Mp4-Introduction to Intel 80x86 Microprocessor Family

1

COM 353 MicroprocessorsLecture 4

COM 353 MicroprocessorsLecture 4

Prof. Dr. Halûk Gümüş[email protected]

[email protected] http://www.gumuskaya.com

Computer Engineering Department

Monday, November 12, 2012

Introduction to Intel 80x86 Microprocessor Family

OBJECTIVESthis lecture enables the student to:• Describe the Intel family of microprocessors from

8085 to Pentium.– In terms of bus size, physical memory & special features.

• Explain the function of the EU (execution unit) and BIU (bus interface unit).

• Describe pipelining and how it enables the CPUto work faster.

OBJECTIVESthis lecture enables the student to:Registers• Describe function and purpose of each program-

visible register in the 8086-Core2 microprocessors, including 64-bit extensions.

• List the bits of the flag register and briefly state the purpose of each bit.

OBJECTIVESthis lecture enables the student to:Memory Architecture• State the purpose of the code segment, data

segment, stack segment, and extra segment.• Explain the difference between a logical address

and a physical address.• Describe how memory is accessed using real and

protected mode memory-addressing techniques.• Describe the "little endian" storage convention

of x86 microprocessors.• State the purpose of the stack.• Explain the function of PUSH and POP instructions.

(cont)

1. Brief History of the x86 Family2. Typical Pins of the x86 Processor3. Internal Processor Architecture4. Memory Architecture5. I/O Operations6. The Microprocessor-Based Personal Computer System

Lecture Outline

BRIEF HISTORY OF THE x86 FAMILY Evolution from 8080/8085 to 8086• In 1978, Intel Corporation introduced the 16-bit

8086 microprocessor, a major improvement over the previous generation 8080/8085 series.– The 8086 capacity of 1 megabyte of memory exceeded

the 8080/8085 maximum of 64K bytes of memory.– 8080/8085 was an 8-bit system, which could work on

only 8 bits of data at a time.• Data larger than 8 bits had to be broken into 8-bit pieces

to be processed by the CPU.– 8086 was a pipelined processor, as opposed to the

nonpipelined 8080/8085.

BRIEF HISTORY OF THE x86 FAMILY Evolution from 8080/8085 to 8086

BRIEF HISTORY OF THE x86 FAMILY Evolution from 8086 to 8088• The 8086 microprocessor has a 16-bit data bus,

internally and externally.– All registers are 16 bits wide, and there is a 16-bit

data bus to transfer data in and out of the CPU• There was resistance to a 16-bit external bus as

peripherals were designed around 8-bit processors.• A printed circuit board with a 16-bit data also bus cost more.

• As a result, Intel came out with the 8088 version.– Identical to the 8086, but with an 8-bit data bus.

• Picked up by IBM as the microprocessor in designing the PC.

BRIEF HISTORY OF THE x86 FAMILY Success of the 8088• The 8088-based IBM PC was an great success,

because IBM & Microsoft made it an open system.– Documentation and specifications of the hardware

and software of the PC were made public• Making it possible for many vendors to clone the hardware

successfully & spawn a major growth in both hardware and software designs based on the IBM PC.

BRIEF HISTORY OF THE x86 FAMILY 80286, 80386, and 80486• Intel introduced the 80286 in 1982, which IBM

picked up for the design of the PC AT.– 16-bit internal & external data buses.– 24 address lines, for 16mb memory. (224 = 16mb)– Virtual memory.

• 80286 can operate in one of two modes:– Real mode - a faster 8088/8086 with the same maximum

of 1 megabyte of memory.– Protected mode - which allows for 16M of memory.

• Also capable of protecting the operating system & programs from accidental or deliberate destruction by a user.

BRIEF HISTORY OF THE x86 FAMILY 80286, 80386, and 80486• Virtual memory is a way of

fooling the processor into thinking it has access to an almost unlimited amount of memory.– By swapping data between disk

storage and RAM.

BRIEF HISTORY OF THE x86 FAMILY 80286, 80386, and 80486• In 1985 Intel introduced 80386 (or 80386DX).

– 32-bit internally/externally, with a 32-bit address bus.– Capable of handling memory of up to 4 gigabytes. (232)– Virtual memory increased to 64 terabytes. (246)

• Later Intel introduced 386SX, internally identical, but with a 16-bit external data bus & 24-bit address bus.– This makes the 386SX system much cheaper.

• Since general-purpose processors could not handle mathematical calculations rapidly, Intel introduced numeric data processing chips.– Math coprocessors, such as 8087, 80287, 80387.

BRIEF HISTORY OF THE x86 FAMILY 80286, 80386, and 80486• On the 80486, in 1989, Intel put a greatly enhanced

80386 & math coprocessor on a single chip.– Plus additional features such as cache memory.

• Cache memory is static RAM with a very fast access time.

• All programs written for the 8088/86 will run on286, 386, and 486 computers.

BRIEF HISTORY OF THE x86 FAMILY 80286, 80386, and 80486

BRIEF HISTORY OF THE x86 FAMILY Pentium® & Pentium® Pro• In 1992, Intel released the Pentium®. (not 80586)

– A name can be copyrighted, but numbers cannot.• On release, Pentium® had speeds of 60 & 66 MHz.

– Designers utilized over 3 million transistors on the Pentium® chip using submicron fabrication technology.

– New design features made speed twice that of 80486/66.• Over 300 times faster than that of the original 8088.

• Pentium® is fully compatible with previous x86 processors but includes several new features.– Separate 8K cache memory for code and data.– 64-bit bus, and a vastly improved floating-point processor.

BRIEF HISTORY OF THE x86 FAMILY Pentium® & Pentium® Pro• The Pentium® is packaged in a 273-pin PGA chip

– BICMOS technology, combines the speed of bipolar transistors with power efficiency of CMOS technology

– 64-bit data bus, 32-bit registers & 32-bit address bus.• Capable of addressing 4gb of memory.

• In 1995 Intel Pentium® Pro was released—the sixth generation x86.– 5.5 million transistors.– Designed primarily for 32-bit servers & workstations.

BRIEF HISTORY OF THE x86 FAMILY Pentium® & Pentium® Pro

BRIEF HISTORY OF THE x86 FAMILY Pentium® II• In 1997 Intel introduced the Pentium® II processor

– 7.5-million-transistor processor featured MMX(MultiMedia Extension) technology incorporatedinto the CPU.

• For fast graphics and audio processing.

• In 1998 the Pentium® II Xeon was released.– Primary market is for servers and workstations.

• In 1999, Celeron® was released.– Lower cost & good performance make it ideal for PCs

used to meet educational and home business needs.

BRIEF HISTORY OF THE x86 FAMILY Pentium® III• In 1999 Intel released Pentium® III.

– 9.5-million-transistor processor.– 70 new instructions called SIMD.

• Enhance video/audio performance in 3-D imaging, and streaming audio.

• In 1999 Intel introduced the Pentium® III Xeon.– Designed more for servers and business workstations

with multiprocessor configurations.

BRIEF HISTORY OF THE x86 FAMILY Pentium® 4• The Pentium® 4 debuted late in 1999.

– Speeds of 1.4 to 1.5 GHz.– System bus operates at 400 MHz

• Completely new 32-bit architecture, called NetBurst.– Designed for heavy multimedia processing.

• Video, music, and graphic file manipulation on the Internet.– New cache and pipelining technology & expansion of

the multimedia instruction set make the P4 a high-end media processing microprocessor.

BRIEF HISTORY OF THE x86 FAMILY Intel 64 Architecture• Intel has selected Itanium® as the new brand name

for the first product in its 64-bit family of processors.– Formerly called Merced.

• The evolution of microprocessors is increasingly influenced by the evolution of the Internet.– Itanium® architecture is designed to meet Internet-driven

needs for servers & high-performance workstations.– Itanium® will have the ability to execute many instructions

simultaneously, plus extremely large memory capabilities.

1. Brief History of the x86 Family

2. Typical Pins of the x86 Processor3. Internal Processor Architecture4. Memory Architecture5. I/O Operations6. The Microprocessor-Based Personal Computer System

Lecture Outline 8088 MICROPROCESSOR

• 8088 is a 40-pin microprocessor chip that can workin two modes: minimum mode and maximum mode. – Maximum mode is used to connect to 8087 coprocessor.

• If a coprocessor is not needed, 8088 is used in minimum mode.

8088 in Min Mode

8088(min)

A19 - A0

D7 - D08

20INTRNMI

Veri Yolu

Adres YoluKesmeler

Yol Hakemliği

RDYol Kontrol

ALE

Yol Durum

WR

INTA

HOLDHLDA

DT/RDEN

RESETÇeşitli

CLK

TESTMN / MX

IO/M

READY

Compare 8088 with 8085

8085A

Vcc40

HLDACLK (OUT)RESET INREADY

S1RDWRALES0A15A14A13A12A11A10A9A8

39383736353433323130292827262524232221

HOLD X1 1

RESET OUT SOD SID TRAP RST 7.5 RST 6.5 RST 5.5 INTR INTA AD0 AD1 AD2 AD3 AD4 AD5 AD6 AD7 VSS

2 3 4 5 6 7 8 91011121314151617181920

X2 A15 - A0

D7 - D08

16

READY

TRAPRST 7.5

RESET IN

Yol Kontrol

Veri Yolu

Adres Yolu

Kesmeler

YolHakemliği

Yol DurumÇeşitli

8085ARDWR

IO/M

RST 6.5RST 5.5INTR

HOLDHLDA

RESET OUT

SIDSOD

S0

IO/M

S1

ALE

CLK

(a) (b)

INTA

X1X2

8088 MICROPROCESSOR Data Bus

– Due to chip packaging limitations in the 1970s, there was great effort to use the minimum number of pinsfor external connections.

• Intel multiplexed address & data buses, using the same pins to carry two sets of information: address & data.

8088 in minimum mode

– Pins 9-16 (AD0–AD7) are used forboth data and addresses in 8088.

• AD stands for "address/data.” – The ALE (address latch enable) pin

signals whether the information on pins AD0–AD7 is address or data.

8088 in minimum mode

8088 MICROPROCESSOR Data Bus

– When 8088 sends out an address,it activates (sets high) the ALE, to indicate the information on pinsAD0–AD7 is the address (A0–A7).

• This information must be latched, then pins AD0–AD7 are used to carry data.

– When data is to be sent out or in, ALE is low, which indicates thatAD0–AD7 will be used as databuses (D0–D7).

– The process of separating address and data from pins AD0–AD7 iscalled demultiplexing.

8088 MICROPROCESSOR Address Bus

– 8088 has 20 address pins (A0–A19), allowing it to address a maximum of one megabyte of memory (220 = 1M).

• To demultiplex address signals, a latch must be used to grab the addresses.

Fig. 9-1a 8088 in minimum mode

– Widely used is the 74LS373 IC, also 74LS573, a 74LS373 variation.

• AD0 to AD7 go to the 74LS373 latch, providing the 8-bit address A0–A7.

• A8–A15 come directly from the microprocessor (pins 2–8 & pin 39).

– The last 4 bits of the address come from A16–A19, pin numbers 35–38.


Role of ALE in address/data demultiplexing 74 LS373 D Latch

The most widely used latch is the 74LS373 IC.Also used is the 74LS573, a 74LS373 variation.


In any system, all addresses must be latched to providea stable, high-drive-capability address bus.

Address,Data,and Control Buses in 8088-based System

Summary: 8088 Bus Interface

'373ALE

IO / M

WRRD

MN / MX

OEG

AD0

AD7

A8

A15

A16 / S3

A19 / S6

D0

D7

A0

A7

A8

A15

A16

A19

AdresYolu

VeriYolu

G

OE

IO / M

WRRD

KontrolYolu

+5V

'373

Summary: 8086 Bus Interface

'373ALE

WRRD

MN / MX

OEG

D0

D15

A0

A7

A8

A15

A16

A19

AdresYolu

VeriYolu

G

OE

WRRD Kontrol

Yolu

+5V

'373

'373 OEG

AD0

AD15

A16 / S3

A19 / S6

BHE / S7 BHE

M / IO M / IO

Summary: Full Buffered 8088 Interface

'373ALE

IO / M

WRRD

MN / MX

OEG

AD0

AD7

A8

A15

A16 / S3

A19 / S6

D0

D7

A0

A7

A8

A15

A 16 A 19

AdresYolu

VeriYolu

G

OE

IO / M

WRRD

KontrolYolu

+5V

'373

DIRG

'245

DENDT / R

'244

OE

'244

OE

Summary: Full Buffered 8086 Interface

'373ALE

WRRD

MN / MX

OEG

A0

A7

A8

A15

A16

A19

AdresYolu

GOE

WRRD

KontrolYolu

+5V

'373

'373 OEG

AD8

AD15

A16 / S3

A19 / S6

BHE / S7 BHE

D0

D7

D8

D15

DIRG

'245

DIRG

'245

DENDT / R

AD0

AD7

OE'244

VeriYolu

M / IO M / IO

Bus Timing

IO / M, SS0

A15 - A8

A19/S6 -A16/S3

T1 T2 T3 T4

ALE

Bir Yol Çevrimi

CLK

RD

DT / R

DEN

AD7 - AD0 A7 - A0 Veri İçeri

OkumaÇevrimi

D7 - D0

WR

DT / R

DEN

AD7 - AD0 A7 - A0 Veri Dışarı

YazmaÇevrimi

D7 - D0

8088 MICROPROCESSOR Control Bus• 8088 can access both memory and I/O devices for

read and write operations, four operations, which need 4 control signals:– MEMR (memory read); MEMW (memory write).– IOR (I/O read); IOW (I/O write).

8088 MICROPROCESSOR Control Bus• 8088 provides three pins for control signals:

– RD, WR, and IO/M. • RD & WR pins are both active-low. • IO/M is low for memory, high for I/O devices.

Fig. 9-4 Control signal generation

8088 MICROPROCESSOR Control Bus• 8088 provides three pins for control signals:

– RD, WR, and IO/M. • RD & WR pins are both active-low. • IO/M is low for memory, high for I/O devices.

Four control signalsare generated:IOR; IOW; MEMR; MEMW. All of these signalsmust be active-low.

8088 MICROPROCESSOR Control Bus

Use of simple logic gates (inverters and ORs) to generate control signals. CPLD (complex programmable logic devices) are used in today’s PC chipsets.

Address,Data,and Control Buses in 8088-based System

8088 MICROPROCESSORBus Timing of the 8088

– 8088 uses 4 clocks for memory & I/O bus activities. • In read timing, ALE latches the address in the first clock cycle. • In the second and third cycles, the read signal is provided. • By the end of the fourth, data must be at the CPU pins. • The entire read or write cycle time is only 4 clock cycles.

ALE Timing

If reading/writing takes more than4 clocks, waitstates (WS) canbe requestedfrom the CPU.

8088 MICROPROCESSOROther Pins

– Pins 24–32 have different functions depending on whether 8088 is in minimum or maximum mode.

• In maximum mode, 8088 needs supporting chips to generate thecontrol signals.

Fig. 9-1a 8088 in minimum mode


Functions of 8088 pins 24–32 in minimum mode.


Functions of 8088 pins 24–32 in minimum mode.

8088 MICROPROCESSOROther Pins• MN/MX (minimum/maximum) - minimum mode is

selected by connecting MN/MX (pin number 33) directly to +5 V.– Maximum mode is selected by grounding this pin.

• NMI (nonmaskable interrupt) - an edge-triggered (low to high) input signal to the processor that will make the microprocessor jump to the interrupt vector table after it finishes the current instruction. – Cannot be masked by software.

• CLOCK - an input signal, connected to the 8284 clock generator.

8088 MICROPROCESSOROther Pins• INTR (interrupt request) - an active-high level-

triggered input signal continuously monitored bythe microprocessor for an external interrupt. – This pin & INTA are connected to the 8259 interrupt

controller chip.• READY - an input signal, used to insert a wait state

for slower memories and I/O. – It inserts wait states when it is low.

• TEST - in maximum mode, an input from the 8087 math coprocessor to coordinate communications.– Not used In minimum mode.

8088 MICROPROCESSOROther Pins• RESET - terminates present activities of the

processor when a high is applied to the RESETinput pin.

A presence of high will force the microprocessor to stop all activity and set the major registers to the values shown at right.

1. Brief History of the x86 Family 2. Typical Pins of the x86 Processor

3. Internal Processor Architecture4. Memory Architecture5. I/O Operations6. The Microprocessor-Based Personal Computer System

Lecture Outline

INSIDE THE 8088/86

Internal Block Diagram of the 8088/86 CPU(Reprinted by permission of Intel Corporation,Copyright Intel Corp.1989)

• There are two ways tomake the CPU processinformation faster:– Increase the working

frequency.• Using technology

available, with cost considerations.

– Change the internalarchitecture of the CPU.

INSIDE THE 8088/86 Pipelining• 8085 could fetch or execute at any given time.

– The idea of pipelining in its simplest form is to allow the CPU to fetch and execute at the same time.

Pipelined vs Nonpipelined Execution

Pipelined Architecture

Fetch1

Dec1

Execute1

Fetch2

Execute2

Meşgul Meşgul(read) Meşgul Meşgul

(write)

Mikroişlemci

Yol

(a)

Fetch1 Read Fetch

2 Write Fetch3

Fetch4

Meşgul Meşgul Meşgul Meşgul Meşgul Meşgul

BIU

Yol

Dec/Exec1

Dec/Exec2EU

(b)

Fetch3

Meşgul

Dec2

Dec/Exec3

Read

Meşgul

Bus Timing:(a) 8085A microprocessor ve 8085A bus timing, (b) 8086/8088 EU, BIU and 8086/8088 bus timing.

INSIDE THE 8088/86 Pipelining• Intel implemented pipelining in 8088/86 by splitting

the internal structure of the into two sections: – The execution unit (EU) and the bus interface unit (BIU).

• These two sections work simultaneously.

• The BIU accesses memory and peripherals, while the EU executes instructions previously fetched.– This works only if the BIU keeps ahead of the EU, so

the BIU of the 8088/86 has a buffer, or queue • The buffer is 4 bytes long in 8088 and 6 bytes in 8086.

• 8088/86 pipelining has two stages, fetch & execute.– In more powerful computers, it can have many stages.

INSIDE THE 8088/86 Pipelining• If an instruction takes too long to execute, the

queue is filled to capacity and the buses will sit idle• In some circumstances, the microprocessor must

flush out the queue.– When a jump instruction is executed, the BIU starts to

fetch information from the new location in memory and information fetched previously is discarded.

– The EU must wait until the BIU fetches the new instruction

• In computer science terminology, a branch penalty.– In a pipelined CPU, too much jumping around reduces

the efficiency of a program.

INSIDE THE 8088/86Registers• In the CPU, registers store information temporarily.

– One or two bytes of data to be processed.– The address of data.

• General-purpose registers in 8088/86 processors can be accessed as either 16-bit or 8-bit registers– All other registers can be accessed only

as the full 16 bits.• In 8088/86, data types are either 8 or 16 bits

– To access 12-bit data, for example, a 16-bit registermust be used with the highest 4 bits set to 0.

INSIDE THE 8088/86Registers (16-bit Architecture)• The bits of a register are numbered in descending

order, as shown:

• The first letter of each register indicates its use.– AX is used for the accumulator.– BX is a base addressing register.– CX is a counter in loop operations.– DX points to data in I/O operations.

INSIDE THE 8088/86Registers

FLAG REGISTER (16-bit Architecture)

• The flag register is a 16-bit register sometimes referred to as the status register.– Although 16 bits wide, only some of the bits are used.

• The rest are either undefined or reserved by Intel.

• Many Assembly language instructions alter flag register bits & some instructions function differently based on the information in the flag register.

FLAG REGISTER

• Six flags, called conditional flags, indicate some condition resulting after an instruction executes.

– These six are CF, PF, AF, ZF, SF, and OF.– The remaining three, often called control flags, control

the operation of instructions before they are executed.

FLAG REGISTER Bits of the flag register• Flag register bits used in x86 Assembly language

programming, with a brief explanation each:– CF (Carry Flag) - Set when there is a carry out, from d7

after an 8-bit operation, or d15 after a 16-bit operation.• Used to detect errors in unsigned arithmetic operations.

– PF (Parity Flag) - After certain operations, the parityof the result's low-order byte is checked.

• If the byte has an even number of 1s, the parity flag is set to 1; otherwise, it is cleared.

– AF (Auxiliary Carry Flag) - If there is a carry from d3 to d4 of an operation, this bit is set; otherwise, it is cleared.

• Used by instructions that perform BCD (binary codeddecimal) arithmetic.


programming, with a brief explanation each:– ZF (Zero Flag) - Set to 1 if the result of an arithmetic or

logical operation is zero; otherwise, it is cleared.– SF (Sign Flag) - Binary representation of signed numbers

uses the most significant bit as the sign bit.• After arithmetic or logic operations, the status of this sign

bit is copied into the SF, indicating the sign of the result.– TF (Trap Flag) - When this flag is set it allows the

program to single-step, meaning to execute one instruction at a time.

• Single-stepping is used for debugging purposes.


programming, with a brief explanation each:– IF (Interrupt Enable Flag) - This bit is set or cleared to

enable/disable only external maskable interrupt requests.– DF (Direction Flag) - Used to control the direction of

string operations.– OF (Overflow Flag) - Set when the result of a signed

number operation is too large, causing the high-orderbit to overflow into the sign bit.

• Used only to detect errors in signed arithmetic operations.

FLAG REGISTER Flag register and ADD instruction• Flag bits affected by the ADD instruction:

– CF (carry flag); PF (parity flag); AF (auxiliary carry flag).– ZF (zero flag); SF (sign flag); OF (overflow flag).

FLAG REGISTER Flag register and ADD instruction• Flag bits affected by the ADD instruction:

– CF (carry flag); PF (parity flag); AF (auxiliary carry flag).– ZF (zero flag); SF (sign flag); OF (overflow flag).

FLAG REGISTER Flag register and ADD instruction• It is important to note differences between 8- and

16-bit operations in terms of impact on the flag bits.– The parity bit only counts the lower 8 bits of the result

and is set accordingly.

FLAG REGISTER Flag register and ADD instruction• The carry flag is set if there is a carry beyond bit

d15 instead of bit d7.– Since the result of the entire 16-bit operation is zero

(meaning the contents of BX), ZF is set to high.

FLAG REGISTER Flag register and ADD instruction• Instructions such as data transfers (MOV) affect no

flags.

FLAG REGISTER Use of the zero flag for looping• A widely used application of the flag register is the

use of the zero flag to implement program loops.– A loop is a set of instructions repeated a number of times.

FLAG REGISTER Use of the zero flag for looping• As an example, to add 5 bytes of data, a counter

can be used to keep track of how many times the loop needs to be repeated.– Each time the addition is performed the counter

is decremented and the zero flag is checked.• When the counter becomes zero, the zero flag is

set (ZF = 1) and the loop is stopped.

FLAG REGISTER Use of the zero flag for looping• Register CX is used to hold the counter.

– BX is the offset pointer.• (SI or DI could have been used instead)

FLAG REGISTER Use of the zero flag for looping• AL is initialized before the start of the loop

– In each iteration, ZF is checked by the JNZ instruction• JNZ stands for "Jump Not Zero“, meaning that if ZF = 0,

jump to a new address.• If ZF = 1, the jump is not performed, and the instruction

below the jump will be executed.

FLAG REGISTER Use of the zero flag for looping• JNZ instruction must come immediately after the

instruction that decrements CX.– JNZ needs to check the effect of "DEC CX" on ZF.

• If any instruction were placed between them, that instruction might affect the zero flag.

80x86 Registers (32-bit Architecture)

General Purpose Registers (32-bit Architecture) Special Purpose Registers: The main functions

Flags Register

C

01

P

23

A

45

Z

6

S

7

T

8

I

9

D

10

O

1112131415

Flags Register (cont.)

Flags Register (cont.) Flags Register (cont.)

Segment Registers The 64-bit Programming Model

• 8086 through Core2 considered program visible.– registers are used during programming and are

specified by the instructions • Other registers considered to be program

invisible.– not addressable directly during applications

programming

• 80286 and above contain program-invisible registers to control and operate protected memory. – and other features of the microprocessor

• 80386 through Core2 microprocessors contain full 32-bit internal architectures.

• 8086 through the 80286 are fully upward-compatible to the 80386 through Core2.

The programming model of the 8086 through the Core2 microprocessor including the 64-bit extensions

Multipurpose Registers • RAX - a 64-bit register (RAX), a 32-bit register

(accumulator) (EAX), a 16-bit register (AX), or as either of two 8-bit registers (AH and AL).

• RBX, addressable as RBX, EBX, BX, BH, BL.

• RCX, as RCX, ECX, CX, CH, or CL.

• RDX, as RDX, EDX, DX, DH, or DL.– a (data) general-purpose register

• RBP, as RBP, EBP, or BP.– points to a memory (base pointer) location

for memory data transfers• RDI addressable as RDI, EDI, or DI.

– often addresses (destination index) string destination data for the string instructions

• RSI used as RSI, ESI, or SI. – the (source index) register addresses source

string data for the string instructions– like RDI, RSI also functions as a general-

purpose register

• R8 - R15 found in the Pentium 4 and Core2 if 64-bit extensions are enabled. – data are addressed as 64-, 32-, 16-, or 8-bit

sizes and are of general purpose• Most applications will not use these registers until

64-bit processors are common. – the 8-bit portion is the rightmost 8-bit only– bits 8 to 15 are not directly addressable as

a byte

Special-Purpose Registers• Include RIP, RSP, and RFLAGS

– segment registers include CS, DS, ES, SS, FS, and GS

• RIP addresses the next instruction in a section of memory.– defined as (instruction pointer) a code segment

• RSP addresses an area of memory called the stack. – the (stack pointer) stores data through this

pointer

The EFLAG and FLAG register counts for the entire 8086 and Pentium microprocessor family

• Flags never change for any data transfer or program control operation.

• Some of the flags are also used to control features found in the microprocessor.

1. Brief History of the x86 Family 2. Typical Pins of the x86 Processor3. Internal Processor Architecture

4. Memory Architecture5. I/O Operations6. The Microprocessor-Based Personal Computer System

Lecture Outline

Real Mode Addressing

• 80286 and above operate in either the real or protected mode.

• Real mode operation allows addressing of only the first 1M byte of memory space—even in Pentium 4 or Core2 microprocessor. – the first 1M byte of memory is called the real

memory, conventional memory, or DOS memory system

Segments and Offsets

• All real mode memory addresses must consist of a segment address plus an offset address. – segment address defines the beginning address

of any 64K-byte memory segment– offset address selects any location within the

64K byte memory segment

• Figure shows how the segment plus offsetaddressing scheme selects a memory location.

The real mode memory-addressing scheme, using a segment address plus an offset

– this shows a memory segment beginning at 10000H, ending at location IFFFFH

• 64K bytes in length

– also shows how an offset address, called a displacement, of F000H selects location1F000H in the memory

Segment and Offset Addressing Scheme Allows Relocation • Segment plus offset addressing allows DOS programs

to be relocated in memory.• A relocatable program is one that can be placed into

any area of memory and executed without change.• Relocatable data can be placed in any area of

memory and used without any change to the program. • Because memory is addressed within a segment by

an offset address, the memory segment can be moved to any place in the memory system without changing any of the offset addresses.

• Only the contents of the segment register must be changed to address the program in the new area of memory.

PROGRAM SEGMENTS • A typical x86 assembly language program consists

of at least 3 segments:– A code segment - which contains the Assembly

language instructions that perform the tasks that the program was designed to accomplish.

– A data segment - used to store information (data) tobe processed by the instructions in the code segment.

– A stack segment - used by the CPU to store information temporarily.

PROGRAM SEGMENTS Origin and definition of the segment• A segment is an area of memory that includes up

to 64K bytes, and begins on an address evenly divisible by 16 (such an address ends in 0H)– 8085 addressed a maximum of 64K of physical memory,

since it had only 16 pins for address lines. (216 = 64K)• Limitation was carried into 8088/86 design for compatibility.

• In 8085 there was 64K bytes of memory for all code, data, and stack information.– In 8088/86 there can be up to 64K bytes in each category.

• The code segment, data segment, and stack segment.

PROGRAM SEGMENTS Logical Address and Physical Address• In literature concerning 8086, there are three types

of addresses mentioned frequently:– The physical address - the 20-bit address actually on

the address pins of the 8086 processor, decoded by the memory interfacing circuitry.

• This address can have a range of 00000H to FFFFFH.• An actual physical location in RAM or ROM within the 1 mb

memory range.– The offset address - a location in a 64K-byte segment

range, which can can range from 0000H to FFFFH.– The logical address - which consists of a segment value

and an offset address.

PROGRAM SEGMENTS Code Segment • To execute a program, 8086 fetches the instructions

(opcodes and operands) from the code segment.– The logical address of an instruction always consists of a

CS (code segment) and an IP (instruction pointer), shown in CS:IP format.

– The physical address for the location of the instructionis generated by shifting the CS left one hex digit, then adding it to the IP.

• IP contains the offset address.

• The resulting 20-bit address is called the physical address since it is put on the external physical address bus pins.

PROGRAM SEGMENTS Code Segment • Assume values in CS & IP as shown in the diagram:

– The offset address contained in IP, is 95F3H.– The logical address is CS:IP, or 2500:95F3H.– The physical address will be 25000 + 95F3 = 2E5F3H

PROGRAM SEGMENTS Code Segment • Calculate the physical address of an instruction:

– The microprocessor will retrieve the instruction from memory locations starting at 2E5F3.


– Since IP can have a minimum value of 0000H and a maximum of FFFFH, the logical address range in this example is 2500:0000 to 2500:FFFF.

– This means that the lowest memory location of the code segment above will be 25000H (25000 + 0000) and the highest memory location will be 34FFFH (25000 + FFFF).


PROGRAM SEGMENTS Code Segment • What happens if the desired instructions are located

beyond these two limits? – The value of CS must be changed to access those

instructions.

PROGRAM SEGMENTS Code Segment - Logical/Physical Address• In the next code segment, CS and IP hold the

logical address of the instructions to be executed.– The following Assembly language instructions have been

assembled (translated into machine code) and stored in memory.

– The three columns show the logical address of CS:IP, the machine code stored at that address, and the corresponding Assembly language code.

– The physical address is put on the address bus by the CPU to be decoded by the memory circuitry.

PROGRAM SEGMENTS code segment logical/physical address

Instruction "MOV AL,57" has a machine code of B057.B0 is the opcode and 57 is the operand.

PROGRAM SEGMENTS Code Segment - Logical/Physical Address

Instruction "MOV AL,57" has a machine code of B057.B0 is the opcode and 57 is the operand.The byte at address 1132:0100 contains B0, the opcode for movinga value into register AL.Address 1132:0101 contains the operand to be moved to AL.

PROGRAM SEGMENTS data segment • Assume a program to add 5 bytes of data, such as

25H, 12H, 15H, 1FH, and 2BH.– One way to add them is as follows:

– In the program above, the data & code are mixed together in the instructions.

• If the data changes, the code must be searched for every place it is included, and the data retyped

• From this arose the idea of an area of memory strictly for data

PROGRAM SEGMENTS data segment • In x86 microprocessors, the area of memory set

aside for data is called the data segment.– The data segment uses register DS and an offset value.– DEBUG assumes that all numbers are in hex.

• No "H" suffix is required.– MASM assumes that they are in decimal.

• The "H" must be included for hex data.

• The next program demonstrates how data canbe stored in the data segment and the programrewritten so that it can be used for any set of data.

PROGRAM SEGMENTS data segment • Assume data segment offset begins at 200H.

– The data is placed in memory locations:

– The program can be rewritten as follows:

PROGRAM SEGMENTS data segment • The offset address is enclosed in brackets, which

indicate that the operand represents the addressof the data and not the data itself.

– If the brackets were not included, as in "MOV AL,0200", the CPU would attempt to move 200 into AL instead of the contents of offset address 200. decimal.

• This program will run with any set of data.• Changing the data has no effect on the code.

PROGRAM SEGMENTS data segment • If the data had to be stored at a different offset

address the program would have to be rewritten– A way to solve this problem is to use a register to hold

the offset address, and before each ADD, increment the register to access the next byte.

• 8088/86 allows only the use of registers BX, SI, and DI as offset registers for the data segment– The term pointer is often used for a register holding

an offset address.

PROGRAM SEGMENTS data segment • In the following example, BX is used as a pointer:

• The INC instruction adds 1 to (increments) its operand.– "INC BX" achieves the same result as "ADD BX,1“– If the offset address where data is located is changed,

only one instruction will need to be modified.

PROGRAM SEGMENTS data segment logical/physical address• The physical address for data is calculated using

the same rules as for the code segment.– The physical address of data is calculated by shifting DS

left one hex digit and adding the offset value, as shownin Examples 1-2, 1-3, and 1-4.

PROGRAM SEGMENTS data segment logical/physical address

PROGRAM SEGMENTS data segment logical/physical address

PROGRAM SEGMENTS little endian convention• Previous examples used 8-bit or 1-byte data.

– What happens when 16-bit data is used?

• The low byte goes to the low memory location and the high byte goes to the high memory address.– Memory location DS:1500 contains F3H.– Memory location DS:1501 contains 35H.

• (DS:1500 = F3 DS:1501 = 35)– This convention is called little endian vs big endian.

• From a Gulliver’s Travels story about how an egg shouldbe opened—from the little end, or the big end.

PROGRAM SEGMENTS little endian convention• In the big endian method, the high byte goes to the

low address.– In the little endian method, the high byte goes to the

high address and the low byte to the low address.

PROGRAM SEGMENTS little endian convention• All Intel microprocessors and many microcontrollers

use the little endian convention.– Freescale (formerly Motorola) microprocessors, along

with some other microcontrollers, use big endian.

PROGRAM SEGMENTS extra segment (ES) • ES is a segment register used as an extra data

segment.– In many normal programs this segment is not used.– Use is essential for string operations.

THE STACK what is a stack? why is it needed?• The stack is a section of read/write memory (RAM)

used by the CPU to store information temporarily.– The CPU needs this storage area since there are

only a limited number of registers.• There must be some place for the CPU to store

information safely and temporarily.

• The main disadvantage of the stack is access time.– Since the stack is in RAM, it takes much longer to

access compared to the access time of registers.• Some very powerful (expensive) computers do not

have a stack.– The CPU has a large number of registers to work with.

THE STACK how stacks are accessed• The stack is a section of RAM, so there must be

registers inside the CPU to point to it.– The SS (stack segment) register.– The SP (stack pointer) register.

• These registers must be loaded before anyinstructions accessing the stack are used.

• Every register inside the x86 can be stored in the stack, and brought back into the CPU from thestack memory, except segment registers and SP.– Storing a CPU register in the stack is called a push.– Loading the contents of the stack into the CPU register

is called a pop.

THE STACK how stacks are accessed• The x86 stack pointer register (SP) points at the

current memory location used as the top of the stack.– As data is pushed onto the stack it is decremented.– As data is popped off the stack into the CPU, it is

incremented.• When an instruction pushes or pops a general-

purpose register, it must be the entire 16-bit register.– One must code "PUSH AX".

• There are no instructions such as "PUSH AL" or "PUSH AH".

THE STACK how stacks are accessed• The SP is decremented after the push is to make

sure the stack is growing downward from upper addresses to lower addresses.– The opposite of the IP. (instruction pointer)

• To ensure the code section & stack section of the program never write over each other, they arelocated at opposite ends of the RAM set asidefor the program.– They grow toward each other but must not meet.

• If they meet, the program will crash.

THE STACK pushing onto the stack• As each PUSH is executed, the register contents are

saved on the stack and SP is decremented by 2.

THE STACK pushing onto the stack• For every byte of data saved on the stack, SP is

decremented once.

Since the pushis saving the contents of a16-bit register,it decrements twice.

THE STACK pushing onto the stack• In the x86, the lower byte is always stored in the

memory location with the lower address.

24H, the content of AH, is savedin the memory location with the address 1235.AL is stored in location 1234.

THE STACK popping the stack• With every pop, the top 2 bytes of the stack are

copied to the x86 CPU register specified by the instruction & the stack pointer is incremented twice.

While the data actually remains in memory, it is not accessible, since the stack pointer, SP is beyond that point.

THE STACK logical vs physical stack address• The exact physical location of the stack depends on

the value of the stack segment (SS) register andSP, the stack pointer.– To compute physical addresses for the stack, shift

left SS, then add offset SP, the stack pointer register.

– Windows assigns values for the SP and SS.

THE STACKa few more words about x86 segments• Can a single physical address belong to many

different logical addresses? – Observe the physical address value of 15020H.

• Many possible logical addresses represent this singlephysical address:

– An illustration of the dynamic behavior of the segment and offset concept in the 8086 CPU.

THE STACKa few more words about x86 segments• When adding the offset to the shifted segment

register results in an address beyond the maximum allowed range of FFFFFH, wrap-around will occur.

THE STACKoverlapping• In calculating the physical address, it is possible

that two segments can overlap.

Summary and Examples:Real Mode Memory Addressing

Segments and Offsets 8086/8088 Memory Access Registers

Segment Address Sources for Different Operations

Operation Type Segment Alternative Segment Offset

Instruction Fetch CS none IP

Stack operation SS none SP

Data operation (aşağıdakiler hariç) DS CS, ES or SS several

String source DS CS, ES veya SS SI

String destination ES none DI

BP (used as base register) SS CS, ES or SS several

8086 Generating Physical Addresses Segmented Addressing

Segmented Memory (x86 Style) 8086/8088 Memory Architecture

1 M byte

00000h

FFFFFh

1 M byte

00000h

FFFFFh

8086/8088 logical memory map

8088 physical memory map

512 K byte

512 K byte

00000h00002h

00001h00003h00005h 00004h

FFFFEhFFFFFh

Yüksek Hafıza Düşük Hafıza

16-bit

Tek Blok Çift Blok

8086 physical memory map

80x86 Memory Bank Layout 80x86 Memory Bank Layout

80x86 Memory Bank Layout Memory Storage Organization

Segmented Memory Example Segment Locations in Physical Memory

Segmented Memory Aliasing Memory Data Organization

Register Transfer Language Memory Read Operations

Memory Write Operations Memory Write Operations (cont.)

Memory Write Operations (cont.) Memory Write Operations (cont.)

Intro to Protected Mode Memory Addressing

• Allows access to data and programs located within & above the first 1M byte of memory.

• Protected mode is where Windows operates.• In place of a segment address, the segment register

contains a selector that selects a descriptor from a descriptor table.

• The descriptor describes the memory segment’s location, length, and access rights.

Selectors and Descriptors

• The descriptor is located in the segment register & describes the location, length, and access rights of the segment of memory. – it selects one of 8192 descriptors from one

of two tables of descriptors• In protected mode, this segment number can

address any memory location in the systemfor the code segment.

• Indirectly, the register still selects a memory segment, but not directly as in real mode.

• Global descriptors contain segment definitions that apply to all programs.

• Local descriptors are usually unique to an application. – a global descriptor might be called a system

descriptor, and local descriptor an application descriptor

• The next figure shows the format of a descriptor for the 80286 through the Core2. – each descriptor is 8 bytes in length– global and local descriptor tables are a

maximum of 64K bytes in length

Global and Local Descriptors The 80286 through Core2 64-bit descriptors

• The base address of the descriptor indicates the starting location of the memory segment.– the paragraph boundary limitation is removed in

protected mode– segments may begin at any address

• The G, or granularity bit allows a segment length of 4K to 4G bytes in steps of 4K bytes. – 32-bit offset address allows segment lengths of

4G bytes– 16-bit offset address allows segment lengths of

64K bytes.

• Operating systems operate in a 16- or 32-bit environment.

• DOS uses a 16-bit environment.• Most Windows applications use a 32-bit

environment called WIN32.• MSDOS/PCDOS & Windows 3.1 operating systems

require 16-bit instruction mode. • Instruction mode is accessible only in a protected

mode system such as Windows Vista.

• The access rights byte controls access to the protected mode segment. – describes segment function in the system and

allows complete control over the segment– if the segment is a data segment, the direction of

growth is specified • If the segment grows beyond its limit, the operating

system is interrupted, indicating a general protection fault.

• You can specify whether a data segment can be written or is write-protected.

Access Rights Byte The access rights byte for the 80286 through Core2 descriptor

• Descriptors are chosen from the descriptor table by the segment register. – register contains a 13-bit selector field, a table

selector bit, and requested privilege level field • The TI bit selects either the global or the local

descriptor table.• Requested Privilege Level (RPL) requests the

access privilege level of a memory segment. – If privilege levels are violated, system normally

indicates an application or privilege level violation

The contents of a segment register during protected mode operation of the 80286 through Core2 microprocessors

• Figure 2–9 shows how the segment register, containing a selector, chooses a descriptor from the global descriptor table.

• The entry in the global descriptor table selects a segment in the memory system.

• Descriptor zero is called the null descriptor, must contain all zeros, and may not be used for accessing memory.

Using the DS register to select a description from the global descriptor table. In this example, the DS register accesses memory locations 00100000H–001000FFH as a data segment.

Program-Invisible Registers

• Global and local descriptor tables are foundin the memory system.

• To access & specify the table addresses, 80286–Core2 contain program-invisible registers. – not directly addressed by software

• Each segment register contains a program-invisible portion used in the protected mode. – often called cache memory because cache is

any memory that stores information

The program-invisible registers within the 80286–Core2 microprocessors.

• When a new segment number is placed in a segment register, the microprocessor accesses a descriptor table and loads the descriptor into the program-invisible portion of the segment register. – held there and used to access the memory

segment until the segment number is changed • This allows the microprocessor to repeatedly access

a memory segment without referring to the descriptor table.– hence the term cache

• The GDTR (global descriptor table register) and IDTR (interrupt descriptor table register) contain the base address of the descriptor table and its limit. – when protected mode operation desired, address

of the global descriptor table and its limit are loaded into the GDTR

• The location of the local descriptor table is selected from the global descriptor table. – one of the global descriptors is set up to

address the local descriptor table

• To access the local descriptor table, the LDTR (local descriptor table register) is loaded with a selector. – selector accesses global descriptor table, & loads

local descriptor table address, limit, & access rights into the cache portion of the LDTR

• The TR (task register) holds a selector, which accesses a descriptor that defines a task. – a task is most often a procedure or application

• Allows multitasking systems to switch tasksto another in a simple and orderly fashion.

Memory Paging

• The memory paging mechanism allows any physical memory location to be assigned to any linear address.

• Iinear address is defined as the address generated by a program.

• Physical address is the actual memory location accessed by a program.

• With memory paging, the linear address is invisibly translated to any physical address.

Paging Registers

• The paging unit is controlled by the contentsof the microprocessor’s control registers.

• Beginning with Pentium, an additional control register labeled CR4 controls extensions to the basic architecture.

• See Figure 2–11 for the contents of control registers CR0 through CR4.

The control register structure of the microprocessor

• The linear address, as generated by software, is broken into three sections that are used to access the page directory entry, page table entry, and memory page offset address.

• Figure 2–12 shows the linear address and its makeup for paging.

• When the program accesses a location between 00000000H and 00000FFFH, the microprocessor physically addresses location 00100000H–00100FFFH.

The format for the linear address (a) and a page directory or page table entry (b)

• Intel has incorporated a special type of cache called TLB (translation look-aside buffer). – because repaging a 4K-byte section of memory

requires access to the page directory and a page table, both located in memory

• The 80486 cache holds the 32 most recent page translation addresses. – if the same area of memory is accessed, the address

is already present in the TLB – This speeds program execution

• Pentium contains separate TLBs for each of their instruction and data caches.

Translation Look-Aside Buffer (TLB) The Page Directory and Page Table

• Only one page directory in the system. • The page directory contains 1024 doubleword

addresses that locate up to 1024 page tables.• Page directory and each page table are 4K bytes in

length. • Figure 2–13 shows the page directory, a few page

tables, and some memory pages.

The paging mechanism in the 80386 through Core2 microprocessors

• DOS and EMM386.EXE use page tables to redefine memory between locations C8000H–EFFFFH as upper memory blocks. – done by repaging extended memory to backfill

conventional memory system to allow DOS access to additional memory

• Each entry in the page directory corresponds to 4M bytes of physical memory.

• Each entry in the page table repages 4K bytes of physical memory.

• Windows also repages the memory system.

The page directory, page table 0, and two memory pages. Note how the address of page 000C8000–000C9000 has been moved to 00110000–00110FFF. Flat Mode Memory

• A flat mode memory system is one in which there is no segmentation. – does not use a segment register to address a

location in the memory• First byte address is at 00 0000 0000H; the

last location is at FF FFFF FFFFH. – address is 40-bits

• The segment register still selects the privilege level of the software.

• Real mode system is not available if the processor operates in the 64-bit mode.

• Protection and paging are allowed in the 64-bit mode.

• The CS register is still used in the protected mode operation in the 64-bit mode.

• Most programs today are operated in the IA32 compatible mode.– current software operates properly, but this will

change in a few years as memory becomeslarger and most people have 64-bit computers

The 64-bit flat mode memory model

1. Brief History of the x86 Family 2. Typical Pins of the x86 Processor3. Internal Processor Architecture4. Memory Architecture

5. I/O Operations6. The Microprocessor-Based Personal Computer System

Lecture Outline I/O Port Addressing A tipical x86-based system can have up to 65,536 input and

65,536 output ports. Each port has an address (like memory) – referred to as “I/O

address space” I/O port is usually 1 byte or 2 bytes – with 386+ may be also 4

bytes Two Addressing Modes

• 1) Immediate Port Address- can only be 1 byte- can only address ports 00h through FFh

• 2) Port Address Present in DX- can address all ports 0000h through FFFFh - can only use DX for port addresses- can only use AL, AX, EAX for port data

I/O Port Addressing Examples

in al, 40h ; al gets 1 byte from port 40h in ax, 255 ; ax gets 2 bytes from port ffhin al, dx ; ax gets 1 byte from port address in dx in eax, dx ; eax gets 4 bytes from port addr. in dx out 80h, al ; send contents of al to port 80hout dx, eax ; send contents of eax to port addr. in dx

Basic 80x86 Based PC I/O Architecture

Interrupt Vectors (DOS PC) I/O Address Space

1. Brief History of the x86 Family 2. Typical Pins of the x86 Processor3. Internal Processor Architecture4. Memory Architecture5. I/O Operations

6. The Microprocessor-Based Personal Computer System

Lecture Outline

The block diagram of a microprocessor-based computer system

The Memory and I/O System • Memory structure of all Intel-based personal

computers similar.• Figure in the next slide illustrates memory map

of a personal computer system. • This map applies to any IBM personal

computer. – also any IBM-compatible clones in existence

The memory map of a personal computer

• Main memory system divided into three parts:– TPA (transient program area) – System area– XMS (extended memory system)

• Type of microprocessor present determines whether an extended memory system exists.

• First 1M byte of memory often called the real or conventional memory system.– Intel microprocessors designed to function

in this area using real mode operation

IBM PC MEMORY MAP

• All x86 CPUs in real mode provide 20 address bits.– Maximum memory access is one megabyte.

• The 20 system address bus lines, A0–A19, can take the lowest value of all 0s to the highest value of all 1s in binary. – Converted to hex, an address range 00000H to FFFFFH.

Fig. 10-14 20 Bit Address Range in Real Mode for x86 CPUs

IBM PC MEMORY MAPConventional Memory - 640K of RAM

Any address assigned to any memory block in the 8088 PCmust fall in this rangeOf the addressable 1024K,PC designers set aside 640Kfor RAM, 128K for video displayRAM, (VDR) & 256K for ROM.In the x86 PC, addresses from 00000 to 9FFFFH, including location 9FFFFH, are set asidefor RAM. Fig. 10-15

Memory Map of the IBM PC

IBM PC MEMORY MAP BIOS Data Area • The BIOS data area is used by BIOS to store some

extremely important system information.

See the entire listing onpage 271 of your textbook.

The operating system navigates the system hardware with the helpof information stored in the BIOS data area.

More About RAM• In the early 80s, most PCs came with 64K to 256K

bytes of RAM, more than adequate at the time– Users had to buy memory to expand up to 640K.

• Managing RAM is left to Windows because...– The amount of memory used by Windows varies.– Different computers have different amounts of RAM.– Memory needs of application packages vary.

• For this reason, we do not assign any values for the CS, DS, and SS registers.– Such an assignment means specifying an exact physical

address in the range 00000–9FFFFH, and this is beyond the knowledge of the user.

Video RAM• From A0000H to BFFFFH is set aside for video

– The amount used and the location vary dependingon the video board installed on the PC

More about ROM• C0000H to FFFFFH is set aside for ROM.

– Not all the memory in this range is used by the PC's ROM.• 64K bytes from location F0000H–FFFFFH are

used by BIOS (basic input/output system) ROM.– Some of the remaining space is used by various adapter

cards (such as the network card), and the rest is free.• The 640K bytes from 00000 to 9FFFFH is referred

to as conventional memory.– The 384K bytes from A0000H to FFFFFH are called

the UMB (upper memory block).

Function of BIOS ROM• There must be some permanent (nonvolatile)

memory to hold the programs telling the CPUwhat to do when the power is turned on– This collection of programs is referred to as BIOS.

• BIOS stands for basic input-output system.– It contains programs to test RAM and other

components connected to the CPU.– It also contains programs that allow Windows to

communicate with peripheral devices.– The BIOS tests devices connected to the PC when

the computer is turned on and to report any errors.

IBM PC MEMORY MAP Video Display RAM (VDR) map • To display information on the monitor of the PC, the

CPU must first store it in video display RAM (VDR). – The video controller displays VDR contents on the screen.

• Address of the VDR must be within the CPU address range.

• In the x86, from A0000 to BFFFFH, a total of 128K bytes of addressable memory is allocated for video.

IBM PC MEMORY MAP ROM Address and Cold Boot in the PC• When power is applied to a CPU it must wake up at

an address that belongs to ROM. – The first code executed by the CPU must be stored in

nonvolatile memory. – On RESET, 8088 starts to fetch

information from CS:IP of FFFF:0000.• Physical address FFFF0H.

– As the microprocessor starts to fetch &execute instructions from FFFF0H, theremust be an opcode in that ROM location.

• The CPU finds the opcode for the FARjump, and the target address of the JUMP.

• 80286 through the Core2 contain the TPA (640K bytes) and system area (384K bytes).– also contain extended memory– often called AT class machines

• The PS/l and PS/2 by IBM are other versions of the same basic memory design.

• Also referred to as ISA (industry standard architecture) or EISA (extended ISA).

• The PS/2 referred to as a micro-channel architecture or ISA system.– depending on the model number

• Pentium and ATX class machines feature addition of the PCI (peripheral component interconnect) bus.– now used in all Pentium through Core2 systems

• Extended memory up to 15M bytes in the 80286 and 80386SX; 4095M bytes in 80486 80386DX, Pentium microprocessors.

• The Pentium Pro through Core2 computer systems have up to 1M less than 4G or 1 M less than 64G of extended memory.

• Servers tend to use the larger memory map.

• Many 80486 systems use VESA local, VL bus to interface disk and video to the microprocessor at the local bus level.– allows 32-bit interfaces to function at same

clocking speed as the microprocessor– recent modification supporting 64-bit data bus

has generated little interest • ISA/EISA standards function at 8 MHz.• PCI bus is a 32- or 64-bit bus.

– specifically designed to function with the Pentium through Core2 at a bus speed of 33 MHz.

• Three newer buses have appeared.• USB (universal serial bus).

– intended to connect peripheral devices to the microprocessor through a serial data path anda twisted pair of wires

• Data transfer rates are 10 Mbps for USB1.• Increase to 480 Mbps in USB2.

• AGP (advanced graphics port) for video cards.

• The port transfers data between video card and microprocessor at higher speeds. – 66 MHz, with 64-bit data path

• Latest AGP speed 8X or 2G bytes/second. – video subsystem change made to accommodate

new DVD players for the PC.

• Latest new buses are serial ATA interface (SATA) for hard disk drives; PCI Express bus for the video card.

• The SATA bus transfers data from PC to hard disk at rates of 150M bytes per second; 300M bytes for SATA-2.– serial ATA standard will eventually reach speeds

of 450M bytes per second • PCI Express bus video cards operate at 16X

speeds today.

The TPA• The transient program area (TPA) holds the

DOS (disk operating system) operating system; other programs that control the computer system.– the TPA is a DOS concept and not really

applicable in Windows – also stores any currently active or inactive DOS

application programs– length of the TPA is 640K bytes

Figure 1–8 The memory map of the TPA in a personal computer. (Note that this map will vary between systems.)

• DOS memory map shows how areas of TPA are used for system programs, dataand drivers.– also shows a large area of

memory available for application programs

– hexadecimal number to left of each area represents the memory addresses that begin and end each data area

• Interrupt vectors access DOS, BIOS (basic I/O system), and applications.

• Areas contain transient data to access I/O devices and internal features of the system. – these are stored in the TPA so they can be

changed as DOS operates

• The IO.SYS loads into the TPA from the disk whenever an MSDOS system is started.

• IO.SYS contains programs that allow DOS to use keyboard, video display, printer, and other I/O devices often found in computers.

• The IO.SYS program links DOS to the programs stored on the system BIOS ROM.

• Drivers are programs that control installable I/O devices. – mouse, disk cache, hand scanner, CD-ROM

memory (Compact Disk Read-Only Memory), DVD (Digital Versatile Disk), or installable devices, as well as programs

• Installable drivers control or drive devices or programs added to the computer system.

• DOS drivers normally have an extension of .SYS; MOUSE.SYS.

• DOS version 3.2 and later files have an extension of .EXE; EMM386.EXE.

• Though not used by Windows, still used to execute DOS applications, even with Win XP.

• Windows uses a file called SYSTEM.INI to load drivers used by Windows.

• Newer versions of Windows have a registry added to contain information about the system and the drivers used.

• You can view the registry with the REGEDIT program.

• COMMAND.COM (command processor) controls operation of the computer from the keyboard when operated in the DOS mode.

• COMMAND.COM processes DOS commands as they are typed from the keyboard.

• If COMMAND.COM is erased, the computer cannot be used from the keyboard in DOS mode.– never erase COMMAND.COM, IO.SYS, or

MSDOS.SYS to make room for other software– your computer will not function

The System Area• Smaller than the TPA; just as important.• The system area contains programs on read-

only (ROM) or flash memory, and areas of read/write (RAM) memory for data storage.

• Figure 1–9 shows the system area of a typical personal computer system.

• As with the map of the TPA, this map also includes the hexadecimal memory addresses of the various areas.

Figure 1–9 The system area of a typical personal computer.

• First area of system space contains video display RAM and video control programs on ROM or flash memory. – area starts at location A0000H

and extends to C7FFFH – size/amount of memory

depends on type of video display adapter attached

• Display adapters generally have video RAM at A0000H–AFFFFH.– stores graphical or bit-mapped data

• Memory at B0000H–BFFFFH stores text data. • The video BIOS on a ROM or flash memory,

is at locations C0000H–C7FFFH. – contains programs to control DOS video display

• C8000H–DFFFFH is often open or free.– used for expanded memory system (EMS) in PC

or XT system; upper memory system in an AT

• Expanded memory system allows a 64K-byte page frame of memory for use by applications.– page frame (D0000H - DFFFFH) used to expand

memory system by switching in pages of memory from EMS into this range of memory addresses

• Locations E0000H–EFFFFH contain cassette BASIC on ROM found in early IBM systems.– often open or free in newer computer systems

• Video system has its own BIOS ROM at location C0000H.

• System BIOS ROM is located in the top 64K bytes of the system area (F0000H–FFFFFH). – controls operation of basic I/O devices connected

to the computer system – does not control operation of video

• The first part of the system BIOS (F0000H–F7FFFH) often contains programs that set up the computer.

• Second part contains procedures that control the basic I/O system.

Windows Systems• Modern computers use a different memory

map with Windows than DOS memory maps.• The Windows memory map in Figure 1–10

has two main areas; a TPA and system area. • The difference between it and the DOS

memory map are sizes and locations of these areas.

The memory map used by Windows XP

• TPA is first 2G bytes from locations 00000000H to 7FFFFFFFH.

• Every Windows program can use up to 2G bytes of memory located at linear addresses 00000000H through 7FFFFFFFH.

• System area is last 2G bytes from 80000000Hto FFFFFFFFH.

• Memory system physical map is much different.

• Every process in a Windows Vista, XP, or 2000 system has its own set of page tables.

• The process can be located anywhere in the memory, even in noncontiguous pages.

• The operating system assigns physical memory to application.– if not enough exists, it uses the hard disk

for any that is not available

I/O Space• I/O devices allow the microprocessor to

communicate with the outside world.• I/O (input/output) space in a computer system

extends from I/O port 0000H to port FFFFH.– I/O port address is similar to a memory address– instead of memory, it addresses an I/O device

• Figure 1–11 shows the I/O map found in many personal computer systems.

Figure 1–11 Some I/O locations in a typical personal computer.

• Access to most I/O devices should always be made through Windows, DOS, or BIOS function calls.

• The map shown is provided as a guide to illustrate the I/O space in the system.

• The area below I/O location 0400H is considered reserved for system devices

• Area available for expansion extends from I/O port 0400H through FFFFH.

• Generally, 0000H - 00FFH addresses main board components; 0100H - 03FFH handles devices located on plug-in cards or also on the main board.

• The limitation of I/O addresses between 0000 and 03FFH comes from original standards specified by IBM for the PC standard.

225

AcknowledgementThe slides have been based in-part upon original slides of a numberof books including: The x86 PC: Assembly Language, Design, and Interfacing, 5/E,

M. A. Mazidi, J. G. Mazidi, D. Causey, Prentice Hall, 2010. Intel Microprocessors, 8th Ed., B. B. Brey, Prentice Hall, 2009. Mikroişlemciler ve Bilgisayarlar, 6. Basım, H. Gümüşkaya, ALFA,

2011.

Documents

Mp4-Introduction to Intel 80x86 Microprocessor Family