest capacity
storage devices, floppy disks, to the largest capacity
devices, hard disk drives.
Zip disks
– Removable storage drives produced by Iomega, allow
users to store much larger amounts of data than a floppy
disk can hold
– Capacity ranges from 100, 250 to 750 MB
– Better option for graphics and large files.
– Were once very popular, and many machines can still be
purchased today with a Zip drive as standard equipment.
But, their use declined with the wide availability of CD-
RW drives and the reduced cost of blank CD-R disks.
 Optical v.s. Magnetic Media
Optical Media
– more durable( 耐久 ):
not ruined by dust or moisture,
nor are they vulnerable to electrical
damage
but can be damaged by physical damages
such as scratches( 刻划 )).
– MTBF rating (average life expectancy) ranges
between 30 and 300 years, while magnetic
media utilize magnetic properties that have a
MTBF of about 3–7 years.
– Less expensive per MB than magnetic disks
 Optical v.s. Magnetic Media
Magnetic Media
– Can be written and read faster than optical
disks (except for floppy disks)
– Most hard disk drives offer greater capacity
than any currently available optical device
 Solid State( 固态存储器 )
Solid-state memory, or flash memory, uses no moving parts
inside the chip.
Records data using electronic charges
Rewrites data by applying electric fields using in-circuit wiring
to erase predetermined sections of the chip so those areas
can be rewritten
CompactFlash and SmartMedia cards.
– CompactFlash card
Uses a controller chip, which can increase performance
on devices with slow processors and flash-memory
chips.
Storage capacity is between 4MB and 4GB
– SmartMedia card
Smaller and thinner than a matchbox
Storage capacity is between 2MB and 256MB ???
 Comparing Storages
There are many ways to store data.
For example, presently three types of CD drives
available, and five kinds of DVD drives.
The chart below lists the most common types of
storage available today.
Magnetic storage media
– can be read and written many times,
optical media
– some are read-only, and
– some are write-once (but they can be read many
times).
 Name Type Capacity Writability

High-density floppy disk Magnetic 1.44 MB Unlimited

SecureDigital card Solid state 4 MB - 2 GB Many

CompactFlash card Solid state 4 MB - 4 GB Many

Super floppy Magnetic 120 or 240 MB Unlimited

USB storage device (thumb Solid state 64, 128, 256 MB, Many
drive) or more
CompactFlash form factor Magnetic 340 MB, 1 GB, 4 Unlimited
— Microdrive GB
 Name Type Capacity Writability

Iomega Zip disk Magnetic 100, 250, or 750 MB Unlimited

CD-ROM Optical 650 or 700 MB Read only

CD-R Optical 650 or 700 MB Write once

CD-RW Optical 650 or 700 MB Many

Iomega Jaz disk Magnetic 1 or 2 GB Unlimited

DVD+/-R Optical 4.7 GB Write once

 Name Type Capacity Writability

DVD+/-RW Optical 4.7 GB Many

DVD+R DL (dual layer) Optical 8.5 GB Write once

DVD-ROM (SLSS) Optical 4.7 GB Read only

DVD-ROM (DLSS or Optical 8.5 GB Read only

SLDS)
DVD-ROM (DLDS) Optical 18.8 GB Read only

Internal hard disk drive Magneti 20 GB or more Unlimited

c
External hard disk drive Magneti 20 GB or more Unlimited
c
 ROM CPU RAM
cache

VRAM Regusters

network

Hard Drive
USB

Tape CD

Magnetic Storage

DVD
Storage Review
Optical Storage
 2.4 Putting Together the
Hardware Components
2.4.1 How Components Work Together.
2.4.2 Lab: Researching a Computer
System.
2.4.3 Lab: Online Configuration
2.4.1 How Components Work
Together
Working Together Microprocessor
CPU
Main Memory

(ALU, Registers, Control unit) RAM

Storage Devices
Storage Devices
(instructions to be
L1 cache
executed when the
L2 cache computer is running)
(usually on CPU)
Hard drive
F Boot Memory
s
r
o
i ROM
I d (instructions needed to
CD-ROM D n
E
Disk t
e boot the computer)
Controller
CMOS
PCI Memory (Configuration information
DVD-ROM Chipset used during the boot
process)

F Legend
Peripherals P i
Parallel Component
modem C U r
I S e PS-2 Memory
sound A W
B
card G i Port
P r
PCI Slots Expansion
e
Card
video
card
Expansion
USB FireWire Slot
AGP Slot
Peripheral
Device
Phone line Monitor Digital camera Camcorder Printer Bus
Speaker, microphone Scanner Mouse, keyboard Disk drive
Major Hardware Components and Their
Functionality
CPU executes instructions stored in memory devices.
During the boot process, the CPU fetches instructions
from the permanent memory devices, ROM and CMOS.
ROM is read-only memory that stores instructions
needed to start up the computer.
CMOS contains system configuration data.
Once the computer is booted, RAM is used to load the
rest of the instructions to be executed by the CPU.
Major Hardware Components and Their
Functionality
Data from storage devices such as the CD-ROM drive
and the hard drive are passed through the disk
controller. Data can also be stored on hard disk or CD.
Data in the hardware system passes through buses. The
buses are the communication channels among
components in the system unit.
Peripheral devices such as the keyboard, mouse,
joystick, printer, speakers, and microphone are
connected to the computer via ports typically in the back
of a system unit.
Expansion cards can be plugged into the expansion
slots of the computer to extend the functionality of a
computer.
 How Components Work
Together
When a computer processes requests from the user, the CPU
directs the other components to carry out specific tasks, and
data is passed among components through buses and the
chipset.
– To save a file to hard disk
the CPU would pass the data to be saved through the front
bus to the chipset.
The chipset sends the file data via the PCI bus to the disk
controller, which would then send the data to the hard disk
storage device.
– To open and display an image file
the CPU would signal the disk controller to fetch the image
file on the storage device using and store it in RAM.
The graphics card would then access the image data and
display the image as pixels on the computer monitor.
Lab: Researching a Computer
System
Researches done through product reviews
Price comparisons
Price and comparisons can be found at:
some web site
– www.pconline.com.cn
– www.it168.com
– www.zol.com.cn
 Lab: Online Configuration
Computer hardware vendors have their
own web sites
Sites specify system configurations of
various products
Priced by components
 2.5 Improving Computer
Performance
2.5.1 Moore's Law
2.5.2 Bottlenecks
2.5.3 Throughput and Latency

Assessments:
– Multiple-Choice Quiz 7
 2.5.1 Moore's Law
Law can be stated as:
Number of transistors on a microchip doubles every 18
months.
Denser the chip  Higher the capacity
Limitations: Chips must be thick enough for the electrons
to pass through.
Predictions based on Moore’s Law
– Processing power (speed) doubles every 18 months.
– Storage capacity of RAM increases exponentially.
Other observations:
– Storage capacity of hard disk drives is also increasing
exponentially( 指数增长 ).
– Cost for consumers to purchase computer parts is
decreasing over time.
 Moore’s Law (continued)
Moore's Law Applied to Intel Processors
100,000,000

10,000,000
Number of Transistors
(Log scaled)

1,000,000

100,000

10,000

1,000
1971 1972 1974 1978 1982 1985 1989 1993 1997 1999 2000
Year of Processor Introduction
 Parkinson’s Law of Data
Parkinson's Law of Data: Data expands
to fill the space available.
– As more memory or disk space becomes
available, the demand for more memory or
disk space increases accordingly.
– As Parkinson's Law predicts
today's operating systems are much more
elaborate and require more memory for their own
use.
– As disk drive capacity increases
people begin using them in new ways (e.g. storing
musical recordings, short video clips, and movies).
 2.5.2 Bottlenecks
Bottlenecks — Slowing a Process
Typical Bottlenecks
Eliminating Bottlenecks
Bottlenecks—Slowing a Process
Bottleneck is a step within a series of
steps that takes the longest time to
complete.
Time required to perform a task consisting
of several steps may be delayed by the
bottleneck step.
Process time cannot be shortened without
speeding up the bottleneck. 研究解决问
题的关键！
 Typical Bottlenecks
Typical bottlenecks:
– Cache
– RAM
– I/O
– Video card (particularly for 3-D gaming)
 Eliminating Bottlenecks
To speed up performance of a system:
– Use profiling tools( 测试工具 ) to
measure each section’s time taken to
complete to determine the bottleneck
steps
– Improve upon the bottleneck steps
2.5.3 Throughput and Latency
Throughput and Latency are two key terms used
in discussing computer performance.
– Throughput( 吞吐量 , 计算能力 ) refers to the
rate at which data flows through the system.
E.g., a computer might execute 500 million
instructions per second.
– Latency ( 响应时间、等待时间 ) refers to the
time required to complete an individual
operation.
E.g., it might take five seconds to launch an
application, or two minutes to reboot the
entire system.
These measures are clearly related
Suppose you want your Web server to
display a large graphic on a user's
computer when they press a button.
Latency is how much time passes
– from the button press
– until the image is displayed.
If the image is a 1 MB file, then with a
throughput of ten megabits per second,
the latency to display the image will be at
least 0.8 seconds.
 Whether latency or throughput is most
appropriate to report depends on the setting.
If you are selecting a provider for your Web
server's network connection,
– you will be more concerned with having
enough throughput, or bandwidth, to serve
your needs.
If you are a user of the same web server
– you will certainly be concerned with the
latency for your request.
– you does not matter to how many other
requests the server processes per second
(i.e., throughput).
– You are mainly concerned with your request.
 Whether latency or throughput is most
appropriate to report depends on the setting.
As a server administrator
– you might hear complaints from people whose
latency was exceedingly high, even though
your throughput was acceptable.
your server handles two different kinds of
requests:
– a request for a small file that can be sent quickly and
– a request for a large file that takes a long time to send.
If the vast majority of requests are for small files
– throughput and latency for small files may be
fine
– while the latency for large files may be
unacceptable.
 A simple way to think about
latency
is to model the time it takes to do a task as
being equal to
– some constant startup time,
+
– a time that scales with the size of the task.
END of Unit 2