1 CS294-8: Research Seminar on Communications to the eXtreme David E. Culler, Randy H. Katz CS Division, EECS Department University of California, Berkeley.

1

CS294-8: Research Seminar on

Communications to the eXtreme

David E. Culler, Randy H. Katz

CS Division, EECS Department

University of California, Berkeley

Spring 2000

2

Agenda

• Revolutions in Computing and Communications

• Convergence, Competition, Divergence• Information Appliances• Deeply Networked Systems

3

Agenda

• Revolutions in Computing and Communications

• Convergence, Competition, Divergence• Information Appliances• Deeply Networked Systems

4

Technology as a Process

Integration: Whatwe can build into asystem

Innovation:breakthroughtechnologies

Time

Capability

For deeply networked systems, system architecture currently lags technology

5

Historic Perspective

• Technology discontinuities drive new computing paradigms, applications, system architectures

• E.g., Xerox Alto– 3Ms--1 mips, 1 megapixel, 1 mbps– Fourth M: 1 megabyte of memory– From time sharing to LAN-connected client-server with

display intensive applications

• What will drive the next discontinuity? What are the new metrics of system capability?

– This seminar: deeply networked systems– eXtreme Devices: the small, the large, the numerous

6

What’s Important: Shifts in Technology Metrics

• Display (human-computer interface)– More ubiquitous I/Os (e.g., MEMS sensors & actuators) and

modalities (speech, vision, image)– How to Quantify?

• Connectivity (computer-computer interface)– Not bandwidth but “scaled ubiquity”– Million accesses per day

• Computing (processing capacity)– Unbounded capacity & utility functionality (very high mean

time to unavailable, gracefully degraded capability acceptable

7

What is Needed?

• Automatic Self-Configuration– Personalization on a Vast Scale– Plug-and-Play

• The OS of the Planet– New management concerns: protection, information utility, not

scheduling the processor– What is the OS of the Internet? TCP plus queue scheduling in

routers

• Adapts to You– Protection, Organization, Preferences by Example

8

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)

9

Agenda

• Revolutions in Computing and Communications

• Convergence, Competition, Divergence• Information Appliances• Deeply Networked Systems

10

Evolution of the Computer

Eniac, 1947

Telephone,1876

Computer+ Modem

1957

Early WirelessPhones, 1978

First Color TVBroadcast, 1953

HBO Launched, 1972

Interactive TV, 1990

Handheld PortablePhones, 1990

First PCAltair,1974

IBMPC,

1981

AppleMac,1984

ApplePowerbook,

1990

IBMThinkpad,

1992

HPPalmtop,

1991

AppleNewton,

1993

PentiumPC, 1993

Red Herring, 10/99

11

Evolution of the Computer

PentiumPC, 1993

Atari HomePong, 1972

AppleiMac, 1998

Pentium IIPC, 1997

Palm VIIPDA, 1999

NetworkComputer,

1996

FreePC, 1999

SegaDreamcast,

1999

Internet-enabledSmart Phones,

1999

Red Herring, 10/99

Convergence, Competition, Divergence

in Computing and Communications

12

Evolution vs. Revolution: Devices in the eXtreme

Evolution

Information Appliances:Scaled down desktops,e.g., CarPC, PdaPC, etc.

Evolved Desktops

Servers:Scaled-up Desktops,

Millennium

Revolution

Information Appliances:Many computers per person,

MEMs, CCDs, LCDs, connectivity

Servers: Integrated withcomms infrastructure;Lots of computing in

small footprint

Display

Keyboard Disk

Mem

Proc

PC Evolution

Display Display

Camera

Sm

art

Senso

rs

Camera

Smart Spaces

ComputingRevolution

WAN

Server, Mem, Disk

InformationUtility

BANG!

Display

Mem

Disk

Proc

13

Telecomm/Connectivity:Access Networks, Cable, DSL, Satellites, Wireless

AT&T, UUnet

Server and Software “Platforms”:Corba/Java, NT/Symbiant/Asperios, NOW Ninja,

e”speak, AIN/ICEBERG, …Microsoft, Sun, Compaq, RealNetworks, Akaimi, ...

Terminal Equipment:PCs, Smart Phones, Game Consoles, Information

Appliances, Set-top Boxes, E-ToysDell, Ericsson, Sony

Convergence, Competition, Diversity

• Implications: – Shift from computer design to consumer design– Heterogeneous “standards,” hybrid networking– Interactive networking, access on demand, QoS

14

Agenda

• Revolutions in Computing and Communications

• Convergence, Competition, Divergence• Information Appliances• Deeply Networked Systems

15

Information Appliances

• Universal Devices vs. Specialized Devices– E.g., Swiss Army Knife vs. Butcher, Butter, Steak, Bread

knife

• Different design constraints based on intended use, enhances ease of use

– Desktop PC– Mobile PC– Desktop “Smart” Phone– Mobile Telephone– Personal Digital Assistant– Set-top Box– Digital VCR– ...

16

Industry Shifts

• Implications of PCs as commodity– Increasingly narrow profit margins

• Some Reactions:– Intel: recent strategic acquisitions focus on owning

silicon for communications, networking, signal processing, multimedia PLUS network services

– Sun: focus on infrastructure servers (clusters, RAID storage)--JAVA/JINI sells more server processing and storage

– HP: focus on non-desktop “information appliances”, e.g., HP CapShare Portable E-copier

17

Fast Projected Growth inNon-PC Terminal

Equipment

Red Herring, 10/99

1998 20020

15

45

60

30

MillionsUnitsShipped

All Non-PCInformation Appliances

Videogame ConsolesInternet TVs

Smart Phones

18

Home Networking

Red Herring, 10/99

Power LineBridge

InternetGateway

WirelessBridge

Appliance Appliance

Web PadTV

CameraPower LineCarrier (PLC)

Phone Line(HomePNA)

PhoneJack

PowerOutlet

HomeRF,Bluetooth,IEEE 802.11

IrDA

HAViHAViX10

Home APIUniversal Plug & Play (uPnP)

DSLCable Modem

Satellite

Heterogeneous devices, standardsDistributed intelligencePlug and play, self-configuration, adapt on the flyConnectivity according to device’s needs

19

Who Will Own the System Software of the 21st Century?

Sony versus Microsoft• Interactive Television

– Set-top Box OS: Aperios, WinCE, something else

– Sony/GI alliance– 7.8 million units sold in 2002

• Direct Broadcast Satellite Television

– TVs with built-in satellite receivers

– 14 million units sold in 2002

• “Smart” Phones– Sony and Microsoft involved in

numerous phone alliances– 6.8 million units sold in 2002

• Video Games– Sony Playstation (Aperios) vs.

Sega Dreamcast (WinCE)– 18.5 million units sold in

2002

• Electronic Toys– Microsoft Barney (WinCE) vs.

Sony robot pets (Aperios)– $1.86 billion in sales in 2002

20

Agenda

• Revolutions in Computing and Communications

• Convergence, Competition, Divergence• Information Appliances• Deeply Networked Systems

21

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

22

Truly eXtreme Devices:Pister’s Dust Motes

• COTS RF Mote– Atmel Microprocessor– RF Monolithics transceiver

» 916MHz, ~20m range, 4800 bps– 1 week fully active, 2 yr @1%

N

S

EW 2 Axis Magnetic Sensor

2 Axis Accelerometer

Light Intensity Sensor

Humidity Sensor

Pressure Sensor

Temperature Sensor

23

COTS Dust - Optical Motes

Laser mote• 650nm laser pointer• 2 day life full duty

CCR mote• 4 corner cubes• 40% hemisphere

24

Concept of Operations

25

Virtual Keyboard

Interfaces for people with Disabilities?

26

Representative Research Challenges in Deeply Networked Systems

• Embedded/Networked Systems– Support for deeply networked systems and mobile code

– OS services in support of sensor/actuator I/O

– Low-latency feedback across software component boundaries

– Tuning of performance and configuration at runtime

– Runtime support for networked, embedded systems

• Sensor Information Technology– Large Scale Distributed Micro Sensor Networking

– Fixed and Mobile Internetworking

– Collaborative Signal Processing

– Nano-cryptography