Upload
frank-whitehead
View
212
Download
0
Embed Size (px)
Citation preview
soc 8.1
Chapter 8What’s Next: Challenges Ahead
Computer System DesignSystem-on-Chipby M. Flynn & W. Luk
Pub. Wiley 2011 (copyright 2011)
soc 8.2
Future (1): Autonomous SOC
• SOC Consists of multiple heterogeneous processors, controllers and memory
• but it’s still only a part of a larger system: with power source, disk, network interface, transducers, I/O, actuators (speakers and displays), etc
• how much of this can we put on a single die? Perhaps all but the actuators
soc 8.3
ASOC: what it is
• a standalone (in so far as possible) SOC with the sensors, actuators, controllers communications and storage
• capable of realizing complete communications, sense, analysis, recognition and motor actions
• must be more than simple sense and communicate; analysis to create information
soc 8.4
Autonomous (untethered) chips
a simplified classification:• simple identification of the die itself (as in
RFID) with RF response• identification of a sensor detected “event”
with RF response (as in Smart Dust [Coo] and many Smart Cards)
• detection of an “event” and processing (classification, recognition, analyzing) the event (ASOC) with RF response of the result
Ref: B.W. Cook et al, “SOC Issues for RF Smart Dust,” Proc IEEEJune 2006
soc 8.5
Untethered systems: RFID vs ASOC
System Passive id Active id RF sensor ASOC Example
RFID, Smart Card (simple)
Smart card, Active RFID
Smart Dust; RFID + sensor
Power source
None Short term battery Battery Integrated Battery
Maximum Memory
ROM ID (1KB)
R/W ID + parameters (2KB)
R/W extensive (100 MB)
RF range (meters)
Passive; order of 1 meter (M)
Active 1-10 M 10 - 20 M 10+M
Compute None FSM or controller FSM More than one CPU
soc 8.6
ASOC basics
• small size– basic die type: O(1/4 -1 cm2 x ½ mm)– note, long term: could be printed on an ultra thin
base• power and energy, self contained• persistent storage• communications with environment (network)• one or more types of sense and reaction
soc 8.7
Area, Time (Performance) and Power design tradeoffs
Dynamic poweronly
soc 8.8
Area
• cost of processed silicon: $1-10/cm2
• most designs target– 1 cm2 or a little less in area; the sweet spot– gives 90%+ yield
• larger dies have– lower yields– fewer dies / wafer– costs can be 10x for a doubling of die size
• small dies aren’t much cheaper– limited by testing and packaging
soc 8.9
Silicon device density scaling
0
20
40
60
80
100
120
90 65 45 32
Feature size
Fla
sh m
emo
ry d
ensi
ty
-100
100
300
500
700
900
1100
1300
1500
tran
sist
or
den
sity
Mega Bytes/ cm2
M transistors/ cm2
Net: there’s either a 1 billion transistors or 100 Mega Bytes of Flash on a 1cm2 die
soc 8.10
Power and batteries
• eliminating the external battery is the key technology for ASOC– no pins, distribution problems
• must print or deposit battery on reverse side of die
• can scavenge power– source may be unreliable– adds on die complexity
soc 8.11
Battery technology
Type Energy (J ) Recharge Y/N Thickness (micron)
Printed [1] 2 / cm2 N 20 Thin film [2] 10 /cm2 Y 100 Button 200 Y 500
(stand alone)
[2] The POWER FAB (Thin Film Lithium Ion Cell) battery system,. http://www.cymbet.com
[1] PowerID, Power Paper Corp. www.powerpaper.com
soc 8.12
Scavenging Energy
Source Charge rate
Comment
Solar 65 (milliwatts)/ cm2 Ambient light 2 (milliwatts)/ cm2 Strain and acoustic A force (sound) changes
alignment of crystal structure, creating voltage; 2 (milliwatts)/ cm2
Piezoelectric effect About 2-4% efficient See [SOD]
RF
An electric field of 10V/m yields 16W/cm2 of antenna
See [YEA]
Temperature difference (Peltier effect)
40 (microwatts/50C difference)
Needs temperature differential.
[YEA] E.M. Yeatman, “Advances in power sources for wireless sensor nodes,” Proceedings of 1st International Workshop on Body Sensor Networks, London, 2004[SOD] Sodano et al, ” Electric power harvesting using piezoelectric materials,” 10th SPIE Conference on Smart Structures and Materials, 2003
soc 8.13
Energy capacity at 1 w usage
Net: an on die battery will have only 10 Joules unless energy is scavenged.At a 10% duty cycle this gives better than a 3 year lifetime.
soc 8.14
Power and performance
• with a power budget of 1 w how to provide meaningful performance?
• if today’s processor offers 5 GHz at 100w – by the cubic rule 1 w (dynamic power)
should offer 10.5 MHz: (10-8)1/3 = 2.1 x 10-3
• but with lots of transistors we need to use them to recover performance
soc 8.15
Power and performance
• with a power budget of 1 w how to provide meaningful performance?
• static power is also a big issue– must be of the O (0.1) w
• methods to reduce static power consumption– sub threshold circuits– power islands– sleep transistors– SOIAS: Silicon on Insulator Active Substrate
soc 8.16
Performance with low clock rate
• No clock: asynchronous logic– no unnecessary state transitions
• Minimum or no cache system– backed by compatible Flash
• VLIW and specialized multi processors– to recover performance
soc 8.17
The ASOC die
soc 8.18
Networking: it’s the ensemble that produces the
action• no individual die is expected to produce a
recognition or a definitive action• recognitions are passed to neighbors; can
be sent to higher level for action or through swarm computing arrived at via the network
• current software models are inadequate in this regard
• for hardware, communication is the key
soc 8.19
Untethered inter die communications
• Light or RF• modulated light can be low power
– relatively easy to focus/ defocus– free space signals are non interfering – but, must have line of sight
• RF, components well understood– RFID technology– can require power; especially at high frequency– antenna focuses power based on carrier
frequency
soc 8.20
On die lasers for communications
0.01
0.1
1
10
1 10 100 1000
pluse width (ns)
po
wer
micro watts
It’s possible to achieve 100 Mbps with 1watt without noiseBut: ambient light is noise; need 10x signal over noise; also distance requiresoptics to collimate the beam for low divergence
soc 8.21
RF, smart dust:1011 bits/Joule/ Meter.
Ref: [Coo] B. W. Cook et al, “SOC Issues for RF Smart Dust,” Proc IEEEJune 2006
65x30x25 mmPrototype; Target 2 mm3
soc 8.22
Today’s ASOC; implantable RF
5 mw (peak), 2 meters, 1 Mbps
Ref: Zarlink’s medical implantable RF
soc 8.23
Audio sensors
• time or frequency domain• ear uses frequency domain• need sensitive chip mounted crystal
transducers– to provide signal (voltage) to sensor
soc 8.24
Audio sensors: Cochlear implant
Ref: Wikipedia
Speech processor,Transmitte
r
Receiver, electrodes
RF
soc 8.25
Audio sensors; cochlear chip; series of frequency bandpass
filters
Ref: B. Wen et al “Active Bidirectional Coupling in a Cochlear Chip” Advances in Neural Information Processing Systems 17, Sholkopf Ed., MIT Press, 2006
soc 8.26
Vision and recognition: edges
Ref: T. Komuro, “SIMD Processor for Vision“ IEEE JSSC, VOL. 39, NO. 1, JAN 2004
64x64 pixel array (PEs) with reconfiguration; PE chainingand fast summation for edge detection
soc 8.27
Vision and recognition: templates
Ref:Etienne-Cummings, “A Vision Chip for Color Segmentation and Pattern Matching,” EURASIP Journal on Applied Signal Processing 2003:7, 703–712
Object recognition with color (RGB to HIS)128 x 64 pixel element arrayUses SAD array scan to match against 32 Templates (432 b each)Achieves 30 frames per second with 1 mw
soc 8.28
Movement: 2D
• ASOC die is 10x10x0.6mm and weights about 200 mg
• with 1 Joule of energy (107 ergs); lifting 200mg 1 cm requires 20 ergs or 2 w-sec
• so as long as speed is slow (order of cm / sec) or duty cycle is low, simple motion using nano motors shouldn’t be a problem
soc 8.29
Movement: Flight Toward 30-gram Autonomous Indoor Aircraft:
Vision-based Obstacle Avoidance and Altitude Control
J. Zufferey and D. Floreano,” Toward 30-gram Autonomous Indoor Aircraft: Vision-based… Control,” Laboratory of Intelligent Systems, EPFL
http://www.youtube.com/watch?v=Lv6amv0yDIg
soc 8.30
Movement: flight
J. Zufferey and D. Floreano,” Toward 30-gram Autonomous Indoor Aircraft:Vision-based … Control,” Laboratory of Intelligent Systems, EPFL
soc 8.31
Movement: the fruit fly
Drosophila melanogaster
soc 8.32
Fruit fly
• length 2.5 mm; volume 2 mm3
• 0.65 milligram; 1 month lifetime • vision: 800 units each w 8
photoreceptors for colors thru the UV (200k neurons); 10x better than human in temporal vision
• also olfaction, audition, learning/memory • flight: wings beat 210x /sec; move 10
cm/sec; rotate 900 in 50 ms
soc 8.33
Summary: ASOC
• the goal is to create a catalog of techniques, sensors, controllers, transceivers and processors together with an interconnection and design methodology for application ASOC
• ASOC can be one or many die; external units as required by system
• we’re a long way in Cost-Time-Power from a fruit fly; but we’re making progress!
soc 8.34
Future (2): self-optimise/self-verify
• 2005 International Technology Roadmap for Semiconductors: overall design challenges– cost-driven design optimisation– verification and test– re-use
• approach to address all 3 challenges?– key elements– challenges– summary
soc 8.35
Approach: key elements
• optimise and verify: hardware + software– meet requirements efficiently and
demonstrably
• self-optimising and self-verifying design (SOSV)– preserve property in design composition
• self?– aware of context– capable of planning– effective external control
• 2 stages– pre-deployment: building design, compile time– post-deployment: operational, run time
soc 8.36
----------------------------------------------------------------------------------- Pre-deployment Post-deployment-----------------------------------------------------------------------------------
focus designer productivity design efficiency
aim optimize/verify initial optimize according to post-deployment design situation
context design tool environment, operation environment, often static often dynamic
acquire context from parameters affecting from data input tool performance e.g. sensors
planning plan post-deployment plan to meet post- optimise/verify deployment
goals
external control frequent infrequent-----------------------------------------------------------------------------------
Pre- and post-deployment
soc 8.37
Re-use
• high-level generic design – requirements + context: multiple designs – optimise: options + parameters + abstraction
levels
• facilitate design composition– preserve self-optimising and self-verifying– modularity of building blocks + interfaces
• platform-based evolution– re-use un-verified design: risky– automate re-verification after changes– platform for re-use: from automatic to self
soc 8.38
Pre-deployment: overview
• available computing resources – components + pre-context: locate and tune
tools– current context: optimise resource + error
recovery
• designer– adapt components: requirements + post-
context– choose control: automation of search strategies– decide: re-use or re-invent
• challenges– productive interaction: designer + tools– avoid combinatorial explosion– maximise re-use: incremental design
soc 8.39
Pre-deployment: example of choices
• circuit technology: eg ASIC or FPGA• input/output: options• memory: hierarchy + options• interconnect: e.g. bus, switch, network-on-
chip• granularity: configurable unit, custom
instruction• synchronisation: e.g. clock domains, self-
timed• parallelism: processors, hardware/software• data representation optimisation• post-deployment optimisation/verification
soc 8.40
Example: number of processors
From: Fidjeland & Luk 05
soc 8.41
Post-deployment: situation-specific
• optimization and verification opportunities– design upgrade– run-time conditions, e.g. noise, process
variation– program phase optimisation
• optimisation and verification process– light-weight: on-site, e.g. proof-carrying
code– heavy-weight: remotely, verified by
signature• run-time system
– deals with exceptions– error diagnosis facilities
soc 8.42
Example: program phase optimisation
From: Styles and Luk 05
• program phase: working set remains constant• reconfigure to speed up frequent branches
soc 8.43
Autonomous systems
• control strategy– make decisions to optimise itself– model of world: planning and action – understand trade-offs: e.g. reconfigure or
not
• event-driven just-in-time reconfiguration– component meta-data description– assemble + tune partially-optimised
components– hide reconfiguration latency
• other possibilities– machine learning– self-organising feature map
soc 8.44
Example: dynamic power optimisation
power surge while self-optimising/verifying
soc 8.45
Challenges: theory + practice for:
• productive automate: evolutionary vs disruptive
• SOSV design: specify + analyse requirements
• composable description: design + context
• multi-level capture: domain-specific constraints
• open standard: design, optim/verify programs
soc 8.46
Summary
• self * (optimising+verifying) = trusted re-use– unify: autonomic, self-test, dynamic optim., RTR– better design + more productive
• self-optimising self-verifying design platform – FPGA-based systems: large + small– autonomous system-on-chip + network of ASOCs– applications: ubiquitous, dependable, secure,
robust
• new generation of designers– building blocks + tools: made smarter– specify, analyse, adapt: requirements + search