EE522

Advanced Embedded Systems

Sources: [Introduction to Embedded Systems, Edward A.

Lee and Sanjit A. Seshia, UC Berkeley.
Embedded Networked Systems, Kai Huang, TU Munich]
What is an Embedded System?
 Many definitions exist:

Embedded Systems = Information processing systems

embedded into a larger product.
-- Peter Marwedel, TU Dortmund

Embedded Software = Software integrated with physical

processes. The technical problem is managing time and
concurrency in computational systems.
-- Edward A. Lee, UC Berkeley
What is an Embedded System?
Embedded Systems = Information processing systems
that are:
• application domain specific (not general purpose)
• tightly coupled to their environment

 Examples of application domains:

automotive electronics, avionics, multimedia,
consumer electronics, etc.
 Environment: type and properties of
input/output information.
 Tightly coupled: the environment dictates what
the system’s response behavior must be. (“ES
cannot synchronize with environment”)
What is an Embedded System?

What they do:

 Sense environment(input signals)
 Process input information
 Respond in real-time (output signals)
Examples: Consumer Electronics
MP3 audio, digital camera, Home electronics (washing
machine, microwave cooker/oven, ...), …
Examples: Telecommunications
Wireless communication (GSM/3G base station,
switch, router, access point, …), end-user equipment,
mobile phone…
Examples: Automotive Electronics
A car is an integrated control, communication, and
information system.
 Anti-lock braking systems (ABS)
 Electronic stability control
 Efficient automatic gearboxes
 Blind-angle alert systems
 Airbags
 …
Examples: Medical Electronics
 The future of surgery is not in blood and guts, but
in bits and bytes.
Examples: Robotics
NASA Curiosity Rover Sony Robotic Dog
Examples: Gaming
Examples: Sensor networks
Sensor networks (civil engineering,
buildings, environmental
monitoring, traffic, emergency
situations)
• Smart products,
wearable/ubiquitous computing
Characteristics of Embedded Systems (1)
Must be dependable
• Reliability: R(t) = probability of a system working correctly at
time t provided that it was working at t = 0
• Maintainability: M(d) = probability of a system working
correctly d time units after error occurred
• Availability: A(t) = probability of system working at time t
• Safety: no harm to be caused by failing system
• Security: confidential and authentic communication

- Even perfectly designed systems can fail if the assumptions about

the workload and possible errors turn out to be wrong.
- Making the system dependable must not be an after-thought, it must
be considered from the very beginning.
Characteristics of Embedded Systems (2)
Must be efficient
 Energy efficient
• Many ES are mobile systems powered by batteries
• Customers expect long run-times from batteries but
• Battery technology improves at a very slow rate
 Code-size efficient (especially for systems on a chip)
• Typically there are no hard discs or huge memories to store
code
 Run-time efficient
• Meet time constraints with least amount of HW resources
and energy – only necessary HW should be present working
at as low as possible Vdd and fclk
 Weight efficient (especially for portable ES)
 Cost efficient (especially for high-volume ES)
Characteristics of Embedded Systems (3)

Many ES must meet real-time constraints

 A real-time system must react to stimuli from the controlled
object (or the operator) within the time interval dictated by the
environment.
 For real-time systems, right answers arriving too late (or even
too early) are wrong.

“A real-time constraint is called hard, if not meeting that

constraint could result in a catastrophe“ [Kopetz, 1997].

 All other time-constraints are called soft.

 A guaranteed system response has to be explained without
statistical arguments.
Characteristics of Embedded Systems (4)

 ES are connected to physical environment through sensors and

actuators.
 Hybrid Systems, i.e., composed of analog and digital parts
 Typically, ES are reactive systems

“A reactive system is one which is in continual interaction with is

environment and executes at a pace determined by that
environment“ [Bergé, 1995].

 Behavior depends on input and current state.

• automata model appropriate
Characteristics of Embedded Systems (5)

 All ES are dedicated systems

• Dedicated towards a certain application:
 Knowledge about the behavior at design time can be used
to minimize resources and to maximize robustness
• Dedicated user interface:
 No mice, no large keyboards and monitors

Not every ES has all of the above characteristics, thus

We can define the term “Embedded System” as follows:
Information processing systems having most of the
above characteristics are called embedded systems.
Comparison
Embedded Systems General Purpose Systems
• Execute few applications • Execute broad class of
that are known at applications
design-time
• Non programmable by • Programmable by the end user
the end user
• Fixed run-time • Faster is better
requirements (additional
computing power not
useful)
• Important criteria • Important criteria
–Cost
–Cost
–Power consumption
–Predictability –Average speed
–...
Another Name ？
Cyber-Physical Systems
Definition of Cyber-Physical System
 Defined by those with Money
• Smart electric grid
• Smart transportation
 Wikipedia
• A full-fledged CPS is typically designed as a network of
interacting elements with physical input and output instead of
as standalone devices
 Cyber-Physical (cy-phy) Systems (CPS) are integrations of
computation with physical processes [Edward Lee, 2006].
 Cyber-physical system (CPS) = Embedded System (ES) + physical
environment
Cyber-Physical Systems
and Embedded Systems
CPS = ES + physical environment
What is a Cyber-Physical System?

Extreme view:
Definition According to National Science
Foundation (US)
 More safe
 CPS = systems of (embedded) systems
• ES is sub-system of CSP
 The 3C concept
• Computation, communication, and control
Trends in Embedded Systems
 In the past Embedded Systems were called Embedded
(micro-)Controllers
 They appeared typically in control dominated
applications:
• Traffic lights control
• Elevators control
• Washing machines and dishwashers
• Electronic Control Unit (ECU)
 They were implemented using a single μProcessor or
dedicated HW (sequential circuit)
 All this is rapidly changing nowadays.
• How And Why?
Trend 1: Towards Multi-Processor Systems
Complexity of ES is increasing, thus
 A single uProcessor is sufficient for some consumer
products
• Application performance demands relatively low
 For other systems – such as cars and aircrafts – a
network of processors is needed
• Due to performance requirements
• Due to safety requirements (a single failed
component should not cause total system failure)
 For some systems – such as mobile devices – a
network of heterogeneous processors is needed
• Due to run-time efficiency requirements
• Due to power efficiency
Trend 2: Higher Degree of Integration
Moore’s Law: the number of transistors that can be placed
on a chip has doubled approximately every two years
 Microprocessor, microcontroller
 System-on-Chip (SoC)
• Processor + memory + I/O-units + communication
structure
 Multi-processor System on a Chip (MPSoC)
• Processor – Co-processor
• (Heterogeneous) Multi-processor
• Network on Chip
 Trend 3: Software Increasing
Implementing ES in specialized HW brings lack of
flexibility (changing standards) and very expensive masks,
thus

 Most of the functionality will be

implemented in software
• On the average, a human
“touches” about 50 to 100
micro-processors per day
• State-of-art car has 70~100
micro-processors
 Exponential increase in
software complexity
Embedded Systems Design (1)
Embedded Systems Design is NOT just a special case of
either hardware (Computer/Electrical Engineering) or
software (Software Engineering/Computer Science) design.
 An embedded system performs computation that is
subject to physical constraints, i.e., interaction with a
physical environment and execution on a physical
(implementation) platform
• Interaction constraints: deadlines, throughput, jitter
• Execution constraints: available resources, power,
failure rates
 It has functional requirements (expected services), and
it has non-functional requirements (performance, power,
cost, robustness, etc.)
Embedded Systems Design (2)
Computer Science provides (software) functionality for
Instruction Set Architectures (ISA) which are characterized
by
• Instruction set
• Organization (program counter, register file,
memory)
• Both independent of any logical implementation and
physical realization
 Computer/Electrical Engineering deals with
• Logical implementation
• Physical realization
Embedded Systems Design (3)
 Embedded Systems design discipline needs to combine
these two approaches, because non-functional behavior
(such as timing, cost, power, robustness, etc.) is a crucial
issue
• when there are real-time constraints imposed by the
environment
• when to predict non-functional behavior using
abstract models that cannot be well specified if the
relation between functional behavior and non-
functional behavior is obscure
Future of Embedded Systems
 Embedded Systems are everywhere
 Embedded Systems market is much larger than the
market of PC-like systems
• Post-PC era in which information processing is more
and more moving away from just PCs to embedded
systems
 Embedded Systems provide the basic technology for
Ubiquitous/Pervasive computing:
• Model of human-computer interaction in which
information processing has been thoroughly
integrated into everyday objects and activities
• Key goal: information available anytime, anywhere
• Building Ambient Intelligence into our environment
Embedded systems are everywhere
From Toothbrush
 Product: Sonicare Plus toothbrush
 Microprocessor: 8-bit Zilog Z8
To Smart Grid
To Outer space
1996: NASA's Mars Sojourner
Rover. Microprocessor: 8-bit Intel
80C85.

2012: NASA’s Curiosity Rover, with

uC/OS-II RT OS
Take-off Message

Everything is embedded systems

Everywhere is embedded systems
The future is Embedded Systems