multi-processors-part1

molassesitalianAI and Robotics

Nov 6, 2013 (3 years and 5 months ago)

54 views

MULTIPROCESSORS


BY

K.SATYASREE

ASSISTANT PROFESSOR

ECE DEPARTMENT

VARDHAMAN COLLEGE OF ENGINEERING

UNIT


5

CONTENTS



Characteristics

of

Multiprocessors



Interconnection

Structures



Time
-
shared

Common

Bus



Multiport

Memory



Crossbar

Switch



Multistage

Switching

Network



Hypercube

System



Inter
-
processor

Arbitration



Serial

Arbitration

Procedure



Parallel

Arbitration

Logic



Dynamic

Arbitration

Algorithms



Inter
-
processor

Communication

and

Synchronization



Cache

Coherence



Shared

Memory

Multiprocessors

Peripheral Devices



Input

-

output

subsystem

of

a

computer

is

called

I/O
.




Familiar

means

of

entering

information

into

a

computer

is

through

keyboard
.



Input

or

output

devices

attached

to

the

computer

are

also

called

peripherals
.




Most

common

peripherals

are

keyboards,

display

units

and

printers
.




Peripherals

are

electromechanical

and

electromagnetic

devices

of

some

complexity
.




Input

and

output

devices

that

communicate

with

computer

in

standard

binary

code

for

alphanumeric

characters

is

ASCII

(American

Standard

Code

for

Information

Interchange)
.



It

uses

7

bits

to

code

128

characters
.

Input
-
Output Interface



I/O

interface

provides

a

method

for

transferring

information

between

internal

storage

and

external

I/O

devices
.




Purpose

of

I/O

interface

is

to

resolve

differences

that

exist

between

the

central

computer

and

each

peripheral
.




Major

differences

are
:




Peripherals

are

electromechanical

and

electromagnetic

devices

and

their

manner

of

operation

is

different

from

the

operation

of

the

CPU

and

memory

which

are

electronic

devices
.


conversion

of

signal

values

may

be

required
.




Data

transfer

rate

of

peripherals

is

usually

slower

than

the

transfer

rate

of

the

CPU
,

and

consequently,

a

synchronization

mechanism

may

be

needed
.




Data

codes

and

formats

in

peripherals

differ

from

the

word

format

in

the

CPU

and

memory
.




Operating

modes

of

peripherals

are

different

from

each

other
.

Input
-
Output Processor


IOP :


Communicate directly with all I/O devices with DMA capability


Fetch and execute its own instruction


IOP instructions are specifically designed to facilitate I/O transfer


DMAC must be set up entirely by the CPU


Designed to handle the details of I/O processing


Can also perform other processing tasks such as arithmetic, logic, branching
and code translation









Command


Instruction

that is read form memory by an
IOP


Different from instructions that are read by the CPU


Commands are prepared by experienced programmers and are stored in memory


Command word = IOP program


I/O Bus

Parallel Processing



Denotes

a

large

class

of

techniques

that

are

used

to

provide

simultaneous

data
-
processing

tasks

for

the

purpose

of

increasing

the

computational

speed

of

a

computer

system
.




Examples

of

Parallel

Processing
:



While

an

instruction

is

being

executed

in

the

ALU,

the

next

instruction

can

be

read

from

memory
.



System

may

have

2

or

more

ALUs

and

be

able

to

execute

2

or

more

instructions

at

the

same

time
.



System

may

have

2

or

more

processors

operating

concurrently
.




Purpose

of

Parallel

Processing
:



Speed

up

the

computer

processing

capability



increase

its

throughput
.




Throughput
:

Amount

of

processing

that

can

be

accomplished

during

a

given

interval

of

time
.


Parallel

Processing

having

multiple

functional

units

that

perform

different

operations

simultaneously

Flynn’s Classification


Till

now

what

ever

CPU

we

have

is

SISD

(Single

Instruction

Single

Data)

type

of

CPU
.

Capable

of

executing

only

one

instruction

with

only

one

data

at

a

time
.




Other

types

of

computers

which

can

be

built

are



SIMD

(Single

Instruction

Multiple

Data)

-

h a s

mu l t i p l e

p r o c e s s i n g

e l e me n t s

( f e w

no
.

of

registers

and

ALU)
.

All

processing

elements

will

execute

the

same

instruction

simultaneously

on

different

data
.



Application
:

Image

processing

(Image

=

M

x

N

pixels)



same

operation

should

be

performed

on

all

pixels



same

instruction

on

multiple

data
.




MISD

(Multiple

Instruction

Single

Data)

-

More

of

theoretical

importance
.




MIMD

(Multiple

Instruction

Multiple

Data)



widely

used

and

leads

to

distributed

computing
.

Has

a

number

of

independent

computers

each

computer

can

execute

different

programs
.




Main

Aim

:

To

Improve

the

performance

of

a

computer

these

different

types

of

CPU’s

are

designed

THANK YOU