BWRC Retreat The Case for Programmability

1

BWRC Retreat The Case for Programmability

Lake Tahoe, CA

Gene A. Frantz, TI Senior Fellow

Mike McMahan, TI Fellow

Texas Instruments Inc.

The Case for Programmability

“How I Learned to Stop Worryingand love DSPs”

or

2


Lake Tahoe, CA

Different Perspectives

• UCB and Texas Instruments sometimes have different views on how to approach the solution to a system design

• And the reason isn’t simply because we are from Texas and you are from California

3


Lake Tahoe, CA

To the man with a hammer, every problem looks like a nail

“A custom data path would bethe most efficient solution tothis problem !! “

Unnamed UCB Professors

4


Lake Tahoe, CA

To the man with a hammer, every problem looks like a nail

“By gosh, this looks like a problem for a DSP !! “

Unnamed TI Engineer

5


Lake Tahoe, CA

The Real Issue• While a programmable DSP isn’t

ALWAYS the right answer, our experience is that in most cases it is.

• Since engineering analysis can lead to a different conclusion,

• The question is WHY does DSP usually win in the market ?

6


Lake Tahoe, CA

You Understand the ProblemAnalog Baseband

and RF Circuits

AD FSM

phone

bookRTOS

ARQ

Keypad,Display

Control

Coders

FFT Filters

Accelerators(bit level)

analog digitalDSP cores

uC core

(ARM)

Logic

Dedicated Logic

Communication

AlgorithmsProtocols

Extracted from BWRC presentations

7


Lake Tahoe, CA

And the Range of Solutions …

MAC

Unit

Addr

Gen

P

Prog Mem

Embedded Processor

(lpArm)

Direct MappedHardware

EmbeddedFPGA

DSP(e.g. TI 320CXX )

Fle

xib

ility

Area or Power

Reconfigurable Processors (Maia)

Factor of 100-1000

100-1000 MOPS/mW

10-100MOPS/mW

.5-5MIPS/mW


8


Lake Tahoe, CA

But the answer isn’t this simple..

Wideband CDMA FDMA Matched

Filter Trained MMSE

Blind MMSE

Multiple Antenna

Parallel Processors

5 11 23 87

Power (mW) 70 150 300 1150

Software Programmable (Optimized for DSP) Area (mm2) 115 250 530 2000

Power (mW) .4 1.6 3.1 8 Direct Mapped Area (mm2) .6 2 3 10

• Software solutions > 100 times less efficient (even ignoring overhead of parallel processing) – .5-5 MIPS/mW software DSP (best case) processor

– 100-1000 MOPS/mW dedicated


9


Lake Tahoe, CA

Agenda


More examples

CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids

• Product ScenarioCellular telephones

10


Lake Tahoe, CA

Digital Cellular Market(Phones Shipped)

1996 1997 1998 1999 2000

Units 48M 86M 162M 260M 435M

Analog Baseband

Digital Baseband

(DSP + MCU)

PowerManagement

Small Signal RF

PowerRF

Cellular Phone: An exampleCellular Phone: An example

11


Lake Tahoe, CA

The Cellular Telephone• Perhaps the highest volume consumer product

in history– TI estimates that 435M cell phones will ship in 2000

• Many standards (e.g. GSM) are relatively mature• This is the ideal market for a hardwired solution• Yet every cell phone which is shipped is based

on a programmable DSP----WHY ?

12


Lake Tahoe, CA

At Least 4 Reasons• Need to take a complete systems view

– Don’t look for local minimums

• Need flexibility– The world changes

• Need to shorten time to market– Can’t afford “perfect” solutions

• Need to maximize and maintain value – Programmability facilitates creation of a value web

13


Lake Tahoe, CA

Need a Complete System View

• Does it matter that I squeeze the last A out of a function if that function accounts for only 10% of the active power consumed in the phone– Remember, the PA accounts for about 70% of the

phone’s active power consumption– and progress in silicon technology continues to reduce

digital power consumption (Gene’s Law)

14


Lake Tahoe, CA

Change Happens !• Standards change, product requirements and

features evolve

• Cannot afford to spin new hardware whenever upgrades are required

• Examples:– Vocoder/FEC modifications– New feature requirements

15


Lake Tahoe, CA

Need to Shorten Time to Market• Phone replacement rates exceed 50% / yr• Development cycles measured in months• Each manufacturer offers dozens of phone

models (e.g. Ericsson’s website lists 31 different GSM phones)

• Virtually every manufacturer moving to one programmable platform as the basis for all phone designs

16


Lake Tahoe, CA

Need to Maximize Value• Value in a fixed solution declines

over time– The next solution to market will be better

• Value in a programmable solution can increase over time– 3rd parties can add functionality to your solution

and maintain competitive balance with competing solutions

– 3rd parties have a stake in your solution

17


Lake Tahoe, CA

DSP Core

S/W

DSP Core

S/W

ARM RISCCore

S/W

ARM RISCCore

S/W

SINGLE CHIP DIGITAL BASEBAND

AS

IC B

ackp

lan

e

User DisplayUser Display

KeyboardKeyboard

SIM CardSIM Card

RFInterface

RFInterfaceAudio

InterfaceAudio

Interface

SpeakerSpeaker MicMic

SINGLE CHIP ANALOG BASEBAND & POWER

MANAGEMENT

Op AmpsOp Amps

SwitchesSwitches

RegulatorsRegulators

ReceiverReceiver

ModulatorModulator DriverDriver

RF SECTION

PowerAmp

PowerAmp

SynthesizerSynthesizer

Touch ScreenTouch Screen

Cellular Phone Block Diagram

18


Lake Tahoe, CA

Cellular Phone Baseband SOC

MCU

Gates

Analog

ROM

DSP

RAM

2000+ phones on each 8” wafer @ .15 Leff1M Baseband Chips per Day

19


Lake Tahoe, CA

Agenda


More examples

CalculatorsCalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids

• IntroductionThe cell phone scenario

20


Lake Tahoe, CA

Calculator - the first SOC• The goal of the calculator business was a single

chip solution

• This was achieved in the Mid ‘70s

• But it still had external components– Keyboard– Display

• As the single chip was programmable it was used on a whole family of calculator products with only the program changed

21


Lake Tahoe, CA

Agenda


More examples

CalculatorsSpeak ‘N SpellSpeak ‘N SpellModemsMP3 player Hearing aids


22


Lake Tahoe, CA

Speak and Spell, 1978

• First single chip DSP– LPC-10 speech synthesizer– Fixed function

• Introduced with largest memory devices of that period (128k ROM)

• Controller was TMS1000 class uC• Same uC core as all other TI consumer

products of that period• Custom peripherals added to drive

display and keyboard

23


Lake Tahoe, CA

Agenda


More examples

CalculatorsSpeak ‘N SpellModemsModemsMP3 player Hearing aids


24


Lake Tahoe, CA

Modem: A Case Study of Programmability • Modems born as systems made up of analog components

• V.21/Bell 103 (300bps) – TI’s first custom implementation of a modem– It had a mixture of custom analog and digital on the same device

• V.22/Bell 212 (1200bps) – TI’s last attempt at a fixed function modem– After multiple passes at silicon we gave up and took it off of the market

• With the introduction of the programmable DSP, the modem market entered a new way of designing modems.– Allowed upgrades through software downloads

• From v.22bis (2400bps) on programmable solutions dominated the

modem industry

25


Lake Tahoe, CA

Modem Case Study

Time

Vol

ume

$200

$150

$100

$69.95

V.32

26


Lake Tahoe, CA

Modem Case Study

Time

Vol

ume

$200

$150

$100

$69.95

$150

$100

$69.95

$200

V.32

V.32bis

27


Lake Tahoe, CA

Modem Case Study

Time

Vol

ume

$200

$150

$100

$69.95

$200

$150

$100

$69.95

$150

$100

$69.95

$200

V.32

V.34

V.32bis

28


Lake Tahoe, CA

Agenda


More examples

CalculatorsSpeak ‘N SpellModemsMP3 playerMP3 player Hearing aids


29


Lake Tahoe, CA

MP3 player: A case study of flexibility

Sony Vaio Music Clip

• Music players need flexibility• There are many encoding

standards– MP3

– AAC

– Dolby Digital

– EPAC

– ATRAC

• There are other interesting

sounds and associated encoders

30


Lake Tahoe, CA

Agenda


More examples

CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aidsHearing aids


31


Lake Tahoe, CA

Hearing Aids: A Case Study ofToo Many Problems to Solve

The solution: Programmability at low power

• Hearing Aids have historically been custom analog solutions

• They are making a transition to digital now

• The debate: should it be custom or programmable

• The problem to be solved

– Every person has a different hearing problem

– As we mature the problem changes

– Each new room environment changes the problem

• What the user wants– To hear – Long battery life– Invisible– Easy to use

32


Lake Tahoe, CA

Agenda• Introduction

The cell phone scenario

More examples

CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids


33


Lake Tahoe, CA

Cost

Power Dissipation

Size

System Considerations

Seems like a good thing to do


34


Lake Tahoe, CA

Two Decades of IntegrationTwo Decades of Integration

50 3 5 20 256 $150.00 250 50K 3"

1980

50 0.8 40 80 2K $15.00 12.5 500K 6"

1990

50 0.1 5,000 1,000 32K $5.00 0.1 5M 12"

2000

Die size (mm)

Technology (uM)

MIPS

MHz

RAM (bytes)

Price

Power (mW/MIPS)

Transistors

Wafer size

2010

5 0.02 50K 10,000 1M $0.15 0.001 50M 12"

Typical Device capabilities

35


Lake Tahoe, CA

Cost

Power Dissipation

Size




36


Lake Tahoe, CA

Gene’s Law

DSP Power

Power Dissipation TrendsPower Dissipation Trends1,000

100

10

1

0.1

0.01

0.001

0.0001

0.00001

mW

/MIP

S

1982

1984

1986

1988

1990

1992

1994

1996

1998

2000

2002

2004

2006

2008

Year

37


Lake Tahoe, CA

Cost

Power Dissipation

Size




38


Lake Tahoe, CA

The Question of Size• Device size has become a non-issue as a result of process technology

– CPUs are close to or at 1mm in die size and shrinking

– ASIC gate density is 100K gates per mm or greater

– Memories continue to shrink

• Systems are getting more complex

BUT

• Human Factors are not shrinking– Hand helds and Desktops are still the same basic size

• Keyboards and Displays still need to be large enough to use

SO

• Most products do not need the whole system on one chip

• The system can be broken into major sub-systems, e.g.– Analog

– Digital

39


Lake Tahoe, CA

Cost

Power Dissipation

Size




40


Lake Tahoe, CA

H/W

TTM

S/W

H/W

Val

ue

Time

• At introduction, value has three components» Hardware» Software» Time to market

• At maturity, product value has only one component

» Hardware

The Value of Time

41


Lake Tahoe, CA

Val

ue

Complexity

Value and Complexity are correlated to some point of complexity

Beyond this point the value is reduced with added complexity

The Value of Complexity

42


Lake Tahoe, CA

RawPerformance

Power Dissipation

Cost

Three Vectors of Value

• Each vector of value creates new market opportunities

• SOC effects all three vectors

• Each end equipment requires a unique combination of the three

43


Lake Tahoe, CA

Cost

Power Dissipation

Size




44


Lake Tahoe, CA

Custom Layout

ASIC

Programmable

Combination

How to do SOC


Lake Tahoe, CA

A Different Look at Programmability

Co

st

Co

st

100% S/W(Programmable)

100% H/W(Fixed Function)

Tech trend

Combination

• Cost can be defined as:– Financial – Power Dissipation– NRE– Time to market

– Mfg cost

– Weight

– Opportunity cost– Size

A combination of software and hardware always gives the lowest cost system design.

46


Lake Tahoe, CA

DSP

CP#1 CP#2 CP#3 CP# n

HW/SW Combination Still Can Be Flexible

• Use DSP for anything which can be accomplished in SW

• Add a dash of programmable (or reconfigurable) HW “coprocessors” where necessary

47


Lake Tahoe, CA

Conclusion• Use programmable DSP where you can

• Use flexible HW where you must

• Don’t wait for perfection

• Move quickly