1. Arquitetura de Computadores I
Fabiano Hessel
Eduardo Augusto Bezerra

2. Overheads for Computers as Components
Bibliografia
Livro texto
Patterson, D. A. & Hennessy, J. L. Organização e projeto de computadores: a interface hardware/software
Livros referenciados e outras referências
Disponíveis na página da disciplina
Slides disponíveis na página
© 2000 Morgan Kaufman
Overheads for Computers as Components

3. Overheads for Computers as Components
Conteúdo
Revisão de conceitos (Anexo B)
Avaliação de desempenho de arquiteturas (Cap. 2)
Pipelines (Cap. 6 - Cap. 3)
Aritmética computacional (Cap. 4)
Tradução de código (Anexo A)
© 2000 Morgan Kaufman
Overheads for Computers as Components

4. Overheads for Computers as Components
Avaliação
2 provas e 1 trabalho prático
Fórmula G1
G1= ( P1 + P2 + 2T ) / 4
P1 – 25/09
P2 – 13/11
P4 – 18/11
G2 – 04/12
© 2000 Morgan Kaufman
Overheads for Computers as Components

5. Overheads for Computers as Components
Trabalho
Implementar pipeline no processador R11, utilizando a linguagem VHDL
Especificação do trabalho prevista para Setembro
Apresentação dos trabalhos
25/NOVEMBRO
27/ NOVEMBRO
© 2000 Morgan Kaufman
Overheads for Computers as Components

6. Overheads for Computers as Components
© 2000 Morgan Kaufman
Overheads for Computers as Components

7. All computing systems on Earth are
embedded systems…
Sistemas embarcados estão em toda parte: carros, avioes, telefones, aparelhos de som, áudio e vídeo, eletrodomésticos em geral, celulares, …
Por exemplo, a BMW série 7 possui 63 processadores embarcados.
O Pentium da Intel (e similares) domina o mercado de desktops pois esses computadores são utilizados em aplicações bem semelhantes.
No caso dos computadores dedicados, um sistema de controle de injeção eletrônica, por exemplo, possui requisitos bastante diferentes de um pager.
© 2000 Morgan Kaufman
Overheads for Computers as Components

8. Overheads for Computers as Components
As vendas dos microprocessadores Pentium da Intel representam apenas cerca de 2% do mercado de processadores:
© 2000 Morgan Kaufman
Overheads for Computers as Components

9. Overheads for Computers as Components
A grande diversidade de aplicações justifica a grande variedade de processadores para sistemas embarcados existentes.
© 2000 Morgan Kaufman
Overheads for Computers as Components

10. Overheads for Computers as Components
© 2000 Morgan Kaufman
Overheads for Computers as Components

11. Overheads for Computers as Components
Em resumo:
Existe muito mais demanda e inovação na área de sistemas embarcados do que na área de computadores pessoais.
Com o aumento da complexidade das aplicações, aumenta também a complexidade dos projetos de sistemas embarcados -> Novas metodologias de projeto.
© 2000 Morgan Kaufman
Overheads for Computers as Components

12. Overheads for Computers as Components
Introduction
What are embedded systems?
Challenges in embedded computing system design.
Design methodologies.
© 2000 Morgan Kaufman
Overheads for Computers as Components

13. Overheads for Computers as Components
Definition
Embedded system: any device that includes a programmable computer but is not itself a general-purpose computer.
Take advantage of application characteristics to optimize the design
© 2000 Morgan Kaufman
Overheads for Computers as Components

14. Overheads for Computers as Components
Embedding a computer
output
analog
input
CPU
analog
mem
embedded
computer
© 2000 Morgan Kaufman
Overheads for Computers as Components

15. Overheads for Computers as Components
Examples
Personal digital assistant (PDA).
Printer.
Cell phone.
Automobile: engine, brakes, dash, etc.
Television.
Household appliances.
PC keyboard (scans keys).
© 2000 Morgan Kaufman
Overheads for Computers as Components

16. Overheads for Computers as Components
Early history
Late 1940’s: MIT Whirlwind computer was designed for real-time operations.
Originally designed to control an aircraft simulator.
First microprocessor was Intel 4004 in early 1970’s.
HP-35 calculator used several chips to implement a microprocessor in 1972.
© 2000 Morgan Kaufman
Overheads for Computers as Components

17. Overheads for Computers as Components
Early history, cont’d.
Automobiles used microprocessor-based engine controllers starting in 1970’s.
Control fuel/air mixture, engine timing, etc.
Multiple modes of operation: warm-up, cruise, hill climbing, etc.
Provides lower emissions, better fuel efficiency.
© 2000 Morgan Kaufman
Overheads for Computers as Components

18. Microprocessor varieties
Microcontroller: includes I/O devices, on-board memory.
Digital signal processor (DSP): microprocessor optimized for digital signal processing.
Typical embedded word sizes: 8-bit, 16-bit, 32-bit.
© 2000 Morgan Kaufman
Overheads for Computers as Components

19. Overheads for Computers as Components
Application examples
Simple control: front panel of microwave oven, etc.
Canon EOS 3 has three microprocessors.
32-bit RISC CPU runs autofocus and eye control systems.
Analog TV: channel selection, etc.
Digital TV: programmable CPUs + hardwired logic.
© 2000 Morgan Kaufman
Overheads for Computers as Components

20. Automotive embedded systems
Today’s high-end automobile may have 100 microprocessors:
4-bit microcontroller checks seat belt;
microcontrollers run dashboard devices;
16/32-bit microprocessor controls engine.
© 2000 Morgan Kaufman
Overheads for Computers as Components

21. BMW 850i brake and stability control system
Anti-lock brake system (ABS): pumps brakes to reduce skidding.
Automatic stability control (ASC+T): controls engine to improve stability.
ABS and ASC+T communicate.
ABS was introduced first---needed to interface to existing ABS module.
© 2000 Morgan Kaufman
Overheads for Computers as Components

22. Overheads for Computers as Components
BMW 850i, cont’d.
sensor
sensor
brake
brake
hydraulic
pump
ABS
brake
brake
sensor
sensor
© 2000 Morgan Kaufman
Overheads for Computers as Components

23. Characteristics of embedded systems
Sophisticated functionality.
Real-time operation.
Low manufacturing cost.
Low power.
Designed to tight deadlines by small teams.
© 2000 Morgan Kaufman
Overheads for Computers as Components

24. Functional complexity
Often have to run sophisticated algorithms or multiple algorithms.
Cell phone, laser printer.
Often provide sophisticated user interfaces.
© 2000 Morgan Kaufman
Overheads for Computers as Components

25. Overheads for Computers as Components
Real-time operation
Must finish operations by deadlines.
Hard real time: missing deadline causes failure.
Soft real time: missing deadline results in degraded performance.
Many systems are multi-rate: must handle operations at widely varying rates.
© 2000 Morgan Kaufman
Overheads for Computers as Components

26. Non-functional requirements
Many embedded systems are mass-market items that must have low manufacturing costs.
Limited memory, microprocessor power, etc.
Power consumption is critical in battery-powered devices.
Excessive power consumption increases system cost even in wall-powered devices.
© 2000 Morgan Kaufman
Overheads for Computers as Components

27. Overheads for Computers as Components
Design teams
Often designed by a small team of designers.
Often must meet tight deadlines.
6 month market window is common.
Can’t miss back-to-school window for calculator.
© 2000 Morgan Kaufman
Overheads for Computers as Components

28. Why use microprocessors?
Alternatives: field-programmable gate arrays (FPGAs), custom logic, etc.
Microprocessors are often very efficient: can use same logic to perform many different functions.
Microprocessors simplify the design of families of products.
© 2000 Morgan Kaufman
Overheads for Computers as Components

29. The performance paradox
Microprocessors use much more logic to implement a function than does custom logic.
But microprocessors are often at least as fast:
heavily pipelined;
large design teams;
aggressive VLSI technology.
© 2000 Morgan Kaufman
Overheads for Computers as Components

30. Overheads for Computers as Components
Power
Custom logic is a clear winner for low power devices.
Modern microprocessors offer features to help control power consumption.
Software design techniques can help reduce power consumption.
© 2000 Morgan Kaufman
Overheads for Computers as Components

31. Challenges in embedded system design
How much hardware do we need?
How big is the CPU? Memory?
How do we meet our deadlines?
Faster hardware or cleverer software?
How do we minimize power?
Turn off unnecessary logic? Reduce memory accesses?
© 2000 Morgan Kaufman
Overheads for Computers as Components

32. Overheads for Computers as Components
Challenges, etc.
Does it really work?
Is the specification correct?
Does the implementation meet the spec?
How do we test for real-time characteristics?
How do we test on real data?
How do we work on the system?
Observability, controllability?
What is our development platform?
© 2000 Morgan Kaufman
Overheads for Computers as Components

33. Overheads for Computers as Components
Design methodologies
A procedure for designing a system.
Understanding your methodology helps you ensure you didn’t skip anything.
Compilers, software engineering tools, computer-aided design (CAD) tools, etc., can be used to:
help automate methodology steps;
keep track of the methodology itself.
© 2000 Morgan Kaufman
Overheads for Computers as Components

34. Overheads for Computers as Components
Design goals
Performance.
Overall speed, deadlines.
Functionality and user interface.
Manufacturing cost.
Power consumption.
Other requirements (physical size, etc.)
© 2000 Morgan Kaufman
Overheads for Computers as Components

35. Overheads for Computers as Components
Levels of abstraction
requirements
specification
architecture
component
design
system
integration
© 2000 Morgan Kaufman
Overheads for Computers as Components

36. Overheads for Computers as Components
Top-down vs. bottom-up
Top-down design:
start from most abstract description;
work to most detailed.
Bottom-up design:
work from small components to big system.
Real design uses both techniques.
© 2000 Morgan Kaufman
Overheads for Computers as Components

37. Overheads for Computers as Components
Stepwise refinement
At each level of abstraction, we must:
analyze the design to determine characteristics of the current state of the design;
refine the design to add detail.
© 2000 Morgan Kaufman
Overheads for Computers as Components

38. Overheads for Computers as Components
Requirements
Plain language description of what the user wants and expects to get.
May be developed in several ways:
talking directly to customers;
talking to marketing representatives;
providing prototypes to users for comment.
© 2000 Morgan Kaufman
Overheads for Computers as Components

39. Functional vs. non-functional requirements
output as a function of input.
Non-functional requirements:
time required to compute output;
size, weight, etc.;
power consumption;
reliability;
etc.
© 2000 Morgan Kaufman
Overheads for Computers as Components

40. Overheads for Computers as Components
GPS moving map needs
Functionality: For automotive use. Show major roads and landmarks.
User interface: At least 400 x 600 pixel screen. Three buttons max. Pop-up menu.
Performance: Map should scroll smoothly. No more than 1 sec power-up. Lock onto GPS within 15 seconds.
Cost: $500 street price = approx. $100 cost of goods sold.
© 2000 Morgan Kaufman
Overheads for Computers as Components

41. GPS moving map needs, cont’d.
Physical size/weight: Should fit in hand.
Power consumption: Should run for 8 hours on four AA batteries.
© 2000 Morgan Kaufman
Overheads for Computers as Components

42. Overheads for Computers as Components
Specification
A more precise description of the system:
should not imply a particular architecture;
provides input to the architecture design process.
May include functional and non-functional elements.
May be executable or may be in mathematical form for proofs.
© 2000 Morgan Kaufman
Overheads for Computers as Components

43. Overheads for Computers as Components
GPS specification
Should include:
What is received from GPS;
map data;
user interface;
operations required to satisfy user requests;
background operations needed to keep the system running.
© 2000 Morgan Kaufman
Overheads for Computers as Components

44. Overheads for Computers as Components
Architecture design
What major components go satisfying the specification?
Hardware components:
CPUs, peripherals, etc.
Software components:
major programs and their operations.
Must take into account functional and non-functional specifications.
© 2000 Morgan Kaufman
Overheads for Computers as Components

45. GPS moving map block diagram
display
GPS
receiver
search
engine
renderer
database
user
interface
© 2000 Morgan Kaufman
Overheads for Computers as Components

46. GPS moving map hardware architecture
display
frame
buffer
CPU
GPS
receiver
memory
panel I/O
© 2000 Morgan Kaufman
Overheads for Computers as Components

47. GPS moving map software architecture
database
search
renderer
pixels
position
user
interface
timer
© 2000 Morgan Kaufman
Overheads for Computers as Components

48. Designing hardware and software components
Must spend time architecting the system before you start coding.
Some components are ready-made, some can be modified from existing designs, others must be designed from scratch.
© 2000 Morgan Kaufman
Overheads for Computers as Components

49. Overheads for Computers as Components
System integration
Put together the components.
Many bugs appear only at this stage.
Have a plan for integrating components to uncover bugs quickly, test as much functionality as early as possible.
© 2000 Morgan Kaufman
Overheads for Computers as Components

50. Overheads for Computers as Components
Summary
Embedded computers are all around us.
Many systems have complex embedded hardware and software.
Embedded systems pose many design challenges: design time, deadlines, power, etc.
Design methodologies help us manage the design process.
© 2000 Morgan Kaufman
Overheads for Computers as Components

51. Overheads for Computers as Components
Instruction sets
Computer architecture taxonomy.
Assembly language.
© 2000 Morgan Kaufman
Overheads for Computers as Components

52. von Neumann architecture
Memory holds data, instructions.
Central processing unit (CPU) fetches instructions from memory.
Separate CPU and memory distinguishes programmable computer.
CPU registers help out: program counter (PC), instruction register (IR), general-purpose registers, etc.
© 2000 Morgan Kaufman
Overheads for Computers as Components

53. Overheads for Computers as Components
CPU + memory
memory
address
CPU PC
200
data
200
ADD r5,r1,r3
ADD r5,r1,r3 IR
© 2000 Morgan Kaufman
Overheads for Computers as Components

54. Overheads for Computers as Components
Harvard architecture
address
CPU
data memory
data PC
address
program memory
data
© 2000 Morgan Kaufman
Overheads for Computers as Components

55. Overheads for Computers as Components
von Neumann vs. Harvard
Harvard can’t use self-modifying code.
Harvard allows two simultaneous memory fetches.
Most DSPs use Harvard architecture for streaming data:
greater memory bandwidth;
more predictable bandwidth.
© 2000 Morgan Kaufman
Overheads for Computers as Components

56. Overheads for Computers as Components
RISC vs. CISC
Complex instruction set computer (CISC):
many addressing modes;
many operations.
Reduced instruction set computer (RISC):
load/store;
pipelinable instructions.
© 2000 Morgan Kaufman
Overheads for Computers as Components

57. Instruction set characteristics
Fixed vs. variable length.
Addressing modes.
Number of operands.
Types of operands.
© 2000 Morgan Kaufman
Overheads for Computers as Components

58. Overheads for Computers as Components
Programming model
Programming model: registers visible to the programmer.
Some registers are not visible (IR).
© 2000 Morgan Kaufman
Overheads for Computers as Components

59. Multiple implementations
Successful architectures have several implementations:
varying clock speeds;
different bus widths;
different cache sizes;
etc.
© 2000 Morgan Kaufman
Overheads for Computers as Components

60. Overheads for Computers as Components
Assembly language
One-to-one with instructions (more or less).
Basic features:
One instruction per line.
Labels provide names for addresses (usually in first column).
Instructions often start in later columns.
Columns run to end of line.
© 2000 Morgan Kaufman
Overheads for Computers as Components

61. ARM assembly language example
label1 ADR r4,c
LDR r0,[r4] ; a comment
ADR r4,d
LDR r1,[r4]
SUB r0,r0,r1 ; comment
© 2000 Morgan Kaufman
Overheads for Computers as Components

62. Overheads for Computers as Components
Pseudo-ops
Some assembler directives don’t correspond directly to instructions:
Define current address.
Reserve storage.
Constants.
© 2000 Morgan Kaufman
Overheads for Computers as Components

63. Overheads for Computers as Components
Endianness
Relationship between bit and byte/word ordering defines endianness:
bit 31
bit 0
bit 0
bit 31
byte 3
byte 2
byte 1
byte 0
byte 0
byte 1
byte 2
byte 3
little-endian
big-endian
© 2000 Morgan Kaufman
Overheads for Computers as Components

64. Example: C assignments (ARM Processor)
x = (a + b) - c;
Assembler:
ADR r4,a ; get address for a
LDR r0,[r4] ; get value of a
ADR r4,b ; get address for b, reusing r4
LDR r1,[r4] ; get value of b
ADD r3,r0,r1 ; compute a+b
ADR r4,c ; get address for c
LDR r2,[r4] ; get value of c
© 2000 Morgan Kaufman
Overheads for Computers as Components

65. Overheads for Computers as Components
C assignment, cont’d.
SUB r3,r3,r2 ; complete computation of x
ADR r4,x ; get address for x
STR r3,[r4] ; store value of x
© 2000 Morgan Kaufman
Overheads for Computers as Components

66. Example: C assignments (SHARC DSP)
x = (a + b) - c;
Assembler:
R0 = DM(_a) ! Load a
R1 = DM(_b); ! Load b
R3 = R0 + R1;
R2 = DM(_c); ! Load c
R3 = R3-R2;
DM(_x) = R3; ! Store result in x
© 2000 Morgan Kaufman
Overheads for Computers as Components