Transcript voorlichting CADTES

Computer Architecture and
Embedded Systems
Paul Havinga
University of Twente
Embedded Systems
CADTES
DIES
Distributed and Embedded Systems
Computer Architecture, Design & Test for Embedded
Systems
Studieadviseurs
CADTES
Bert Molenkamp
[email protected]
DIES
Hans Scholten
[email protected]
Embedded Systems everywhere


Audio and video signal processors
Control of machines
Watches
Medical equipment
Cars (motor control, airbag, ABS, traction control)
Communication (GSM/UMTS)
.........

90% of all computers are embedded computers!





… trends ….
Device 1
Device 2
Bus
interface
Shared bus
PCI / USB
CPU
Device N
CADTES research themes

Efficient architectures
– low-power, high-performance
– Reconfigurable architectures

Design methods for embedded systems
– Transformational design
– retargetable code-generation

Ubiquitous computing
– sensor networks, self-organizing wireless networks,
dependability
– Personal networks
– Mobile computing
CADTES Research fields
Distributed
computing
Robustness
Security
Co-operation
Communication
Dependable systems
Mobile
computing
CADTES
Computer
Architecture
Reconfigurable
Energy efficient
System-on-Chip
HW/SW co-design
Autonomous
Energy efficient
Mobility
Wireless
Ad-hoc routing
Marc Weiser’s vision

Desktop computer replaced with embedded
computing in physical objects
 Small and invisible
 Enhance original functionality of physical
objects
 People would do their work assisted by
computer technology, but without having to
focus on the computers
Away from the “average device”

Powerful, personal capabilities from specialized
devices
– small, highly mobile or embedded in the environment


Intelligence + immense storage and processing in the
infrastructure
Devices
Everything connected
Laptops, Desktops
Reconfigurable computing
Technology Changes &
Architectural Implications

Zillions of Tiny Devices
– Proliferation of information
appliances, MEMS, etc.

“Of course it’s connected!”
– Cheap, ample bandwidth
– “Always on” networking





Vast (Technical) Capacity
– Scalable computing in the
infrastructure
– Rapid decline in processing,
memory, & storage cost

Adaptive Self-Configuration
Loosely Organized
“Good Enough” Reliabilty
and Availability
Any-to-Any Transducers
(dealing with heterogeneity,
over time--legacy--and
space)
Communities (sharing)
Emerging Application Paradigms








Ubiquitous Computing
Smart Spaces
Sensor Networks
Active Badges and Tags
Home Networking, e-everything
Information Appliances
Wearables
...
Deeply Networked Systems

“Everything” is networked
– Even very small things like sensors and actuators
– Explosion in the number of connected end devices

Processing moves towards the network
edges
– Protocol stack plus some ability to execute mobile
code in network end devices

Processing moves towards the network core
– Services executing inside the network
Call to Architecture

Technology exists (or will soon) to realize
grand visions of where computing can go
 What’s missing?
 Architecture

Framework that realizes the application vision
from emerging technology
– systematic application of design methods
Current projects
(and thus potential assignments !)

Reconfigurable Computing
– Chameleon, Gecko, AWGN (chameleon.ctit.utwente.nl)
– focus on efficient architectures for mobile and wireless
devices

Mobile and Ubiquitous Computing
– EYES: European project on Energy Efficient Sensor
Networks (http://eyes.eu.org)
– Consensus: collaborative sensor networks
– Seamless Services for heterogeneous wireless systems
– BigBAN: Body and personal area networks
More information

Reconfigurable computing
– G.J.M. Smit: [email protected]

Ubiquitous computing
– P.J.M. Havinga: [email protected]

http://wwwes.cs.utwente.nl