Sunteți pe pagina 1din 30

home computer was the Intel 8080, a complete 8-bit computer

How Microprocessors Work on one chip, introduced in 1974. The first microprocessor to
make a real splash in the market was the Intel 8088, introduced
NEXT in 1979 and incorporated into the IBM PC (which first appeared
The computer you are using to around 1982). If you are familiar with the PC market and its
read this page uses history, you know that the PC market moved from the 8088 to
a microprocessor to do its work. the 80286 to the 80386 to the 80486 to the Pentium to the
The microprocessor is the heart Pentium II to the Pentium III to the Pentium 4. All of these
of any normal computer, whether microprocessors are made by Intel and all of them are
it is a desktop machine, improvements on the basic design of the 8088. The Pentium 4
a server or a laptop. The can execute any piece of code that ran on the original 8088, but
microprocessor you are using it does it
might be a Pentium, a K6, a about 5,000
PowerPC, a Sparc or any of the times faster!
many other brands and types of Since
microprocessors, but they all do 2004, Intel h
approximately the same thing in approximately the same way. as
A microprocessor -- also known as a CPU or central processing introduced
unit -- is a complete computation engine that is fabricated on a microproces
single chip. The first microprocessor was the Intel 4004, sors with
introduced in 1971. The 4004 was not very powerful -- all it multiple
could do was add and subtract, and it could only do that 4 bits at cores and
a time. But it was amazing that everything was on one chip. millions
Prior to the 4004, engineers built computers either from more transistors. But even these microprocessors follow the
collections of chips or from discrete components same general rules as earlier chips.
(transistors wired one at a time). The
4004 powered one of the first portable Additional information about the table on this page:
electronic calculators. The date is the year that the processor was first introduced.
Many processors are re-introduced at higher clock speeds
Microprocessor Progression: Intel for many years after the original release date.
The first microprocessor to make it into a

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 1
Mr. Jay-R C. Matibag
Transistors is the number of transistors on the chip. You can
see that the number of transistors on a single chip has risen
steadily over the years. A chip is also called an integrated circuit. Generally it is a small,
Microns is the width, in microns, of the smallest wire on the thin piece of silicon onto which the transistors making up the
chip. For comparison, a human hair is 100 microns thick. As the microprocessor have been etched. A chip might be as large as
feature size on the chip goes down, the number of transistors an inch on a side and can contain tens of millions of transistors.
Simpler processors might consist of a few thousand transistors
etched onto a chip just a few millimeters square.
Clock speed is the maximum rate that the chip can be clocked
at. Clock speed will make more sense in the next section. Microprocessor Logic
Data Width is the width of the ALU. An 8-bit ALU can
add/subtract/multiply/etc. two 8-bit numbers, while a 32-bit ALU
can manipulate 32-bit numbers. An 8-bit ALU would have to To understand how a
execute four instructions to add two 32-bit numbers, while a 32- microprocessor works, it is
helpful to look inside and
bit ALU can do it in one instruction. In many cases, the external learn about the logic used
data bus is the same width as the ALU, but not always. The to create one. In the
8088 had a 16-bit ALU and an 8-bit bus, while the modern process you can also learn
Pentiums fetch data 64 bits at a time for their 32-bit ALUs. about assembly
MIPS stands for "millions of instructions per second" and is a language -- the native
rough measure of the performance of a CPU. Modern CPUs can language of a
microprocessor -- and
do so many different things that MIPS ratings lose a lot of their
many of the things that
meaning, but you can get a general sense of the relative power engineers can do to boost the speed of a processor.
of the CPUs from this column.
A microprocessor executes a collection of machine instructions
From this table you can see that, in general, there is a
that tell the processor what to do. Based on the instructions, a
relationship between clock speed and MIPS. The maximum
clock speed is a function of the manufacturing process and microprocessor does three basic things:
delays within the chip. There is also a relationship between the
number of transistors and MIPS. For example, the 8088 clocked Using its ALU (Arithmetic/Logic Unit), a microprocessor
at 5 MHz but only executed at 0.33 MIPS (about one instruction can perform mathematical operations like addition,
per 15 clock cycles). Modern processors can often execute at a subtraction, multiplication and division. Modern
rate of two instructions per clock cycle. That improvement is microprocessors contain complete floating point
directly related to the number of transistors on the chip and will
make more sense in the next section.
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 2
Mr. Jay-R C. Matibag
processors that can perform extremely sophisticated This is about as simple as a microprocessor gets. This
operations on large floating point numbers. microprocessor has:
A microprocessor can move data from
one memory location to another. An address bus (that may be 8, 16 or 32 bits wide) that
A microprocessor can make decisions and jump to a new sends an address to memory
set of instructions based on those decisions. A data bus (that may be 8, 16 or 32 bits wide) that can
send data to memory or receive data from memory
There may be very sophisticated things that a microprocessor An RD (read) and WR (write) line to tell the memory
does, but those are its three basic activities. The following whether it wants to set or get the addressed location
diagram shows an extremely simple microprocessor capable of A clock line that lets a clock pulse sequence the
doing those three things: processor
A reset line that resets the program counter to zero (or
whatever) and restarts execution

Let's assume that both the address and data buses are 8 bits
wide in this example.

Here are the components of this simple microprocessor:

Registers A, B and C are simply latches made out of flip-

flops. (See the section on "edge-triggered latches"
in How Boolean Logic Works for details.)
The address latch is just like registers A, B and C.
The program counter is a latch with the extra ability to
increment by 1 when told to do so, and also to reset to
zero when told to do so.
The ALU could be as simple as an 8-bit adder (see the
section on adders in How Boolean Logic Works for

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 3
Mr. Jay-R C. Matibag
details), or it might be able to add, subtract, multiply and Tell the C register to latch the value currently output by
divide 8-bit values. Let's assume the latter here. the ALU
The test register is a special latch that can hold values Tell the program counter register to latch the value
from comparisons performed in the ALU. An ALU can currently on the data bus
normally compare two numbers and determine if they are Tell the address register to latch the value currently on
equal, if one is greater than the other, etc. The test the data bus
register can also normally hold a carry bit from the last Tell the instruction register to latch the value currently on
stage of the adder. It stores these values in flip-flops and the data bus
then the instruction decoder can use the values to make Tell the program counter to increment
decisions. Tell the program counter to reset to zero
There are six boxes marked "3-State" in the diagram. Activate any of the six tri-state buffers (six separate lines)
These are tri-state buffers. A tri-state buffer can pass a Tell the ALU what operation to perform
1, a 0 or it can essentially disconnect its output (imagine Tell the test register to latch the ALU's test bits
a switch that totally disconnects the output line from the Activate the RD line
wire that the output is heading toward). A tri-state buffer Activate the WR line
allows multiple outputs to connect to a wire, but only one
of them to actually drive a 1 or a 0 onto the line. Coming into the instruction decoder are the bits from the test
The instruction register and instruction decoder are register and the clock line,
responsible for controlling all of the other components. as well as the bits from the
instruction register.
Although they are not shown in this diagram, there would be
Microprocessor Memory
control lines from the instruction decoder that would:
Tell the A register to latch the value currently on the data
The previous section
bus talked about the address
Tell the B register to latch the value currently on the data and data buses, as well as
bus the RD and WR lines.
These buses and lines
connect either to RAM or

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 4
Mr. Jay-R C. Matibag
ROM -- generally both. In our sample microprocessor, we have microprocessor then begins executing the boot sector's
an address bus 8 bits wide and a data bus 8 bits wide. That instructions from RAM. The boot sector program will tell the
means that the microprocessor can address (28) 256 bytes of microprocessor to fetch something else from the hard disk into
memory, and it can read or write 8 bits of the memory at a time.
RAM, which the microprocessor then executes, and so on. This
Let's assume that this simple microprocessor has 128 bytes of
ROM starting at address 0 and 128 bytes of RAM starting at is how the microprocessor loads and executes the
address 128. entire operating system.

ROM stands for read-only memory. A ROM chip is programmed Microprocessor Performance and Trends
with a permanent collection of pre-set bytes. The address bus PREV NEXT
tells the ROM chip which byte to get and place on the data bus. The number of transistors available has a huge effect on the
When the RD line changes state, the ROM chip presents the performance of a processor. As seen earlier, a typical
selected byte onto the data bus. instruction in a processor like an 8088 took 15 clock cycles to
RAM stands for random-access memory. RAM contains bytes of
execute. Because of the design of the multiplier, it took
information, and the microprocessor can read or write to those
approximately 80 cycles just to do one 16-bit multiplication on
bytes depending on whether the RD or WR line is signalled.
One problem with today's RAM chips is that they forget the 8088. With more transistors, much more powerful multipliers
everything once the power goes off. That is why the computer capable of single-cycle speeds become possible.
needs ROM. More transistors also allow for a technology called pipelining.
By the way, nearly all computers contain In a pipelined architecture, instruction execution overlaps. So
some amount of ROM (it is possible to even though it might take five clock cycles to execute each
create a simple computer that contains
instruction, there can be five instructions in various stages of
no RAM -- many microcontrollers do this
execution simultaneously. That way it looks like one instruction
by placing a handful of RAM bytes on the
processor chip itself -- but generally completes every clock cycle.
impossible to create one that contains no
ROM). On a PC, the ROM is called Many modern processors have multiple instruction decoders,
the BIOS (Basic Input/Output System). When the each with its own pipeline. This allows for multiple instruction
microprocessor starts, it begins executing instructions it finds in streams, which means that more than one instruction can
the BIOS. The BIOS instructions do things like test the hardware complete during each clock cycle. This technique can be quite
in the machine, and then it goes to the hard disk to fetch complex to implement, so it takes lots of transistors.
the boot sector. This boot sector is another small program, and
the BIOS stores it in RAM after reading it off the disk. The
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 5
Mr. Jay-R C. Matibag
One reason why the world needs 64-bit processors is because
The trend in processor design has primarily been toward full 32- of their enlarged address spaces. Thirty-two-bit chips are often
bit ALUs with fast floating point processors built in and pipelined constrained to a maximum of 2 GB or 4 GB of RAM access.
execution with multiple instruction streams. The newest thing in That sounds like a lot, given that most home computers
processor design is 64-bit ALUs, and people are expected to currently use only 256 MB to 512 MB of RAM. However, a 4-GB
have these processors in their home PCs in the next decade. limit can be a severe problem for server machines and
There has also been a tendency toward special instructions (like machines running large databases. And even home
the MMX instructions) that make certain operations particularly machines will start bumping up against the 2 GB or 4 GB limit
efficient, and the addition of hardware virtual memory support pretty soon if current trends continue. A 64-bit chip has none of
and L1 caching on the processor chip. All of these trends push these constraints because a 64-bit RAM address space is
up the transistor count, leading to the multi-million transistor essentially infinite for the foreseeable future -- 2^64 bytes of
powerhouses available today. These processors can execute RAM is something on the order of a billion gigabytes of RAM.
about one billion instructions per second!
With a 64-bit address bus and wide, high-speed data buses on
64-bit Microprocessors the motherboard, 64-bit machines also offer faster I/O
PR (input/output) speeds to things like hard disk drives and video
Sixty-four-bit cards. These features can greatly increase system
processors have been performance.
with us since 1992, and Servers can definitely benefit from 64 bits, but what about
in the 21st century they normal users? Beyond the RAM solution, it is not clear that a
have started to become 64-bit chip offers "normal users" any real, tangible benefits at
mainstream. Both Intel the moment. They can process data (very complex data
and AMD have features lots of real numbers) faster. People doing video
introduced 64-bit chips, editing and people doing photographic editing on very large
and the Mac G5 sports images benefit from this kind of computing power. High-end
a 64-bit processor. Sixty-four-bit processors have 64-bit ALUs, games will also benefit, once they are re-coded to take
64-bit registers, 64-bit buses and so on. advantage of 64-bit features. But the average user who is

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 6
Mr. Jay-R C. Matibag
reading e-mail, browsing the Web and editing Word documents You already know that the computer in front of you has memory.
is not really using the processor in that way. What you may not know is that most of the electronic items you
use every day have some form of memory also. Here are just a
few examples of the many items that use memory:
How Computer Memory Works
Computer Memory Basics


When you think about it, it's amazing how many different types
of electronic memory you encounter in daily life. Many of them
have become an integral part of our vocabulary:

Dynamic RAM
Although memory is technically any form of electronic storage, it
Static RAM
is used most often to identify fast, temporary forms of storage. If
Flash memory
your computer's CPU had to constantly access the hard drive to
Memory Sticks
retrieve every piece of data it needs, it would operate very
Virtual memory
slowly. When the information is kept in memory, the CPU can
Video memory
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 7
Mr. Jay-R C. Matibag
access it much more quickly. Most forms of memory are basic information about storage devices, boot sequence,
intended to store data temporarily. security, Plug and Play (auto device recognition)
capability and a few other items.
As you can see in the diagram above, the CPU accesses
The computer loads the operating system (OS) from the
memory according to a distinct hierarchy. Whether it comes
hard drive into the system's RAM. Generally, the critical
from permanent storage (the hard drive) or input (the keyboard),
parts of the operating system are maintained in RAM as
most data goes in random access memory (RAM) first. The
long as the computer is on. This allows the CPU to have
CPU then stores pieces of data it will need to access, often in
immediate access to the operating system, which
a cache, and maintains certain special instructions in
enhances the performance and functionality of the overall
the register. We'll talk about cache and registers later.
All of the components in your computer, such as the CPU, the When you open an application, it is loaded into RAM. To
hard drive and the operating system, work together as a team, conserve RAM usage, many applications load only the
and memory is one of the most essential parts of this team. essential parts of the program initially and then load other
From the moment you turn your computer on until the time you pieces as needed.
shut it down, your CPU is constantly using memory. Let's take a After an application is loaded, any files that are opened
look at a typical scenario: for use in that application are loaded into RAM.
When you save a file and close the application, the file is
You turn the computer on. written to the specified storage device, and then it and
The computer loads data from read-only the application are purged from RAM.
memory (ROM) and performs a power-on self-
test (POST) to make sure all the major components are In the list above, every time something is loaded or opened, it is
functioning properly. As part of this test, the memory placed into RAM. This simply means that it has been put in the
controller checks all of the memory addresses with a computer's temporary storage area so that the CPU can
quick read/write operation to ensure that there are no access that information more easily. The CPU requests the data
errors in the memory chips. Read/write means that data it needs from RAM, processes it and writes new data back to
is written to a bit and then read from that bit. RAM in a continuous cycle. In most computers, this shuffling
The computer loads the basic input/output of data between the CPU and RAM happens millions of times
system (BIOS) from ROM. The BIOS provides the most every second. When an application is closed, it and any

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 8
Mr. Jay-R C. Matibag
accompanying files are usually purged (deleted) from RAM to quantities and then backing it up with larger quantities of
make room for new data. If the changed files are not saved to a less expensive memory.
permanent storage device before being purged, they are lost.
The cheapest form of read/write memory in wide use
One common question about desktop computers that comes up today is the hard disk. Hard disks provide large
all the time is, "Why does a computer need so many memory quantities of inexpensive, permanent storage. You can
systems?" buy hard disk space for pennies per megabyte, but it can
take a good bit of time (approaching a second) to read a
Types of Computer Memory
megabyte off a hard disk. Because storage space on a
A typical computer has: hard disk is so cheap and plentiful, it forms the final stage
of a CPUs memory hierarchy, called virtual memory.
Level 1 and level 2 caches
The next level of the hierarchy is RAM. We discuss RAM
Normal system RAM
in detail in How RAM Works, but several points about
Virtual memory
RAM are important here.
A hard disk
Fast, powerful CPUs need quick and easy access to The bit size of a CPU tells you how many bytes of
large amounts of data in order to maximize their information it can access from RAM at the same time.
performance. If the CPU cannot get to the data it needs, For example, a 16-bit CPU can process 2 bytes at a time
it literally stops and waits for it. Modern CPUs running at (1 byte = 8 bits, so 16 bits = 2 bytes), and a 64-bit CPU
speeds of about 1 gigahertz can consume massive can process 8 bytes at a time.
amounts of data -- potentially billions of bytes per Megahertz (MHz) is a measure of a CPU's processing
second. The problem that computer designers face is speed, or clock cycle, in millions per second. So, a 32-
that memory that can keep up with a 1-gigahertz CPU is bit 800-MHz Pentium III can potentially process 4 bytes
extremely expensive -- much more expensive than simultaneously, 800 million times per second (possibly
anyone can afford in large quantities. more based on pipelining)! The goal of the memory
Computer designers have solved the cost problem by system is to meet those requirements.
"tiering" memory -- using expensive memory in small A computer's system RAM alone is not fast enough to
match the speed of the CPU. That is why you need
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 9
Mr. Jay-R C. Matibag
a cache (discussed later). However, the faster RAM is, Burst mode depends on the expectation that data requested by
the better. Most chips today operate with a cycle rate of the CPU will be stored in sequential memory cells. The
50 to 70 nanoseconds. The read/write speed is typically a memory controller anticipates that whatever the CPU is working
function of the type of RAM used, such as DRAM, on will continue to come from this same series of memory
SDRAM, RAMBUS. We will talk about these various addresses, so it reads several consecutive bits of data together.
types of memory later. This means that only the first bit is subject to the full effect of
latency; reading successive bits takes significantly less time.
First, let's talk about system RAM.
The rated burst mode of memory is normally expressed as four
System RAM speed is controlled by bus width and bus speed.
numbers separated by dashes. The first number tells you the
Bus width refers to the number of bits that can be sent to the
number of clock cycles needed to begin a read operation; the
CPU simultaneously, and bus speed refers to the number of
times a group of bits can be sent each second. A bus second, third and fourth numbers tell you how many cycles are
cycle occurs every time data travels from memory to the CPU. needed to read each consecutive bit in the row, also known as
For example, a 100-MHz 32-bit bus is theoretically capable of the wordline. For example: 5-1-1-1 tells you that it takes five
sending 4 bytes (32 bits divided by 8 = 4 bytes) of data to the cycles to read the first bit and one cycle for each bit after that.
CPU 100 million times per second, while a 66-MHz 16-bit bus Obviously, the lower these numbers are, the better the
can send 2 bytes of data 66 million times per second. If you do
performance of the memory.
the math, you'll find that simply changing the bus width from 16
bits to 32 bits and the speed from 66 MHz to 100 MHz in our Burst mode is often used in conjunction with pipelining, another
example allows for three times as much data (400 million bytes means of minimizing the effects of latency. Pipelining organizes
versus 132 million bytes) to pass through to the CPU every data retrieval into a sort of assembly-line process. The memory
controller simultaneously reads one or more words from
memory, sends the current word or words to the CPU and writes
In reality, RAM doesn't usually operate at optimum
speed. Latency changes the equation radically. Latency refers one or more words to memory cells. Used together, burst mode
to the number of clock cycles needed to read a bit of and pipelining can dramatically reduce the lag caused by
information. For example, RAM rated at 100 MHz is capable of latency.
sending a bit in 0.00000001 seconds, but may take 0.00000005
So why wouldn't you buy the fastest, widest memory you can
seconds to start the read process for the first bit. To
compensate for latency, CPUs uses a special technique get? The speed and width of the memory's bus should match
called burst mode. the system's bus. You can use memory designed to work at 100

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 10
Mr. Jay-R C. Matibag
MHz in a 66-MHz system, but it will run at the 66-MHz speed of is very small, normally ranging between 2 kilobytes (KB) and 64
the bus so there is no advantage, and 32-bit memory won't fit on KB.
a 16-bit bus.
The secondary or level 2 cache typically resides on a memory
Even with a wide and fast bus, it still takes longer for data to get card located near the CPU. The level 2 cache has a direct
from the memory card to the CPU than it takes for the CPU to connection to the CPU. A dedicated integrated circuit on
actually process the data. That's where caches come in. the motherboard, the L2 controller, regulates the use of the
level 2 cache by the CPU. Depending on the CPU, the size of
the level 2 cache ranges from 256 KB to 2 megabytes (MB). In
Cache and Registers most systems, data needed by the CPU is accessed from the
cache approximately 95 percent of the time, greatly reducing the
overhead needed when the CPU has to wait for data from the
main memory.

Some inexpensive systems dispense with the level 2 cache

altogether. Many high performance CPUs now have the level 2
cache actually built into the CPU chip itself. Therefore, the size
of the level 2 cache and whether it is onboard (on the CPU) is a
major determining factor in the performance of a CPU. For more
details on caching. A particular type of RAM, static random
access memory (SRAM), is used primarily for cache. SRAM
uses multiple transistors, typically four to six, for each memory
cell. It has an external gate array known as a bistable
multivibrator that switches, or flip-flops, between two states.
Caches are designed to alleviate this bottleneck by making the This means that it does not have to be continually refreshed like
data used most often by the CPU instantly available. This is DRAM. Each cell will maintain its data as long as it has power.
accomplished by building a small amount of memory, known Without the need for constant refreshing, SRAM can operate
as primary or level 1 cache, right into the CPU. Level 1 cache
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 11
Mr. Jay-R C. Matibag
extremely quickly. But the complexity of each cell make it How RAM Works
prohibitively expensive for use as standard RAM.
Random access memory (RAM) is the best known form
The SRAM in the cache can of computer memory. RAM is
be asynchronous or synchronous. Synchronous SRAM is considered "random access"
designed to exactly match the speed of the CPU, while because you can access any
asynchronous is not. That little bit of timing makes a difference memory cell directly if you know
in performance. Matching the CPU's clock speed is a good the row and column that intersect
thing, so always look for synchronized SRAM. at that cell.
The final step in memory is the registers. These are memory The opposite of RAM is serial
cells built right into the CPU that contain specific data needed access memory (SAM). SAM
by the CPU, particularly the arithmetic and logic unit (ALU). stores data as a series of memory
An integral part of the CPU itself, they are controlled directly by cells that can only be accessed sequentially (like a cassette
the compiler that sends information for the CPU to process. tape). If the data is not in the current location, each memory cell
is checked until the needed data is found. SAM works very well
for memory buffers, where the data is normally stored in the
Memory can be split into two main categories: volatile and order in which it will be used (a good example is the texture
nonvolatile. Volatile memory loses any data as soon as the
system is turned off; it requires constant power to remain buffer memory on a video card). RAM data, on the other hand,
viable. Most types of RAM fall into this category. can be accessed in any order.
Nonvolatile memory does not lose its data when the system or Similar to a microprocessor, a memory chip is an integrated
device is turned off. A number of types of memory fall into this circuit (IC) made of millions of transistors and capacitors. In the
category. The most familiar is ROM, but Flash memory storage most common form of computer memory, dynamic random
devices such as CompactFlash or SmartMedia cards are also access memory (DRAM), a transistor and a capacitor are
forms of nonvolatile memory. paired to create a memory cell, which represents a single bit of
data. The capacitor holds the bit of information -- a 0 or a 1. The
transistor acts as a switch that lets the control circuitry on the
memory chip read the capacitor or change its state.

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 12
Mr. Jay-R C. Matibag
A capacitor is like a small bucket that is able to store electrons. DRAM works by sending a charge through the appropriate
To store a 1 in the memory cell, the bucket is filled with column (CAS) to activate the transistor at each bit in the
electrons. To store a 0, it is emptied. The problem with the column. When writing, the row lines contain the state the
capacitor's bucket is that it has a leak. In a matter of a few capacitor should take on. When reading, the sense-amplifier
milliseconds a full bucket becomes empty. Therefore, for determines the level of charge in the capacitor. If it is more than
dynamic memory to work, either the CPU or the memory 50 percent, it reads it as a 1; otherwise it reads it as a 0. The
controller has to come along and recharge all of the capacitors counter tracks the refresh sequence based on which rows have
holding a 1 before they discharge. To do this, the memory been accessed in what order. The length of time necessary to
controller reads the memory and then writes it right back. This do all this is so short that it is expressed
refresh operation happens automatically thousands of times per in nanoseconds (billionths of a second). A memory chip rating
second. of 70ns means that it takes 70 nanoseconds to completely read
and recharge each cell.
The capacitor in a dynamic RAM memory cell is like a leaky
bucket. It needs to be refreshed periodically or it will discharge Memory cells alone would be worthless without some way to get
to 0. This refresh operation is where dynamic RAM gets its information in and out of them. So the memory cells have a
name. Dynamic RAM has to be dynamically refreshed all of the whole support infrastructure of other specialized circuits. These
time or it forgets what it is holding. The downside of all of this circuits perform functions such as:
refreshing is that it takes time and slows down the memory.
Identifying each row and column (row address
In this article, you'll learn all about what RAM is, what kind you
select and column address select)
should buy and how to install it. See the next page to learn more
Keeping track of the refresh sequence (counter)
about dynamic RAM and memory cells.
Reading and restoring the signal from a cell (sense
Memory Cells and DRAM Telling a cell whether it should take a charge or not
(write enable)
Memory cells are etched onto a silicon wafer in an array of
columns (bitlines) and rows (wordlines). The intersection of a Other functions of the memory controller include a series of
bitline and wordline constitutes the address of the memory cell. tasks that include identifying the type, speed and amount of
memory and checking for errors.

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 13
Mr. Jay-R C. Matibag
Static RAM chips use a small outline J-lead (SOJ) pin configuration, but
quite a few manufacturers use the thin small outline
Static RAM uses a completely different technology. In static package (TSOP) configuration as well. The key difference
RAM, a form of flip-flop holds each bit of memory. A flip-flop for between these newer pin types and the original DIP
a memory cell takes four or six transistors along with some configuration is that SOJ and TSOP chips are surface-
wiring, but never has to be refreshed. This makes static RAM mounted to the PCB. In other words, the pins are soldered
significantly faster than dynamic RAM. However, because it has directly to the surface of the board, not inserted in holes or
more parts, a static memory cell takes up a lot more space on a sockets.
chip than a dynamic memory cell. Therefore, you get less
Memory chips are normally only available as part of a card
memory per chip, and that makes static RAM a lot more
called a module. You've probably seen memory listed as 8x32
or 4x16. These numbers represent the number of the chips
Static RAM is fast and expensive, and dynamic RAM is less multiplied by the capacity of each individual chip, which is
expensive and slower. So static RAM is used to create measured in megabits (Mb), or one million bits. Take the result
the CPU's speed-sensitive cache, while dynamic RAM forms the and divide it by eight to get the number of megabytes on that
larger system RAM space. module. For example, 4x32 means that the module has four 32-
Memory chips in desktop computers originally used a pin megabit chips. Multiply 4 by 32 and you get 128 megabits.
configuration called dual inline package (DIP). This pin Since we know that a byte has 8 bits, we need to divide our
configuration could be soldered into holes on the result of 128 by 8. Our result is 16 megabytes!
computer's motherboard or plugged into a socket that was Types of RAM
soldered on the motherboard. This method worked fine when
computers typically operated on a couple of megabytes or less The following are some common types of RAM:
of RAM, but as the need for memory grew, the number of chips
needing space on the motherboard increased. SRAM: Static random access memory uses multiple
transistors, typically four to six, for each memory cell but
The solution was to place the memory chips, along with all of
doesn't have a capacitor in each cell. It is used primarily
the support components, on a separate printed circuit
for cache.
board (PCB) that could then be plugged into a special
connector (memory bank) on the motherboard. Most of these

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 14
Mr. Jay-R C. Matibag
DRAM: Dynamic random access memory has memory bandwidth, meaning greater speed. Maximum transfer
cells with a paired transistor and capacitor requiring rate to L2 cache is approximately 1,064 MBps (for DDR
constant refreshing. SDRAM 133 MHZ).
FPM DRAM: Fast page mode dynamic random access RDRAM: Rambus dynamic random access memory is
memory was the original form of DRAM. It waits through a radical departure from the previous DRAM architecture.
the entire process of locating a bit of data by column and Designed by Rambus, RDRAM uses a Rambus in-line
row and then reading the bit before it starts on the next memory module (RIMM), which is similar in size and pin
bit. Maximum transfer rate to L2 cache is approximately configuration to a standard DIMM. What makes RDRAM
176 MBps. so different is its use of a special high-speed data bus
EDO DRAM: Extended data-out dynamic random called the Rambus channel. RDRAM memory chips work
access memory does not wait for all of the processing of in parallel to achieve a data rate of 800 MHz, or 1,600
the first bit before continuing to the next one. As soon as MBps. Since they operate at such high speeds, they
the address of the first bit is located, EDO DRAM begins generate much more heat than other types of chips. To
looking for the next bit. It is about five percent faster than help dissipate the excess heat Rambus chips are fitted
FPM. Maximum transfer rate to L2 cache is with a heat spreader, which looks like a long thin wafer.
approximately 264 MBps. Just like there are smaller versions of DIMMs, there are
SDRAM: Synchronous dynamic random access also SO-RIMMs, designed for notebook computers.
memory takes advantage of the burst mode concept to Credit Card Memory: Credit card memory is a
greatly improve performance. It does this by staying on proprietary self-contained DRAM memory module that
the row containing the requested bit and moving rapidly plugs into a special slot for use in notebook computers.
through the columns, reading each bit as it goes. The PCMCIA Memory Card: Another self-contained DRAM
idea is that most of the time the data needed by the CPU module for notebooks, cards of this type are not
will be in sequence. SDRAM is about five percent faster proprietary and should work with any notebook computer
than EDO RAM and is the most common form in whose system bus matches the memory card's
desktops today. Maximum transfer rate to L2 cache is configuration.
approximately 528 MBps. CMOS RAM: CMOS RAM is a term for the small amount
DDR SDRAM: Double data rate synchronous dynamic of memory used by your computer and some other
RAM is just like SDRAM except that is has higher devices to remember things like hard disk settings --

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 15
Mr. Jay-R C. Matibag
see Why does my computer need a battery? for details. Memory Modules
This memory uses a small battery to provide it with the
power it needs to maintain the memory contents.
VRAM: VideoRAM, also known as multiport dynamic
random access memory (MPDRAM), is a type of RAM
used specifically for video adapters or 3-D accelerators.
The "multiport" part comes from the fact that VRAM
normally has two independent access ports instead of
one, allowing the CPU and graphics processor to access
the RAM simultaneously. VRAM is located on the
graphics card and comes in a variety of formats, many of
which are proprietary. The amount of VRAM is a
determining factor in the resolution and color depth of the
display. VRAM is also used to hold graphics-specific
information such as 3-D geometry data and texture
The type of board and connector used for RAM
maps. True multiport VRAM tends to be expensive, so
today, many graphics cards use SGRAM (synchronous in desktop computers has evolved over the past few
graphics RAM) instead. Performance is nearly the same, years. The first types were proprietary, meaning that
but SGRAM is cheaper. different computer manufacturers developed memory
boards that would only work with their specific systems.
Then came SIMM, which stands for single in-line
memory module. This memory board used a 30-pin
connector and was about 3.5 x .75 inches in size (about
9 x 2 cm). In most computers, you had to install SIMMs in
pairs of equal capacity and speed. This is because the
width of the bus is more than a single SIMM. For
example, you would install two 8-megabyte (MB) SIMMs
to get 16 megabytes total RAM. Each SIMM could send 8

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 16
Mr. Jay-R C. Matibag
bits of data at one time, while the system bus could DIMMs, known as MicroDIMMs, which have either 144
handle 16 bits at a time. Later SIMM boards, slightly pins or 172 pins.
larger at 4.25 x 1 inch (about 11 x 2.5 cm), used a 72-pin
Most memory available today is highly reliable. Most
connector for increased bandwidth and allowed for up to
systems simply have the memory controller check for
256 MB of RAM.
errors at start-up and rely on that. Memory chips with
As processors grew in speed and bandwidth capability, built-in error-checking typically use a method known
the industry adopted a new standard in dual in-line as parity to check for errors. Parity chips have an extra
memory module (DIMM). With a whopping 168-pin or bit for every 8 bits of data. The way parity works is
184-pin connector and a size of 5.4 x 1 inch (about 14 x simple. Let's look at even parity first.
2.5 cm), DIMMs range in capacity from 8 MB to 1 GB per
When the 8 bits in a byte receive data, the chip adds up
module and can be installed singly instead of in pairs.
the total number of 1s. If the total number of 1s is odd,
Most PC memory modules and the modules for the Mac
the parity bit is set to 1. If the total is even, the parity bit is
G5 systems operate at 2.5 volts, while older Mac G4
set to 0. When the data is read back out of the bits, the
systems typically use 3.3 volts. Another
total is added up again and compared to the parity bit. If
standard, Rambus in-line memory module (RIMM), is
the total is odd and the parity bit is 1, then the data is
comparable in size and pin configuration to DIMM but
assumed to be valid and is sent to the CPU. But if the
uses a special memory bus to greatly increase speed.
total is odd and the parity bit is 0, the chip knows that
Many brands of notebook computers use there is an error somewhere in the 8 bits and dumps the
proprietary memory modules, but several manufacturers data. Odd parity works the same way, but the parity bit
use RAM based on the small outline dual in-line is set to 1 when the total number of 1s in the byte are
memory module (SODIMM) configuration. SODIMM even.
cards are small, about 2 x 1 inch (5 x 2.5 cm), and have
The problem with parity is that it discovers errors but
144 or 200 pins. Capacity ranges from 16 MB to 1 GB
does nothing to correct them. If a byte of data does not
per module. To conserve space, the Apple iMac desktop
match its parity bit, then the data are discarded and the
computer uses SODIMMs instead of the traditional
system tries again. Computers in critical positions need a
DIMMs. Sub-notebook computers use even smaller
higher level of fault tolerance. High-end servers often
have a form of error-checking known as error-correction
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 17
Mr. Jay-R C. Matibag
code (ECC). Like parity, ECC uses additional bits to
monitor the data in each byte. The difference is that ECC ROM Types
uses several bits for error checking -- how many depends
There are five basic ROM types:
on the width of the bus -- instead of one. ECC memory
uses a special algorithm not only to detect single bit ROM
errors, but actually correct them as well. ECC memory PROM
will also detect instances when more than one bit of data EPROM
in a byte fails. Such failures are very rare, and they are EEPROM
not correctable, even with ECC. Flash memory
The majority of computers sold today
Each type has unique characteristics, which you'll learn about
use nonparity memory chips. These chips do not
in this article, but they are all types of memorywith two things
provide any type of built-in error checking, but instead in common:
rely on the memory controller for error detection.
Data stored in these chips is nonvolatile -- it is not lost
How ROM Works
when power is removed.
Read-only memory (ROM), also Data stored in these chips is either unchangeable or
known as firmware, is an requires a special operation to change (unlike RAM,
integrated circuit programmed with which can be changed as easily as it is read).
specific data when it is
manufactured. ROM chips are ROM at Work
used not only in computers, but in
Similar to RAM, ROM chips (Figure 1)
most other electronic items as well.
contain a grid of columns and rows.
But where the columns and rows
In this article, you will learn about intersect, ROM chips are
the different types of ROM and how each works. This article is fundamentally different from RAM
one in a series of articles dealing with computer memory, chips. While RAM uses transistors to
including: turn on or off access to a capacitor at each intersection, ROM

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 18
Mr. Jay-R C. Matibag
uses a diode to connect the lines if the value is 1. If the value is about the size of your fingernail, contains the 30-second song
clips in ROM and the control codes to synchronize
0, then the lines are not connected at all.
the motors to the music.
A diode normally allows current to flow in only one direction and
has a certain threshold, known as the forward breakover, that PROM
determines how much current is required before the diode will
Creating ROM chips
pass it on. In silicon-based items such as processors and
totally from scratch
memory chips, the forward breakover voltage is approximately is time-consuming
0.6 volts. By taking advantage of the unique properties of a and very expensive
diode, a ROM chip can send a charge that is above the forward in small quantities.
breakover down the appropriate column with the selected row For this reason,
grounded to connect at a specific cell. If a diode is present at mainly, developers
that cell, the charge will be conducted through to the ground, created a type of
ROM known as programmable read-only memory (PROM).
and, under the binary system, the cell will be read as being "on"
Blank PROM chips can be bought inexpensively and coded by
(a value of 1). The neat part of ROM is that if the cell's value is
anyone with a special tool called a programmer.
0, there is no diode at that intersection to connect the column
and row. So the charge on the column does not get transferred PROM chips (Figure 2) have a grid of columns and rows just as
to the row. ordinary ROMs do. The difference is that every intersection of a
As you can see, the way a ROM chip works necessitates the column and row in a PROM chip has a fuse connecting them. A
programming of perfect and complete data when the chip is charge sent through a column will pass through the fuse in a cell
created. You cannot reprogram or rewrite a standard ROM chip. to a grounded row indicating a value of 1. Since all the cells
If it is incorrect, or the data needs to be updated, you have to have a fuse, the initial (blank) state of a PROM chip is all 1s. To
throw it away and start over. Creating the original template for a
change the value of a cell to 0, you use a programmer to send a
ROM chip is often a laborious process full of trial and error. But
specific amount of current to the cell. The higher voltage breaks
the benefits of ROM chips outweigh the drawbacks. Once the
template is completed, the actual chips can cost as little as a the connection between the column and row by burning out the
few cents each. They use very little power, are extremely fuse. This process is known as burning the PROM.
reliable and, in the case of most small electronic devices,
contain all the necessary programming to control the device. A
great example is the small chip in the singing fish toy. This chip,
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 19
Mr. Jay-R C. Matibag
PROMs can only be programmed once. They are more fragile the column (bitline), enters the floating gate and drains to a
than ROMs. A jolt of static electricity can easily cause fuses in
the PROM to burn out, changing essential bits from 1 to 0. But
blank PROMs are inexpensive and are great for prototyping the
data for a ROM before committing to the costly ROM fabrication This charge causes the floating-gate transistor to act like
process. an electron gun. The excited electrons are pushed through and
trapped on the other side of the thin oxide layer, giving it a
negative charge. These negatively charged electrons act as a
barrier between the control gate and the floating gate. A device
Working with ROMs and PROMs can be a wasteful business. called a cell sensor monitors the level of the charge passing
through the floating gate. If the flow through the gate is greater
Even though they are inexpensive per chip, the cost can add up
than 50 percent of the charge, it has a value of 1. When the
over time. Erasable programmable read-only charge passing through drops below the 50-percent threshold,
memory (EPROM) addresses this issue. EPROM chips can be the value changes to 0. A blank EPROM has all of the gates
rewritten many times. Erasing an EPROM requires a special fully open, giving each cell a value of 1.
tool that emits a certain frequency of ultraviolet (UV)
light. EPROMs are configured using an EPROM programmer To rewrite an EPROM, you must erase it first. To erase it, you
that provides voltage at specified levels depending on the type must supply a level of energy strong enough to break through
of EPROM used. the negative electrons blocking the floating gate. In a
Once again we have a grid of columns and rows. In an EPROM, standard EPROM, this is best accomplished with UV light at a
the cell at each intersection has two transistors. The two frequency of 253.7. Because this particular frequency will not
transistors are separated from each other by a thin oxide layer. penetrate most plastics or glasses, each EPROM chip has a
One of the transistors is known as the floating gate and the quartz window on top of it. The EPROM must be very close to
other as the control gate. The floating gate's only link to the the eraser's light source, within an inch or two, to work properly.
row (wordline) is through the control gate. As long as this link is An EPROM eraser is not selective, it will erase the
in place, the cell has a value of 1. To change the value to 0 entire EPROM. The EPROM must be removed from the device
requires a curious process called Fowler-Nordheim it is in and placed under the UV light of the EPROM eraser for
tunneling. Tunneling is used to alter the placement of several minutes. An EPROM that is left under too long can
electrons in the floating gate. An electrical charge, usually 10 to become over-erased. In such a case, the EPROM's floating
13 volts, is applied to the floating gate. The charge comes from
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 20
Mr. Jay-R C. Matibag
gates are charged to the point that they are unable to hold the Manufacturers responded to this limitation with Flash memory,
electrons at all. a type of EEPROM that uses in-circuit wiring to erase by
applying an electrical field to the entire chip or to predetermined
EEPROMs and Flash Memory sections of the chip called blocks. Flash memory works much
faster than traditional EEPROMs because it writes data in
Though EPROMs are a big step up from PROMs in terms of chunks, usually 512 bytes in size, instead of 1 byte at a time.
reusability, they still require dedicated equipment and a labor-
intensive process to remove and reinstall them each time a What is Dual Channel Mode?
change is necessary. Also, changes cannot be made
incrementally to an EPROM; the whole chip must be Is Dual Channel mode something that I need?
erased. Electrically erasable programmable read-only "Dual Channel Mode" is a feature that was created to reduce
memory (EEPROM) chips remove the biggest drawbacks of the potential performance bottleneck that exists between the
EPROMs. CPU and the Memory Controller. It is enabled when a pair of
same-size memory modules are installed into matching banks,
In EEPROMs: usually color coded on the motherboard. Based on our own
experience, dual channel mode provides about a 5-10%
The chip does not have to removed to be rewritten. increase in performance in most games and applications.
The entire chip does not have to be completely erased to Unless specifically required in rare cases, combining memory
change a specific portion of it. modules of different sizes in the same machine is compatible
and will not affect system stability or reliability in any way.
Changing the contents does not require additional
Most people will not realise any difference if dual channel mode
dedicated equipment.
is enabled or not, but if you are looking for absolute best
performance, then dual channel mode does provide a slight
Instead of using UV light, you can return the electrons in the performance increase.
cells of an EEPROM to normal with the localized application of What is Dual Channel DDR Memory?
an electric field to each cell. This erases the targeted cells of
There is a common misconception surrounding the term dual
the EEPROM, which can then be rewritten. EEPROMs are channel DDR. The same DDR memory modules that can be
changed 1 byte at a time, which makes them versatile but slow. used in any DDR based system can be used in any dual
In fact, EEPROM chips are too slow to use in many products channel system. Although referred to as dual channel DDR
memory, it is the systems themselves that are released with
that make quick changes to the data stored on the chip. either single memory channels or dual memory channels. Dual

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 21
Mr. Jay-R C. Matibag
memory channel designs double the peak bandwidth over need to be upgraded in like pairs. If you intend to fully utilize the
equivalent systems that only offer single memory channels. dual channel features, we recommend purchasing and installing
Many of the new systems released as dual channel allow the two like memory modules (one for channel A, and one for
end user to run the system in either single channel OR dual channel B) now to insure like parts. This should eliminate a
channel memory mode. potential future headache when deciding to upgrade from single
channel to dual channel operation.
Here is an example of how it works: In single channel memory
systems, the memory modules are all installed on one channel, A Good Rule of Thumb for Upgrading a Dual Channel DDR
with only one access route to the memory controller (the official Based System
communicator between the installed memory and the rest of the
Single Channel Operation: Install one or two modules (mixed or
same capacities), but install modules in only one bank.
Dual Channel Operation: Install in like pairs (same
speed/capacity*), in first slot of each bank. Second set of
modules should also be installed in like pairs (same
speed/capacity*) in second slot of each bank. The module pair
in the first set of slots does not need to be the same capacity as
the module pair in the second set of slots.
In dual channel memory systems, the memory modules are
installed on two separate channels, each with its own access * If like speeds or like capacities (or the combination of both) are
route to the memory controller, thus doubling the peak data not installed, the system will automatically revert to single
bandwidth. channel operation, regardless of module

How Motherboards Work

If you've ever taken the case off
of a computer, you've seen the
one piece of equipment that ties
everything together -- the
What is Important to Know About Dual Channel DDR motherboard. A motherboard
Memory Upgrades? allows all the parts of your
Many dual channel based systems can run in either single computer to receive power and
channel or dual channel mode. In order to take full advantage of communicate with one another.
the system running in dual channel mode, the memory modules
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 22
Mr. Jay-R C. Matibag
Motherboards have come a long way in the last twenty years. performance is either part of the motherboard or plugs into it via
The first motherboards held very few actual components. The a slot or port.
first IBM PC motherboard had only a processor and card slots.
The shape and layout of a motherboard is called the form factor.
Users plugged components like floppy drive controllers
The form factor affects where individual components go and the
and memory into the slots.
shape of the computer's case. There are several specific form
factors that most PC motherboards use so that they can all fit in
Form Factor standard cases. For a comparison of form factors, past and

The form factor is just one of the many standards that apply to
motherboards. Some of the other standards include:

The socket for the microprocessor determines what

kind of Central Processing Unit (CPU) the motherboard
The chipset is part of the motherboard's logic system
and is usually made of two parts -- the northbridge and
the southbridge. These two "bridges" connect the CPU to
other parts of the computer.
The Basic Input/Output System (BIOS) chip controls the
most basic functions of the computer and performs a self-
test every time you turn it on. Some systems feature dual
A motherboard by itself is useless, but a computer has to have BIOS, which provides a backup in case one fails or in
one to operate. The motherboard's main job is to hold the case of error during updating.
computer's microprocessor chip and let everything else connect The real time clock chip is a battery-operated chip that
to it. Everything that runs the computer or enhances its maintains basic settings and the system time.

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 23
Mr. Jay-R C. Matibag
The slots and ports found on a motherboard include: Redundant Array of Independent Discs (RAID) controllers
allow the computer to recognize multiple drives as one
Peripheral Component Interconnect (PCI)- connections drive.
for video, sound and video capture cards, as well as PCI Express is a newer protocol that acts more like a
network cards network than a bus. It can eliminate the need for other
Accelerated Graphics Port (AGP) - dedicated port for ports, including the AGP port.
video cards. Rather than relying on plug-in cards, some motherboards
Integrated Drive Electronics (IDE) - interfaces for the have on-board sound, networking, video or other
hard drives peripheral support.
Universal Serial Bus or FireWire - external peripherals
Memory slots Many people think of the CPU as one of the most important
parts of a computer. We'll look at how it affects the rest of the
computer in the next section.

Memory and Other Features

We've established that the
speed of the processor itself
controls how quickly a
computer thinks. The speed
of the chipset and busses
controls how quickly it can
communicate with other parts
of the computer. The speed
of the RAM connection
directly controls how fast the computer can access instructions
and data, and therefore has a big effect on system performance.
A fast processor with slow RAM is going nowhere.
Some motherboards also incorporate newer technological

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 24
Mr. Jay-R C. Matibag
The amount of memory available also controls how much data video, sound support and RAID controllers.
the computer can have readily available. RAM makes up the
Motherboards with all the bells and whistles are convenient and
bulk of a computer's memory. The general rule of thumb is the
simple to install. There are motherboards that have everything
more RAM the computer has, the better.
you need to create a complete computer -- all you do is stick the
Much of the memory available today is dual data rate (DDR) motherboard in a case and add a hard disk, a CD drive and a
memory. This means that the memory can transmit data twice power supply. You have a completely operational computer on a
per cycle instead of once, which makes the memory faster. single board.
Also, most motherboards have space for multiple memory chips,
For many average users, these built-in features provide ample
and on newer motherboards, they often connect to the
support for video and sound. For avid gamers and people who
northbridge via a dual bus instead of a single bus. This further
do high-intensity graphic or computer-aided design (CAD) work,
reduces the amount of time it takes for the processor to get
however, separate video cards provide much better
information from the memory.
A motherboard's memory
slots directly affect what
kind and how much
memory is supported.
How Graphics Cards Work
Just like other
components, the
memory plugs into the
slot via a series of pins.
The memory module must have the right number of pins to fit
into the slot on the motherboard.

In the earliest days of

motherboards, virtually everything
other than the processor came on
a card that plugged into the
board. Now, motherboards
feature a variety of onboard
accessories such as LANsupport,
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 25
Mr. Jay-R C. Matibag
The images you see on your monitor are made of tiny dots Creating an image out of binary data is a demanding process.
called pixels. At most common resolution settings, a screen To make a 3-D image, the graphics card first creates a wire
displays over a million pixels, and the computer has to decide frame out of straight lines. Then, it rasterizes the image (fills in
what to do with every one in order to create an image. To do the remaining pixels). It also adds lighting, texture and color. For
this, it needs a translator -- something to take binary data from fast-paced games, the computer has to go through this process
the CPU and turn it into a picture you can see. Unless a about sixty times per second. Without a graphics card to
computer has graphics capability built into the motherboard, that perform the necessary calculations, the workload would be too
translation takes place on the graphics card. much for the computer to handle.

A graphics card's job is complex, but its principles and The graphics card accomplishes this task using four main
components are easy to understand. In this article, we will look components:
at the basic parts of a video card and what they do. We'll also
examine the factors that work together to make a fast, efficient A motherboard connection for data and power
graphics card. A processor to decide what to do with each pixel on the
Memory to hold information about each pixel and to
Think of a computer as a company with its own art department.
temporarily store completed pictures
When people in the company want a piece of artwork, they send
A monitor connection so you can see the final result
a request to the art department. The art department decides
how to create the image and then puts it on paper. The end
result is that someone's idea becomes an actual, viewable The GPU

A graphics card works along the same principles. The CPU,

working in conjunction with software applications, sends
information about the image to the graphics card. The graphics
card decides how to use the pixels on the screen to create the
image. It then sends that information to the monitor through a

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 26
Mr. Jay-R C. Matibag
Like a motherboard, a graphics card is a printed circuit board location on the screen. Part of the RAM can also act as a frame
that houses a processor and RAM. It also has an input/output buffer, meaning that it holds completed images until it is time to
system (BIOS) chip, which stores the card's settings and display them. Typically, video RAM operates at very high
performs diagnostics on the memory, input and output at speeds and is dual ported, meaning that the system can read
startup. A graphics card's processor, called a graphics from it and write to it at the same time.
processing unit (GPU), is similar to a computer's CPU. A GPU,
The RAM connects directly to the digital-to-analog converter,
however, is designed specifically for performing the complex
called the DAC. This converter, also called the RAMDAC,
mathematical and geometric calculations that are necessary for
translates the image into an analog signal that the monitor can
graphics rendering. Some of the fastest GPUs have more
use. Some cards have multiple RAMDACs, which can improve
transistors than the average CPU. A GPU produces a lot of
performance and support more than one monitor.
heat, so it is usually located under a heat sink or a fan.

In addition to its processing power, a GPU uses special

programming to help it analyze and use
data. ATI and nVidia produce the vast majority of GPUs on the Graphics cards have come a long way since IBM
introduced the first one in 1981. Called a Monochrome
market, and both companies have developed their own Display Adapter (MDA), the card provided text-only
enhancements for GPU performance. To improve image quality, displays of green or white text on a black screen. Now, the
the processors use: minimum standard for new video cards is Video Graphics
Array (VGA), which allows 256 colors. With high-
performance standards like Quantum Extended Graphics
Full scene anti aliasing (FSAA), which smoothes the Array (QXGA), video cards can display millions of colors at
edges of 3-D objects resolutions of up to 2040 x 1536 pixels.
Anisotropic filtering (AF), which makes images look

Each company has also developed specific techniques to

help the GPU apply colors, shading, textures and patterns.

As the GPU creates images, it needs somewhere to hold

information and completed pictures. It uses the card's RAM for
this purpose, storing data about each pixel, its color and its
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 27
Mr. Jay-R C. Matibag
PCI Connection PCIe also supports the use of two graphics cards in the same

Most graphics cards have two monitor connections. Often, one

is a DVI connector, which supports LCD screens, and the other
is a VGA connector, which supports CRT screens. Some
graphics cards have two DVI connectors instead. But that
doesn't rule out using a CRT screen; CRT screens can connect
to DVI ports through an adapter. At one time, Apple made
monitors that used the proprietary Apple Display Connector
(ADC). Although these monitors are still in use, new Apple
monitors use a DVI connection.

Most people use only one of their two monitor connections.

People who need to use two monitors can purchase a graphics
Graphics cards connect to the computer through the
card with dual head capability, which splits the display
motherboard. The motherboard supplies power to the card and
between the two screens. A computer with two dual head, PCIe-
lets it communicate with the CPU. Newer graphics cards often
enabled video cards could theoretically support four monitors.
require more power than the motherboard can provide, so they
also have a direct connection to the computer's power supply. In addition to connections for the motherboard and monitor,
some graphics cards have connections for:
Connections to the motherboard are usually through one of
three interfaces: TV display: TV-out or S-video
Analog video cameras: ViVo or video in/video out
Peripheral component interconnect (PCI)
Digital cameras: FireWire or USB
Advanced graphics port (AGP)

PCI Express is the newest of the three and provides the fastest
DirectX and Open GL are application programming
transfer rates between the graphics card and the motherboard. interfaces, or APIs. An API helps hardware and software
communicate more efficiently by providing instructions for
Computer System Servicing Grade 12
Almond Academy Foundation Incorporated Page 28
Mr. Jay-R C. Matibag
complex tasks, like 3-D rendering. Developers optimize computer's case. Lots of high-performance video cards are
graphics-intensive games for specific APIs. This is why the
newest games often require updated versions of DirectX or illustrated or have decorative fans or heat sinks.
Open GL to work correctly. But a high-end card provides more power than most people
APIs are different from drivers, which are programs that allow really need. People who use their computers primarily for e-
hardware to communicate with a computer's operating system. mail, word processing or Web surfing can find all the necessary
But as with updated APIs, updated device drivers can help graphics support on a motherboard with integrated graphics. A
programs run correctly. mid-range card is sufficient for most casual gamers. People who
need the power of a high-end card include gaming enthusiasts
and people who do lots of 3-D graphic work.
Choosing a Good Graphics Card

A good overall measurement of a card's performance is

its frame rate, measured in frames per second (FPS). The
frame rate describes how many complete images the card can
display per second. The human eye can process about 25
frames every second, but fast-action games require a frame rate
of at least 60 FPS to provide smooth animation and scrolling.
Components of the frame rate are:

Triangles or vertices per second: 3-D images are

made of triangles, or polygons. This measurement
describes how quickly the GPU can calculate the whole
polygon or the vertices that define it. In general, it
describes how quickly the card builds a wire frame
A top-of-the-line graphics card is easy to spot. It has lots image.
of memory and a fast processor. Often, it's also more visually Pixel fill rate: This measurement describes how many
appealing than anything else that's intended to go inside a pixels the GPU can process in a second, which translates
to how quickly it can rasterize the image.

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 29
Mr. Jay-R C. Matibag
The graphics card's hardware directly affects its speed. These overheating. While overclocking can lead to better performance,
are the hardware specifications that most affect the card's it also voids the manufacturer's warranty.
speed and the units in which they are measured:

GPU clock speed (MHz)

Size of the memory bus (bits)
Amount of available memory (MB)
Memory clock rate (MHz)
Memory bandwidth (GB/s)
RAMDAC speed (MHz)

The computer's CPU and motherboard also play a part, since a

very fast graphics card can't compensate for a motherboard's
inability to deliver data quickly. Similarly, the card's connection
to the motherboard and the speed at which it can get
instructions from the CPU affect its performance.


Many motherboards have integrated graphics capabilities
and function without a separate graphics card. These
motherboards handle 2-D images easily, so they are ideal
for productivity and Internet applications. Plugging a
separate graphics card into one of these motherboards
overrides the onboard graphics functions.

Some people choose to improve their graphics card's

performance by manually setting their clock speed to a higher
rate, known as overclockings. People usually overclock
their memory, since overclocking the GPU can lead to

Computer System Servicing Grade 12

Almond Academy Foundation Incorporated Page 30
Mr. Jay-R C. Matibag