CA 1 Introduction

dce
2010
COMPUTER ARCHITECTURE
CS2010
Faculty of Computer Science and Engineering
Department of Computer Engineering
BK
TP.HCM
Dinh Duc Anh Vu

http://www.cse.hcmut.edu.vn/~anhvu
dce
2010
Chapter 1
Computer Abstraction and
Technology
Adapted from Computer Organization and Design, 4th
Edition, Patterson & Hennessy, © 2008
Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 2

dce
2010
Review: Some Basic Definitions
• Kilobyte – 210 or 1,024 bytes
• Megabyte – 220 or 1,048,576 bytes
– sometimes “rounded” to 106 or 1,000,000 bytes
• Gigabyte – 230 or 1,073,741,824 bytes
– sometimes rounded to 109 or 1,000,000,000 bytes
• Terabyte – 240 or 1,099,511,627,776 bytes
– sometimes rounded to 1012 or 1,000,000,000,000 bytes
• Petabyte – 250 or 1024 terabytes
– sometimes rounded to 1015 or 1,000,000,000,000,000
bytes
• Exabyte – 260 or 1024 petabytes
– Sometimes rounded to 1018 or 1,000,000,000,000,000,000
bytes

dce
2010
Definition of a Computer
• A computer is a data processing machine
which is operated automatically under the
control of a list of instructions (called a
program) stored in its main memory.
Computer
Central
Data Transfer Main
Processing Unit
Memory
(CPU) Control

dce
2010
Computer System
• A computer system consists of a computer
and its peripherals.
• Computer peripherals include input devices,
output devices, and secondary memories.
Computer System
Input Output
devices
Computer devices
Secondary
memory

dce
2010
Classes of Computers
• Desktop computers
– Designed to deliver good performance to a single user at low cost usually executing 3rd party
software, usually incorporating a graphics display, a keyboard, and a mouse
– General purpose, variety of software
– Subject to cost/performance tradeoff
• Servers
– Used to run larger programs for multiple, simultaneous users typically accessed only via a
network and that places a greater emphasis on dependability and (often) security
– Network based
– High capacity, performance, reliability
– Range from small servers to building sized
• Supercomputers
– A high performance, high cost class of servers with hundreds to thousands of processors,
terabytes of memory and petabytes of storage that are used for high-end scientific and
engineering applications
• Embedded computers (processors)
– A computer inside another device used for running one predetermined application
– Hidden as components of systems
– Stringent power/performance/cost constraints

dce
2010
Growth in Cell Phone Sales (Embedded)
embedded growth >> desktop growth
1200
Cell Phones PCs TVs
1000
800
In Millions
600
400
200
• Where else are embedded processors found?

dce
2010
Embedded Computers in Your Car

dce
2010
Embedded Computers in Your Car
Embedded Systems

dce
2010
Embedded Processor Characteristics
The largest class of computers spanning the
widest range of applications and performance
• Often have minimum performance

requirements. Example?
• Often have stringent limitations on cost.
Example?
• Often have stringent limitations on power
consumption. Example?
• Often have low tolerance for failure. Example?
dce
2010
The Computer Revolution
• Progress in computer technology
– Underpinned by Moore’s Law
• Makes novel applications feasible
– Computers in automobiles
– Cell phones
– Human genome project
– World Wide Web
– Search Engines
• Computers are pervasive

dce
2010
The Evolution of Computer Hardware
• When was the first transistor invented?
The 1st transistor

(Bell Labs, 1947)
dce
2010
The Evolution of Computer Hardware
• When was the first IC (integrated circuit) invented?

dce
2010
The Underlying Technologies
Year Technology Relative Perform/Unit Cost
1951 Vacuum Tube 1
1965 Transistor 35
1975 Integrated Circuit (IC) 900
1995 Very Large Scale IC (VLSI) 2,400,000
2005 Submicron VLSI 6,200,000,000
What if technology in the transportation

industry advanced at the same rate?

dce
2010
Moore’s Law
• In 1965, Intel’s Gordon Moore Dual Core Itanium
predicted that the number of with 1.7B transistors
transistors that can be integrated
on single chip would double
about every two years
feature size
&
die size
Courtesy, Intel ®
dce
2010
PowerPC 750
• Introduced in 1999
• 3.65M transistors
• 366 MHz clock rate
• 40 mm2 die size
• 250nm (0.25micron)
technology

dce 2010
AMD’s Barcelona Multicore Chip
HT PHY, link 1 Slow IO Fuses • Four out-of-
http://www.techwarelabs.com/reviews/processors/barcelona/
128-bit FPU order cores on

HT PHY, link 2
2MB Load/ L1 Data 512kB one chip

Shared Store Cache
• 1.9 GHz clock
L2 Core 2
Cache
L3 Execution L2
Cache Fetch/ Ctl
Decode/ L1 Instr
rate
Branch Cache D
D
• 65nm
Northbridge R
P
technology
H
Y
• Three levels of
caches (L1,
HT PHY, link 3
Core 4 Core 3
L2, L3) on chip
• Integrated
Northbridge
HT PHY, link 4 Slow IO Fuses

dce
2010
Technology Scaling Road Map (ITRS)
• Fun facts about 45nm transistors
– 30 million can fit on the head of a pin
– You could fit more than 2,000 across the width of
a human hair
– If car prices had fallen at the same rate as the
price of a single transistor has since 1968, a new
car today would cost about 1 cent
Year 2004 2006 2008 2010 2012
Feature size (nm) 90 65 45 32 22
Intg. Capacity (BT) 2 4 6 16 32

dce
2010
Evolution in DRAM Chip Capacity
human memory
human DNA
100,000,000
64,000,000
4X growth every 3 years! 16,000,000
10,000,000 0.07 m
4,000,000
0.1 m
Kbit capacity/chip
1,000,000 1,000,000
book 0.13 m
256,000
100,000 0.18-0.25 m
64,000
0.35-0.4 m
16,000
10,000
0.5-0.6 m
4,000
1,000 1,000
0.7-0.8 m
encyclopedia
1.0-1.2 m
256 2 hrs CD audio
1.6-2.4 m
100
64 30 sec HDTV
page
10
1980 1983 1986 1989 1992 1995 1998 2001 2004 2007 2010
Year
dce
2010
Growth in Processor Performance

dce
2010
But What Happened to Clock Rates
and Why?
• Clock rates hit a
“power wall”
120
100
Power (Watts)
80
60
40
20
0

dce
2010
A Sea Change is at Hand
• The power challenge has forced a change in the design of
microprocessors
– Since 2002 the rate of improvement in the response time of
programs on desktop computers has slowed from a factor of 1.5
per year to less than a factor of 1.2 per year
• As of 2006 all desktop and server companies are shipping
microprocessors with multiple processors – cores – per
chip
Product AMD Intel Nehalem IBM Power 6 Sun Niagara
Barcelona 2
Cores per chip 4 4 2 8
Clock rate 2.5 GHz ~2.5 GHz? 4.7 GHz 1.4 GHz
Power 120 W ~100 W? ~100 W? 94 W
• Plan of record is to double the number of cores per chip per

generation (about every two years)
dce
2010
Technology Outlook
High Volume
Manufacturing 2004 2006 2008 2010 2012 2014 2016 2018
Technology Node
(nm) 90 65 45 32 22 16 11 8
Integration Capacity
(BT) 2 4 8 16 32 64 128 256
Delay = CV/I scaling 0.7 ~0.7 >0.7 Delay scaling will slow down
Energy/Logic Op
scaling >0.35 >0.5 >0.5 Energy scaling will slow down
Bulk Planar CMOS High Probability Low Probability
Alternate, 3G etc Low Probability High Probability
Variability Medium High Very High
ILD (K) ~3 <3 Reduce slowly towards 2 to 2.5
RC Delay 1 1 1 1 1 1 1 1
Metal Layers 6-7 7-8 8-9 0.5 to 1 layer per generation

dce
2010
Impacts of Advancing Technology
• Processor
– logic capacity: increases about 30% per year
– performance: 2x every 1.5 to 2 years
• Memory
– DRAM capacity: 4x every 3 years, about 60% per year
– speed: 1.5x every 10 years
– cost per bit: decreases about 25% per year
• Disk
– capacity: increases about 60% per year
– speed:
– cost per bit:

dce
2010
Under the Covers
• Five classic components of a computer – input,
output, memory, datapath, and control
• Same components for all kinds of computer
– Desktop, server, embedded
• Input/output includes
– User-interface devices
• Display, keyboard, mouse
– Storage devices
• Cache (SRAM), main memory (DRAM), hard disk, CD/DVD,
flash
– Network adapters
• For communicating with other computers

dce
2010
Components of a Computer
• Our primary focus:
the processor
(datapath and
control)
– Implemented using
millions of transistors
– Impossible to
understand by
looking at each
transistor
– We need abstraction!

dce
2010
Computer Architecture
• Computer architecture refers to those attributes of a
computer system visible to programmers, or those
attributes that have a direct impact on the logical
execution of programs.
Registers
Registers
Registers
Instruction
I/O Devices ALU Set
Memory
System

dce
2010
Typical Architecture Attributes
• The instruction set (instruction types and operations)
– With associated argument fields, assembly syntax, and machine
encoding.
• Basic data representation methods
– Types and sizes of operands
• I/O mechanisms
• The basic units in the CPU
• Functions of the major components
• Instruction execution
– Control flow instructions
• Memory organization (memory addressing techniques)
– A set of addressing modes (ways to name locations)
• The ways in which the basic components are interconnected
– Often an I/O interface (usually memory-mapped)
• …

dce
2010
Many Definitions for CA
• “The science and art of selecting and
interconnecting hardware components to
create computers that meet functional,
performance and cost goals.”
• “The theory behind the design of a computer.”
• “The conceptual design and fundamental
operational structure of a computer system.”
• “The arrangement of computer components
and their relationships.”
• …

dce
2010
Computer Organization
• Computer organization refers to the operational units and
their interconnections that realize the architectural
specifications (i.e. how features are implemented)
– Control signals, interfaces between the computer and peripherals,
memory technology
Registers Hidden Reg.

I/O Devices ALU
Memory Micro-program
System controller

dce
2010
Architecture vs. Organization (1)
• Ex. Multiplication function:
– Architectural issue: having a multiply instruction or
not.
– Organization issue: a special multiply unit or
repeated use of the add unit to perform
multiplication.

dce
2010
• Many computer manufacturers offer a family of
computer models, all with the same architecture but
with differences in organisation
– All Intel x86 family share the same basic architecture
– The IBM System/370 family share the same basic
architecture
• This gives
– Different models in the family have different price and
performance
– Organization changing with changing technology
• Code compatibility
• At least backwards

dce
2010
• In microcomputer, the relationship between
architecture and organization is very close
– Changes in technology not only influence
organization but also result in the introduction of
more powerful and more complex architectures

dce
2010
Structure & Function
• Recognize the hierarchical nature of most complex
systems
– Hierarchical system is a set of interrelated subsystems,
each of the latter, in turn, hierarchical in structure until we
reach some lowest level of elementary subsystem
• Structure is the way in which components relate to
each other
• Function is the operation of individual components
as part of the structure
• In terms of description, there are 2 choices
– Bottom-up
– Top-down

dce
2010
Functional View
• All computer functions are:
– Data processing
– Data storage
– Data movement
– Control

dce
2010
Operations (a)
Data movement

dce
2010
Operations (b)
Storage

dce
2010
Operations (c)
Processing from/to storage

dce
2010
Operations (d)
Processing from storage to I/O

dce
2010
Structure – Top Level
Peripherals Computer
Central
Main
Processing
Memory
Unit
Computer Systems
Interconnection
Input
Communication
Output
lines

dce
2010
Structure – The CPU
CPU
Computer
Arithmetic
Registers and
I/O
System Logic Unit
CPU
Bus Internal CPU
Memory Interconnection
Control
Unit

dce
2010
Structure – The Control Unit
Control Unit
CPU Sequencing
ALU Logic
Internal Control
Bus Unit Control Unit
Registers Registers and
Decoders
Control
Memory

dce
2010
Understanding Performance
• Algorithm
– Determines number of operations executed
• Programming language, compiler, architecture
– Determine number of machine instructions executed per
operation
• Processor and memory system
– Determine how fast instructions are executed
• I/O system (including OS)
– Determines how fast I/O operations are executed

dce
2010
Why Learn This Stuff?
• You want to call yourself a “computer scientist/engineer”
• You want to build HW/SW people use (so you need to
deliver performance at low cost)
• You need to make a purchasing decision or offer “expert”
advice
• Both hardware and software affect performance

– The algorithm determines number of source-level statements
– The language/compiler/architecture determine the number of
machine-level instructions
• (Chapter 2 and 3)
– The processor/memory determine how fast machine-level
instructions are executed
• (Chapter 5, 6, and 7)

dce
2010
Below the Program
Applications software
Systems software
Hardware
• Application software
– Written in high-level language
• System software
– Operating system – supervising program that interfaces the user’s
program with the hardware (e.g., Linux, MacOS, Windows)
• Handles basic input and output operations
• Allocates storage and memory
• Provides for protected sharing among multiple applications
– Compiler – translate programs written in a high-level language (e.g., C,
Java) into instructions that the hardware can execute
• Hardware
– Processor, memory, I/O controllers

dce
2010
Below the Program (Con’t)
• High-level language program (in C)
swap (int v[], int k)
(int temp;
temp = v[k]; one-to-many
v[k] = v[k+1];
v[k+1] = temp;
) C compiler
• Assembly language program (for MIPS)

swap: sll $2, $5, 2
add $2, $4, $2
lw $15, 0($2) one-to-one
lw $16, 4($2)
sw $16, 0($2)
sw $15, 4($2)
jr $31 Assembler
• Machine (object, binary) code (for MIPS)
000000 00000 00101 0001000010000000
000000 00100 00010 0001000000100000
. . .

dce
2010
Advantages of Higher-Level Languages ?
• Higher-level languages
• As a result, very little programming is done today at the

assembler level

dce
2010
Below the Program (Con’t)
• High-level language program (in C)
swap (int v[], int k)
(int temp;
temp = v[k];
v[k] = v[k+1];
v[k+1] = temp;)
• Assembly language program (for MIPS) C compiler
swap: sll $2, $5, 2
add $2, $4, $2
lw $15, 0($2)
lw $16, 4($2)
sw $16, 0($2)
sw $15, 4($2)
jr $31
• Machine (object, binary) code (for MIPS)
Assembler
000000 00000 00101 0001000010000000
000000 00100 00010 0001000000100000
100011 00010 01111 0000000000000000
100011 00010 10000 0000000000000100
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
000000 11111 00000 0000000000001000

dce
2010
Input Device Inputs Object Code
000000 00000 00101 0001000010000000
000000 00100 00010 0001000000100000
100011 00010 01111 0000000000000000
100011 00010 10000 0000000000000100
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
000000 11111 00000 0000000000001000
Processor Memory Devices

Network
Control
Input
Datapath Output

dce
2010
Object Code Stored in Memory

000000 00000 00101 0001000010000000 Network
000000 00100 00010 0001000000100000
Control 100011 00010 01111 0000000000000000
100011 00010 10000 0000000000000100 Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output

dce
2010
Processor Fetches an Instruction
Processor fetches an instruction from memory

000000 00000 00101 0001000010000000 Network
000000 00100 00010 0001000000100000
Control 100011 00010 01111 0000000000000000
100011 00010 10000 0000000000000100 Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output

dce
2010
Control Decodes the Instruction
Control decodes the instruction to determine what
to execute

000000 00000 00101 0001000010000000 Network
000000 00100 00010 0001000000100000
Control 100011 00010 01111 0000000000000000
000000 00100 00010 0001000000100000
100011 00010 10000 0000000000000100 Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output

dce
2010
Datapath Executes the Instruction
Datapath executes the instruction as directed by
control

000000 00000 00101 0001000010000000 Network
000000 00100 00010 0001000000100000
Control 100011 00010 01111 0000000000000000
000000 00100 00010 0001000000100000
100011 00010 10000 0000000000000100 Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output
contents Reg #4 ADD contents Reg #2
results put in Reg #2

dce
2010
What Happens Next?

000000 00000 00101 0001000010000000 Network
000000 00100 00010 0001000000100000
Control 100011 00010 01111 0000000000000000
100011 00010 10000 0000000000000100 Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output

dce
2010
Processor Organization
• Control needs to have circuitry to
• Datapath needs to have circuitry to
What location does it load from and store to?

dce
2010
Output Data Stored in Memory
At program completion the data to be output
resides in memory

Network
Control
Input
101011 00010 10000 0000000000000000
101011 00010 01111 0000000000000100
Datapath 000000 11111 00000 0000000000001000 Output

dce
2010
Output Device Outputs Data

Network
Control
Input
Datapath Output
101011 00010 10000 0000000000000000

101011 00010 01111 0000000000000100
000000 11111 00000 0000000000001000

dce
2010
Abstractions
• Abstraction helps us deal with complexity
– Hide lower-level detail
• Instruction set architecture (ISA)
– The hardware/software interface
• Application binary interface (ABI)
– The ISA plus system software interface
• Implementation
– The details underlying and interface

dce
2010
The Instruction Set Architecture (ISA)
software
instruction set architecture
hardware
The interface description separating the

software and hardware

dce
2010
Instruction Set Architecture (ISA)
• ISA, or simply architecture – the abstract interface
between the hardware and the lowest level software
that encompasses all the information necessary to
write a machine language program, including
instructions, registers, memory access, I/O, …
– Enables implementations of varying cost and performance
to run identical software
• The combination of the basic instruction set (the ISA)

and the operating system interface is called the
application binary interface (ABI)
– ABI – The user portion of the instruction set plus the
operating system interfaces used by application
programmers. Defines a standard for binary portability
across computers.

dce 2010
ISA Type Sales
Other
SPARC
1400
Hitachi SH
1200 PowerPC
Millions of Processor
Motorola 68K
1000
MIPS
800 IA-32
ARM
600
400
200
0
1998 1999 2000 2001 2002

dce
2010
How Do the Pieces Fit Together?
Applications
Operating
System
Instruction Set Compiler Firmware
Architecture Memory I/O system network
Processor
system
Datapath & Control
Digital Design
Circuit Design
• Coordination of many levels of abstraction

• Under a rapidly changing set of forces
• Design, measurement, and evaluation

CA 1 Introduction

Caricato da

Informazioni sul documento

Descrizione originale:

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

CA 1 Introduction

Caricato da

Copyright:

Formati disponibili

dce

Dinh Duc Anh Vu

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 2

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 3

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 4

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 5

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 6

• Where else are embedded processors found?

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 8

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 9

• Often have minimum performance

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 11

The 1st transistor

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 13

What if technology in the transportation

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 14

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 16

128-bit FPU order cores on

2MB Load/ L1 Data 512kB one chip

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 17

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 18

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 20

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 21

• Plan of record is to double the number of cores per chip per

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 23

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 24

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 25

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 26

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 27

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 28

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 29

Registers Hidden Reg.

I/O Devices ALU

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 30

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 31

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 32

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 33

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 34

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 35

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 36

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 37

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 38

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 39

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 40

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 41

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 42

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 43

• Both hardware and software affect performance

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 44

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 45

• Assembly language program (for MIPS)

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 46

• As a result, very little programming is done today at the

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 47

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 48

Processor Memory Devices

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 49

Processor Memory Devices

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 50

Processor Memory Devices

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 51

Processor Memory Devices

Computer Architecture – Chapter 1 ©2010, Dr. Dinh Duc Anh Vu 52