2015-10-30
TDTS 08
Advanced Computer Architecture
[Datorarkitektur]
www.ida.liu.se/~TDTS08
Zebo Peng
Embedded Systems Laboratory (ESLAB)
Dept. of Computer and Information Science (IDA)
Linköping University
Contact Information

Zebo Peng, course leader and examiner
Email: zebo.peng@liu.se

Ke Jiang, course and lab assistant
Email: ke.jiang@liu.se

Arian Maghazeh, lab assistant
Email: arian.maghazeh@liu.se

Åsa Kärrman, course secretary
Email: asa.karrman@liu.se
Zebo Peng, IDA, LiTH
2
TDTS 08 – Lecture 1
1
2015-10-30
Course Information

Web page  http://www.ida.liu.se/~TDTS08

Lectures
 12 lectures.
 Lecture notes will be available at the web page usually one day
before each lecture.
 The whole set of last year’s lecture notes is on the web.
 Lecture notes following the course book’s structure are also
available on the web.

Examination
 Written exam, closed book.
 Previous exam examples are at the course web site.
Zebo Peng, IDA, LiTH
3
TDTS 08 – Lecture 1
Course Information (cont’d)

Literature
 William Stallings: Computer Organization and
Architecture, 10th edition, Peason, 2015.
 Additional articles available at the website.
 http://williamstallings.com/ComputerOrganization/
• Student resources, incl. homework problems & solutions.
 You can also use:
• Older editions of Stallings’ book.
• Books covering the same subjects.
Ex. Hennessy and Patterson: “Computer Architecture: A
Quantitative Approach.”
Zebo Peng, IDA, LiTH
4
TDTS 08 – Lecture 1
2
2015-10-30
Course Information (cont’d)

Labs





Hands-on exercises with concepts taught in the course.
Use tools for architecture evaluation via simulation.
Give insights in various trade-offs involved in the design of computers.
Enhance the understanding of parallel computer systems.
Lab assignments





Lab 1: Cache Memories.
Lab 2: Instruction Pipelining.
Lab 3: Superscalar Processors.
Lab 4: VLIW Processors.
Lab 5: Multiprocessor and Multi-Computer Systems.

Please sign up for the labs in the website before November 11.

Additional information to be given in the seminar (lesson)

Wednesday November 11, 15-17.
Zebo Peng, IDA, LiTH
5
TDTS 08 – Lecture 1
Lecture 1



Computer architecture:
concepts and definitions
CPU and instruction
execution
What is expected from this
course
Zebo Peng, IDA, LiTH
6
TDTS 08 – Lecture 1
3
2015-10-30
Computer Architecture
Computer architecture refers to those attributes of a computer
system that are visible to programmers, or have a direct
impact on the logical execution of programs.

Control
Logic
Registers
Instruction
I/O Devices
ALU
Set
Memory
System
Zebo Peng, IDA, LiTH
7
TDTS 08 – Lecture 1
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.”
…
Zebo Peng, IDA, LiTH
8
TDTS 08 – Lecture 1
4
2015-10-30
Typical Architecture Attributes

The instruction set.

Data representation methods.

The basic hardware units in the CPU.

Functions of the main components.

Instruction execution.

Memory organization.

I/O mechanisms.

The ways in which the main components are
interconnected.

…
Zebo Peng, IDA, LiTH
9
TDTS 08 – Lecture 1
What is a Computer?
Zebo Peng, IDA, LiTH
10
TDTS 08 – Lecture 1
5
2015-10-30
Definition of a Computer

A computer is a data processing machine which is
operated automatically under the control of a list of
instructions stored in its main memory.
Computer
Central
Processing Unit
(CPU)
Data transfer
Main
Memory
Control
Zebo Peng, IDA, LiTH
11
TDTS 08 – Lecture 1
A 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
device
Computer
Output
device
Secondary
memory
Zebo Peng, IDA, LiTH
12
TDTS 08 – Lecture 1
6
2015-10-30
Microprocessor Market Share
General-purpose computers
98%
2%
Zebo Peng, IDA, LiTH
13
TDTS 08 – Lecture 1
Basic Principles of Computers
Virtually all modern computer designs are based on the
von Neumann architecture principles:

Data and instructions are stored in a
single read/write memory.

The contents of this memory are
addressable by location, without
regard to what are stored there.

Instructions are executed sequentially
(from one instruction to the next)
unless the order is explicitly modified.
CPU
Memory
Zebo Peng, IDA, LiTH
14
TDTS 08 – Lecture 1
7
2015-10-30
Why von Neumann Architecture?

General-purpose, programmable.
 They can solve very different problems
by executing different programs.


Instruction execution is done
automatically.
It can be built with very simple
electronics components:
 Data processing function is performed
by electronic gates.
 Data storage function is provided by
memory cells.
 Data communication is achieved by
electrical wires.
Zebo Peng, IDA, LiTH
15
CPU
Memory
TDTS 08 – Lecture 1
Technology Development
Eniac, 1946
Zebo Peng, IDA, LiTH
16
TDTS 08 – Lecture 1
8
2015-10-30
Technology Development
Year
Relative perf./cost
Technology
1951 Vacuum tube
1
1965 Transistor
35
1975 Integrated circuit (IC)
900
1995 Very large scale IC (VLSI)
2,400,000
2005 Ultra large scale IC
6,200,000,000
Eniac, 1946
Zebo Peng, IDA, LiTH
17
TDTS 08 – Lecture 1
Moore’s Law
# of trans.
1000 M
750 M
Number of transistors per chip
would double every 1.5 years.
Similar improvement in:
Clock Frequency (every 2 years)
Performance
Memory capacity
50 M
25 M
year
75
80
Zebo Peng, IDA, LiTH
85
90
18
95
00
05
10
TDTS 08 – Lecture 1
9
2015-10-30
Intel Microprocessor Evolution
Intel 8‐core Xeon
2.3 Billion Transistor
45nm Intel 4004
2.3 Thousands transistors
10000 nm
19
Images courtesy of Intel Corporation
Zebo Peng, IDA, LiTH
19
TDTS 08 – Lecture 1
Lecture 1



Computer architecture:
concepts and definitions
CPU and instruction
execution
What is expected from this
course
Zebo Peng, IDA, LiTH
20
TDTS 08 – Lecture 1
10
2015-10-30
Central Processing Unit (CPU)
The Central Processing Unit (CPU), also called
processor, includes two main units:
 A program control unit, and
 An Arithmetic and Logic Unit (ALU).
CPU
Arithmetic
and Logic
Unit
Control Unit
Register
Zebo Peng, IDA, LiTH
21
TDTS 08 – Lecture 1
CPU (Cont’d)

The primary function of a CPU is to execute the instructions
stored in the main memory.

An instruction tells the CPU to perform one of its basic
operations.

The CPU includes also a set of registers, which are
temporary storage devices used to hold control information,
key data, and intermediate results.

It includes also an internal bus infrastructure, which provides
data movement paths among the control unit, ALU, and
registers.

The CU is the one which interprets (decodes) the instruction
to be executed and "tells" the other components what to do.
Zebo Peng, IDA, LiTH
22
TDTS 08 – Lecture 1
11
2015-10-30
CPU Internal Structure
Zebo Peng, IDA, LiTH
23
TDTS 08 – Lecture 1
Registers

CPU must have some working space (temporary
storage).

These storage units are called registers.

They are the top level component in the memory
hierarchy.

Number and function of the registers vary
between different computers.

Register organization is one of the major design
decisions.
Zebo Peng, IDA, LiTH
24
TDTS 08 – Lecture 1
12
2015-10-30
Register Organization

The registers serve two main functions:
 User-Visible Registers: used by machine or assembly
language programmers to minimize memory access.
• General-purpose registers
• Data registers
• Address registers
• Condition code registers
 Control and Status Registers: used by the control unit
to control the operation of the CPU, and by the
operating system to control the execution of programs.
Zebo Peng, IDA, LiTH
25
TDTS 08 – Lecture 1
Machine Instructions

The CPU can only execute machine code in binary format,
called machine instructions.

A machine instruction specifies the following information:
 What has to be done (the operation code)
 To whom the operation applies (source operands)
 Where does the result go (destination operand)
 How to continue after the operation is finished (next instruction
address).

Machine instructions are of four types:
 Arithmetic and logic operations.
 Data transfer between memory and CPU registers.
 Program control (conditional branches, etc.).
 I/O transfer.
Zebo Peng, IDA, LiTH
26
TDTS 08 – Lecture 1
13
2015-10-30
Instruction Set Design

The design of an instruction set is critical to the operations
of a computer system. The most important issues are:
 Operation repertoire — How many and which operations to
provide, and how complex these operations should be.
 Data types — Which data types to be supported.
 Instruction format — Length, number of addresses, size of various
fields, etc.
 Registers — Number of CPU registers and their use.
 Addressing — Which modes to be provided.

The issues are highly interrelated and must be considered
together.
Zebo Peng, IDA, LiTH
27
TDTS 08 – Lecture 1
Instruction Execution Mechanism
PC
AR
IR
Control Unit
ALU
CPU
MAR
MBR
Address
D/I
Main Memory
Zebo Peng, IDA, LiTH
28
TDTS 08 – Lecture 1
14
2015-10-30
Instruction Execution
fetch cycle
fetch
execute cycle
decode
PC -> MAR
Decode(IR)
M[MAR] -> MBR
MBR -> IR
PC + 1 -> PC
execute
Perform the specified operation
(memory access may be needed)
(PC may be changed)
PC
AR
Control Unit
IR
MAR
Zebo Peng, IDA, LiTH
CPU
29
ALU
MBR
TDTS 08 – Lecture 1
Machine Cycles

The execution of an instruction is carried out in a machine
cycle (instruction cycle).

The CPU executes one instruction after the other, cycle by
cycle, repeatedly.

The machine cycle time (or instruction execution time) of a
computer gives an indication of its performance (speed).
 Ex. a computer can have a performance of 733 MIPS (Millions of
Instructions Per Second).

Since different instructions need different time to execute,
the average instruction execution time is often used.

Very common, FLOPS (Floating-point Operations Per
Second) is used nowadays.
Zebo Peng, IDA, LiTH
30
TDTS 08 – Lecture 1
15
2015-10-30
Summary
A computer executes repeatedly a series of instructions
(called programs) stored in its main memory:
 It performs data processing operations specified by the
programs.
 It runs the programs automatically, with no need for
human intervention.
 It can perform the operations in extremely high speed.
 It can store and manipulate a large amount of data.
 It can communicate with each other and with users in an
efficient way.
 It represents program and data in the same way, which
leads to flexibility.
Zebo Peng, IDA, LiTH
31
TDTS 08 – Lecture 1
Lecture 1



Computer architecture: concept
and definitions
CPU and instruction
execution
What is expected from this
course
Zebo Peng, IDA, LiTH
32
TDTS 08 – Lecture 1
16
2015-10-30
Computer Architecture

Computer architecture refers to those attributes of a computer
system that are visible to programmers, or have a direct
impact on the logical execution of programs.
Control
Logic
Registers
Instruction
I/O Devices
ALU
set
Memory
System
Zebo Peng, IDA, LiTH
33
TDTS 08 – Lecture 1
Computer Organization

Computer organization refers to the operational units and their
interconnections that realize the architectural specifications.
Registers
I/O Devices
ALU
Memory
System

Hidden Reg.
Microprog.
controller
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.
Zebo Peng, IDA, LiTH
34
TDTS 08 – Lecture 1
17
2015-10-30
Lecture Contents
1. Introduction: Basic concepts and definitions of computer
architecture and organizations.
2. Memory System: Memory hierarchy, cache memories,
virtual memories, memory management.
3. Instruction Pipelining: Organization, pipeline hazards,
reducing branch penalties, branch prediction strategies.
4. RISC Architectures: Analysis of instruction execution,
compiling for RISC computers, RISC-CISC trade-offs.
5. Superscalar Architectures: Instruction level parallelism
and machine parallelism, HW techniques for performance
enhancement, limitations.
6. VLIW Architectures: VLIW advantages and limitations,
compiling for VLIW architectures, the Merced (Itanium)
architecture.
Zebo Peng, IDA, LiTH
35
TDTS 08 – Lecture 1
Lecture Contents (Cont’d)
7.
Parallel Computation: Parallel programs, performance of
parallel computers, classification of architectures.
8.
SIMD Architectures: Vector processors, array processors,
multimedia extensions.
9.
MIMD Architectures: Symmetric multiprocessors, NUMA
architecture, and clusters.
10.
Cache Coherence in Parallel Architectures: Cache
design for parallel system, cache coherence protocols.
11.
Multi-Core Processor and GPU: Technology, hardware
issues, software impact, commercial examples.
12.
Low-Power Architectures: Power consumption in CMOS
circuits, designing for low power, Crusoe processor.
Zebo Peng, IDA, LiTH
36
TDTS 08 – Lecture 1
18