Post on 08-May-2015
transcript
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
Extracted from BWRC presentations
8
BWRC Retreat The Case for Programmability
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
Extracted from BWRC presentations
9
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids
• Product ScenarioCellular telephones
10
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsCalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids
• IntroductionThe cell phone scenario
20
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsSpeak ‘N SpellSpeak ‘N SpellModemsMP3 player Hearing aids
• IntroductionThe cell phone scenario
22
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsSpeak ‘N SpellModemsModemsMP3 player Hearing aids
• IntroductionThe cell phone scenario
24
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Modem Case Study
Time
Vol
ume
$200
$150
$100
$69.95
V.32
26
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Modem Case Study
Time
Vol
ume
$200
$150
$100
$69.95
$150
$100
$69.95
$200
V.32
V.32bis
27
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsSpeak ‘N SpellModemsMP3 playerMP3 player Hearing aids
• IntroductionThe cell phone scenario
29
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda
The Case for Programmability
More examples
CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aidsHearing aids
• IntroductionThe cell phone scenario
31
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Agenda• Introduction
The cell phone scenario
More examples
CalculatorsSpeak ‘N SpellModemsMP3 player Hearing aids
The Case for Programmability
33
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Cost
Power Dissipation
Size
System Considerations
Seems like a good thing to do
The Case for Programmability
34
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Cost
Power Dissipation
Size
System Considerations
Seems like a good thing to do
The Case for Programmability
36
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Cost
Power Dissipation
Size
System Considerations
Seems like a good thing to do
The Case for Programmability
38
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Cost
Power Dissipation
Size
System Considerations
Seems like a good thing to do
The Case for Programmability
40
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Cost
Power Dissipation
Size
System Considerations
Seems like a good thing to do
The Case for Programmability
44
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Custom Layout
ASIC
Programmable
Combination
How to do SOC
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
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
BWRC Retreat The Case for Programmability
Lake Tahoe, CA
Conclusion• Use programmable DSP where you can
• Use flexible HW where you must
• Don’t wait for perfection
• Move quickly