Computer Architecture

Ngo Lam Trung, Pham Ngoc Hung, Hoang Van Hiep

Department of Computer Engineering
School of Information and Communication Technology
Hanoi University of Science and Technology
E-mail: [trungnl, hungpn, hiephv]@soict.hust.edu.vn

IT3030E Fall 2024 1

 Course administration
❑ Textbook: [Required] Computer Organization and
Design RISC-V 2nd edition, Patterson &
Hennessy 2021.
[Optional] Computer Organization and
Architecture, 10th Edition, William Stalling
❑ Slides: pdf
❑ Schedule: as in timetable

IT3030E Fall 2024 2

 Course syllabus
❑ Chapter 1: Introduction
❑ Chapter 2: Computer System and Interconnection
❑ Chapter 3: Instruction Set Architecture
❑ Chapter 4: Computer Arithmetic
❑ Chapter 5: CPU
❑ Chapter 6: Memory
❑ Chapter 7: I/O system
❑ Chapter 8: Multicores and multiprocessors

IT3030E Fall 2024 3

 Computers are so important
❑ Current modern life
l Industrial revolutions, the 3rd (Automation) and the 4th (Digital
revolution).
l Cell phones, the Internet, Grab, Google Maps...
l WWW, search engines, social networks, e-commerce…
l Robotics, EV, UAV, self-driving cars,…

❑ Future
l Tailored medical care based on individual genome.
l Super-human: transfer human’s brain to a mechanical body
(robot) for interstellar traveling (The Matrix movies franchise,
1999, Michio Kaku, Physics of the Future 2011 and The Future
of the Mind 2015).
l …and many more

IT3030E Fall 2024 4

 Outcomes from this course
❑ Computer Architecture and Organization
l Understanding of basic computer system organization.
l Abstraction and instruction set architecture: how high-level
language programs translate into computer language programs,
and how hardware execute the latter programs.
l Hardware/software interface, and how software instructs
hardware to perform functions.

❑ Computer performance
l How to evaluate performance
l Basic techniques to improve computer performance.

IT3030E Fall 2024 5

 Study guide
❑ Do read the textbook and APPENDIX A!
❑ Attend class regularly, stay focused.
❑ Comprehend all exercises and homework.
❑ Old-school approach: pen and paper for doing exercise
and taking notes.
❑ Experience in C/C++ will be useful.
❑ Code of conduct:
l No web surfing, music, video, game in class.
l Food is not allowed (water/soft drink OK).

❑ Mid-term and Final exam will be online quiz, with topics

from exercises and homework.

IT3030E Fall 2024 6

 Homework/exercises
❑ RISC-V assembly programming
❑ RISC-V simulator (RARS 1.6)

IT3030E Fall 2024 7

 Chapter 1: Introduction

1. Computer Abstraction and Technology

2. Performance Evaluation

[with materials from Computer Organization and Design RISC-V Edition,

Patterson & Hennessy, ©2021, MK
IT3030E Fall 2024
and M.J. Irwin’s presentation, PSU 2008] 8
 1. Computer Abstraction and Technology
❑ What is a computer?
❑ Computer classification
❑ Computer generations
❑ The key of computer evolution: IC making technology
❑ Computer organization

IT3030E Fall 2024 9

 1. Computer Abstraction and Technology
❑ What is a computer?
❑ A machine that
l Accepts input data
l Processes data by executing a stored program
l Produces output

❑ Which one is computer?

IT3030E Fall 2024 10

 Classes of Computers
❑ Supercomputers
l Super fast + expensive for high-end applications

❑ Server
l Network based
l High capacity, performance, reliability
l Range from small servers to building sized

❑ Desktop computers
l General purpose, variety of software
l Subject to cost/performance tradeoff

❑ Embedded computers
l Hidden as components of systems
l Stringent power/performance/cost constraints

IT3030E Fall 2024 11

 Dominant look and feel of computer classes

Embedded

PC

Server
Super computer
IT3030E Fall 2024 12
 Price/performance of computer classes

Super $Millions
Mainframe
$100s Ks
Server $10s Ks
Differences in scale,
not in substance Workstation $1000s

Personal $100s

Embedded $10s

IT3030E Fall 2024 13

 Post-PC era
❑ PDA, smart phone, tablet…
❑ Smart TV, set top box…
❑ Cloud computing (AMZ EC2, cloud gaming…)

The number manufactured per year of tablets and smart phones

IT3030E Fall 2024 Smartphone sales worldwide 2007-2023 | Statista 14

 Seven important ideas in computer architecture

Simplification Make common Performance

via abstraction cases fast via Parallelism

Performance Performance Memory Dependability

via Pipelining via Prediction hierarchy via
redundancy
IT3030E Fall 2024 15
 A brief history of computers
❑ 0th generation: mechanical/analog calculators
l Jacquard’s punch card: for textile factories, later used for the first
computers
l Pascalite machine
l Babage’s Analytical Engine
l Ada Lovelace: first computer program!!!

Pascalite machine
Babbage’s Analytical Engine (plan 25)
Curiosity Stream - Calculating Ada: The Countess of Computing
IT3030E Fall 2024 16
 A brief history of computers
❑ 1st generation: Vacuum tubes
l ENIAC: 1st general purpose computer
- Computing artillery-firing tables
- Enormous in size and energy consumption
l IAS: computer with Von Newman architecture
- Memory, ALU, Control, Input/Output, stored-program concept
l UNIVAC: 1st commercial computer

IT3030E Fall 2024 17

 A brief history of computers
❑ 2nd generation: transistor
❑ Computer became smaller and faster

IBM System/360
IT3030E Fall 2024 18
 A brief history of computers
❑ Later generations: IC and VLSI
❑ Increasing price/performance
❑ Moore’s law

W.Stallings, COA, 10th edition

IT3030E Fall 2024 19

 Key to computer evolution: IC making technology

The chip manufacturing process

IT3030E Fall 2024 20

 Video: How an IC is made

IT3030E Fall 2024 21

 Moore’s Law

IT3030E Fall 2024

How do we benefit from this? 22
 Key to computer evolution: IC making technology

❑ Electronics technology continues to evolve

l Increased capacity and performance
l Reduced cost

[Textbook COD 5th edition]

IT3030E Fall 2024 23
 Hardware/software interface: abstraction

❑ Application software
l Written in high-level language (HLL)

❑ System software
l Compiler: translates HLL code to
machine code
l Operating System: service code
- Handling input/output
- Managing memory and storage
- Scheduling tasks & sharing resources

❑ Hardware
l Processor, memory, I/O controllers

IT3030E Fall 2024 24

 Levels of Program Code

❑ High-level language
l Level of abstraction closer to
problem domain
l Provides for productivity and
portability

❑ Assembly language
l Textual representation of
instructions

❑ Hardware representation
l Binary digits (bits)
l Encoded instructions and
data
IT3030E Fall 2024 25
 What’s below your program?
❑ High-level language program (in C)
swap (int v[], int k)
{ int temp;
temp = v[k];
v[k] = v[k+1]; one-to-many
v[k+1] = temp;
C compiler
}

❑ Assembly language program (for RISC-V CPU)

swap: slli x6, x11, 3
add x6, x10, x6
lw x5, 0(x6)
lw x7, 4(x6) one-to-one
sw x7, 0(x6)
sw x5, 4(x6)
assembler
jalr x0, 0(x1)

❑ Machine (object, binary) code (for RISC-V CPU)

00000000001101011001001100010011
00000000011001010000001100110011
00000000000000110011001010000011
IT3030E Fall 2024 . . . 26
 Computer Organization
❑ Computer’s basic operation
Input data
Process data by executing stored program
Output data

❑ What are required components of computer?

For data input:
For storing information:
For program execution and data processing:
For data output:

IT3030E Fall 2024 27

 Computer Organization
❑ Five classic components of a computer – input, output,
memory, datapath, and control

❑ datapath +
control =
processor
(CPU)

IT3030E Fall 2024 28

 Computer Organization (in real-world products)
❑ Where are CPU, mem, I/O?

iPhone XS Max teardown

IT3030E Fall 2024 29
 Computer Organization (in real-world products)
❑ Where are CPU, mem, I/O?

iPhone XS Max mainboard

IT3030E Fall 2024 30
 Computer Organization (in real-world products)
❑ Is the CPU only a “CPU”?

Apple A12 package

IT3030E Fall 2024 31
 2. Computer performance evaluation
❑ What is performance?
❑ A storage system
How much time to find a file/object?
How much time to transfer a file?
How many files can be served simultaneously?

❑ A web server
How fast a request can be served?
How many request can be served per second?

❑ Performance is multi-dimensional with many criteria

Throughput
Response time
…

❑ We focus on response time

IT3030E Fall 2024 32
 2. Computer performance evaluation
❑ Response time:
System performance: elapsed time on unload system
CPU performance: user CPU time, the time that CPU actually
spent on executing user program.

❑ To maximize performance, need to minimize execution

time

If computer X is n times faster than Y, then

IT3030E Fall 2024 33

 Relative Performance Example
❑ If computer A runs a program in 10 seconds and
computer B runs the same program in 15 seconds, how
much faster is A than B?
We know that A is n times faster than B if

performanceA execution_timeB
-------------------- = --------------------- = n
performanceB execution_timeA

The performance ratio is 15

------ = 1.5
10
Assume performance of B is 1, then performance of A
is 1.5

IT3030E Fall 2024 34

 Performance Factors
❑ CPU execution time (CPU time) – time the CPU spends
working on a task
l Does not include time waiting for I/O or running other programs

CPU execution time = # CPU clock cyclesx clock cycle time

for a program for a program

= #-------------------------------------------
CPU clock cycles for a program
clock rate

❑ Can improve performance by reducing either the length

of the clock cycle or the number of clock cycles required
for a program
IT3030E Fall 2024 35
 Review: Machine Clock Rate

❑ Clock rate (clock cycles per second in MHz or GHz) is

inverse of clock cycle time (clock period)
CC = 1 / CR

1 nsec (10-9) clock cycle => 1 GHz (109) clock rate

500 psec clock cycle => 2 GHz clock rate
250 psec clock cycle => 4 GHz clock rate
200 psec clock cycle => 5 GHz clock rate

IT3030E Fall 2024 36

 Improving Performance Example
❑ A program runs on computer A with a 2 GHz clock in 10
seconds. What clock rate must computer B run at to run
this program in 6 seconds? Assume that, computer B
will require 1.2 times as many clock cycles as computer
A to run the program.
CPU timeA = -------------------------------
CPU clock cyclesA
clock rateA
CPU clock cyclesA = 10 sec x 2 x 109 cycles/sec
= 20 x 109 cycles
1.2 x 20 x 109 cycles
CPU timeB = -------------------------------
clock rateB
1.2 x 20 x 109 cycles = 4 GHz
clock rateB = -------------------------------
6 seconds
IT3030E Fall 2024 37
 Clock Cycles per Instruction
❑ Not all instructions take the same amount of time to
execute
l Average execution time ~ average clock cycles per instruction

# CPU clock cycles # Instructions Average clock cycles

= x
for a program for a program per instruction

❑ Clock cycles per instruction (CPI) – the average number of

clock cycles each instruction takes to execute
A way to compare two different implementations of the same ISA

CPI for this instruction class

A B C
CPI 1 2 3
IT3030E Fall 2024 38
 Using the Performance Equation
❑ Computers A and B implement the same ISA. Computer
A has a clock cycle time of 250 ps and an effective CPI of
2.0 for some program and computer B has a clock cycle
time of 500 ps and an effective CPI of 1.2 for the same
program. Which computer is faster and by how much?
Each computer executes the same number of
instructions, I, so
CPU timeA = I x 2.0 x 250 ps = 500 x I ps
CPU timeB = I x 1.2 x 500 ps = 600 x I ps

Clearly, A is faster … by the ratio of execution times

performanceA execution_timeB 600 x I ps
------------------- = --------------------- = ---------------- = 1.2
performanceB execution_timeA 500 x I ps

IT3030E Fall 2024 39

 The Performance Equation
❑ Our basic performance equation is then calculated

CPU time = Instruction_count x CPI x clock_cycle

Instruction_count x CPI
= -----------------------------------------------
clock_rate

❑ Key factors that affect performance (CPU execution time)

The clock rate: CPU specification
CPI: varies by instruction type and ISA implementation
Instruction count: measure by using profilers/ simulators

IT3030E Fall 2024 40

 Dynamic Instruction Count

How many Each “for” consists of two

instructions are instructions: increment index,
executed in this check exit condition
program fragment? 12,422,450 Instructions
250 instructions
for i = 1, 100 do 2 + 20 + 124,200 instructions
20 instructions 100 iterations
for j = 1, 100 do 12,422,200 instructions in all
40 instructions 2 + 40 + 1200 instructions
for k = 1, 100 do 100 iterations
10 instructions 124,200 instructions in all
endfor 2 + 10 instructions
endfor 100 iterations for i = 1, n
endfor 1200 instructions in while x > 0
Static count = 326 all

IT3030E Fall 2024 41

 Improving performance by CPI
Op Freq CPIi Freq x CPIi
ALU 50% 1
Load 20% 5
Store 10% 3
Branch 20% 2

𝐴𝑣𝑔 𝐶𝑃𝐼 = ෍ 𝑓𝑟𝑒𝑞𝑖 ∗ 𝐶𝑃𝐼𝑖 =

❑ How much faster would the machine be if a better data cache

reduced the average load time to 2 cycles?

❑ What if branch instruction is only one cycle?

❑ What if two ALU instructions could be executed at once?

IT3030E Fall 2024 42

 Improving performance by CPI
Op Freq CPIi Freq x CPIi
ALU 50% 1 .5 .5 .5 .25
Load 20% 5 1.0 .4 1.0 1.0
Store 10% 3 .3 .3 .3 .3
Branch 20% 2 .4 .4 .2 .4

𝐴𝑣𝑔 𝐶𝑃𝐼 = ෍ 𝑓𝑟𝑒𝑞𝑖 ∗ 𝐶𝑃𝐼𝑖 = 2.2 1.6 2.0 1.95

❑ How much faster would the machine be if a better data cache

reduced the average load time to 2 cycles?
CPU time new = 1.6 x IC x CC so 2.2/1.6 means 37.5% faster
❑ What if branch instruction is only one cycle?
CPU time new = 2.0 x IC x CC so 2.2/2.0 means 10% faster
❑ What if two ALU instructions could be executed at once?
CPU time new = 1.95 x IC x CC so 2.2/1.95 means 12.8% faster
IT3030E Fall 2024 43
 How to improve performance?
❑ Shorter clock cycle = faster clock rate
→ latest CPU technology
❑ Smaller CPI
→ optimizing Instruction Set Architecture
❑ Smaller instruction count
→ optimizing algorithm and compiler
❑ To get best performance, multiple criteria are combined
and considered at design time
→ specific CPU for specific class computation problem

IT3030E Fall 2024 44

 Faster Clock  Shorter Running Time

Suppose addition takes 1 ns

Clock period = 1 ns; 1 cycle
Clock period = ½ ns; 2 cycles Solution
1 GHz

4 steps

20 steps

2 GHz In this example, addition time

does not improve in going from
1 GHz to 2 GHz clock

Faster steps do not necessarily mean

shorter travel time.

IT3030E Fall 2024 45

 Measuring/benchmarking PC performance
❑ SPEC CPU benchmark
l Started in 1989
l SPEC CPU2006: 12 integer, 17 floating point benchmarks
l Reference machine: Sun Ultra Enterprise 2 (1997) running on a
296 MHz UltraSPARC II CPU.

FIGURE 1.18 SPECINTC2006 benchmarks running on a 2.66 GHz Intel Core i7 920.
IT3030E Fall 2024 46
 (Uni)processor performance since 1908

Reference machine: VAX 11/780 (5MHz)

Change to multi-processors

IT3030E Fall 2024 47

 End of chapter 1

IT3030E Fall 2024 48