D ISTRIBUTED S YSTEMS - The Next Grand Challenge in Embedded System - - PowerPoint PPT Presentation
D ISTRIBUTED S YSTEMS - The Next Grand Challenge in Embedded System Design Jan M. Rabaey Donald O. Pederson Distinguished Prof. Director FCRP MultiScale Systems Center (MuSyC) Scientific Co-Director Berkeley Wireless Research Center University
Donald O. Pederson Distinguished Prof. Director FCRP MultiScale Systems Center (MuSyC) Scientific Co-Director Berkeley Wireless Research Center University of California at Berkeley
INTEL, FEBRUARY 23 2011
Infrastructural core
TRILLIONS OF CONNECTED DEVICES
[J. Rabaey, ASPDAC’08]
1970 Mainframes 1980 PCs 1990 Internet 2000 Wireless & Personal Devices 2010- Cloud Computing Immersive User Experiences Ubiquitous Sensing
[MuSyC 2009]
The functionality is in the swarm! Resources can be dynamically provided based on availability
[H. Gill, NSF 2008]
Modeling/ Abstractions
System Metrics (ENERGY)
Run-time Management / Diagnostics
Verification Security/Tru st Robustness/ Reliability
Failure to Address in Fundamental and Cohesive Way will Slow Down or Prohibit Adoption
Energy among most compelling concern of distributed IT platform and its applications.
Mobiles Smart grid Avionics Human-centric systems
OUR VISION: Distributed Sense and Control Systems to Dynamically Enforce Energy-Proportionality
While some opportunities are left, concepts now commonly exploited The end of voltage and energy scaling !?
Unless novel devices are adapted soon …
0.001 0.01 0.1 1 Total Switching Leakage
0.2 0.4 0.6 0.8 1 1.2 VDD (V) 0.001 0.01 0.1 1 Energy (norm.)
0.3V
12x
In Need of Novel Architectural Ideas
Energy-efficiency of most systems decreases under reduced loads Energy-Proportional Computing
Throughput Actual Ideal
Power
Courtesy:
Throughput Power Actual Ideal DOING NOTHING (or LITTLE) WELL
Energy efficiency of most systems degrades under reduced load conditions How we design systems How nature designs systems
[* Term coined by L. Barroso, Google]
Throughput Power Actua l Ideal DOING NOTHING (or LITTLE) WELL
Energy-Proportional over Large Throughput Range.
Not the case in today’s systems (computing, storage, communication)
“Providing computation/computation at the optimal energy”
“Matching computation to desired utility”
A continuously changing alignment (environment, density, activity) The Swarm/Cloud Operating System -
Dynamically trading off resources
The Swarm/Cloud Services and Applications “What matters in the end is the utility delivered to the user”
Communication (Spectrum) Computation
Sensing Actuation Storage Energy
17
Features
Multi-university teams Focus on topics where evolutionary R&D is insufficient Emphasis on discovery; long-range time horizon Large-scale effort (~ $7M per center annually) Equal cost sharing between industry & government Access to relevantly trained graduate students
“The (SRC) focus center program is designed to create a nationwide, multi-university network of research centers that will keep the United States and U.S. semiconductor firms at the front of the global microelectronics revolution.”
Craig R. Barrett Retired Chairman of the Board, Intel Former Chair, Semiconductor Technology Council Recent Chair, FCRP Governing Council
Grand Goal: Grand Challenge: Create comprehensive and systematic solution the distributed multi-scale system design challenge. “Energy-smart” distributed systems, that
demand
all scales of design hierarchy. Common Core: 20 Faculty Distributed over 10 US Universities SCS Theme Distributed sense and control systems. Target: Airborne Platforms (Avionics) LSS Theme Large-scale “energy-intensive” systems Target: Data centers SSS Theme Small-scale “energy-frugal” systems Target: Human-centered networks for augmented sensing (e.g. BMI) Exploring the multi-scale space:
SCS LSS SSS
Including experts in petascale computing, networking, control, signal processing, information theory, avionics and neuro-engineering
Address challenges in complex distributed control systems by employing structured and formal design methodologies that seamlessly and coherently combine various dimensions of multi-scale design space, and that provide appropriate abstractions to manage inherent complexity. Case study: Avionics
Complexity
Today
Power sources/sinks Electric distribution Control system
Tomorrow
Large Airborne Platforms
In Line with DARPA META Program Reduction of development time of complex, distributed control systems by 2X through increased use of formal methods for specification, design and verification. Reduction of the number of faults that require the system to be taken out of service for inspection or repair by 2X, through the increase used of onboard models and dynamic reconfiguration to provide enhanced fault tolerance.
Platform-based design enables architecture exploration (tradeoff weight, stability, …)
Power System Architecture Control System Architecture Hardware, Software, Communications
Redesign
Incremental conservative design
Dynamics problems identified in verification Communications latency impacts stability Dynamics, control, communication latency addressed in all layers
Current State of the Art
Robust design for distributed control system Ptolemy, Metro tools enable robust design
systems
Our Approach (STRONG impact on META I and II BAA) Collaboration with UTC (HS), IBM and Raytheon Contributors: E. Lee, R. Murray and ASV Realistic Test Benches under development
Realize distributed closed-loop power-management strategies that result in “energy- intensive” large-scale systems to be orders of magnitude more energy-efficient, while ensuring that mission-critical goals are met. To be accomplished by employing holistic multi-scale solution including all components of the system at multiple hierarchy levels. Target: Data centers
“Doing nothing well”
SOLUTION: Distributed and hierarchical management that ensures that energy is only consumed if, when and where needed.
Enable “energy-proportional” computing, and to “do nothing well” in Datacenters and Cloud Computing METRIC: Datacenter Energy Efficiency
Barroso & Hölzle, 2009
B Workload Model/ Predictor Energy Aware Workload Scheduler Cluster Manager Building/Facility Manager Tasks SLAs Energy Supply Information Energy Consumption Application Resource Footprint
Contributors: Katz, Snavely, Rosing, NSF GreenLight
Cooling-aware management
Explore absolute bounds of energy-efficiency and miniaturization in “energy-frugal” human-centric distributed IT systems, through distributed management strategy that dynamically and adaptively selects correct operational point corresponding to varying application needs in terms of accuracy or resolution. Target: Augmented sensing in humans (BMI)
KEY METRIC: UTILITY/ENERGY Utility Maximization
user/application relevant utility
platforms to maximize utility
Explore, analyze, and implement advanced closed-loop learning systems in brain-machine interfaces
In collaboration with UCB Neuroscience and UCSF Neurosurgery
Scalable Signal acquisition
Utility-Optimizing Scalable Systems Management
Hugely Scalable Processor Attentional Algorithms Scalable Radio Frequency Tx and Rx RF Energy Harvesting Efficient Integrated Microscopic Antenna Voltage Scalable Power Source
3D Integrated Packaging
3 3
Contributors: Rabaey, Blaauw, Franzon
3D Inductors promising higher L, Q
Energy-neutral wireless link delivers energy- proportionality over broad performance range from scavenged power
3
1 mm
65 nm CMOS, in fab
[Franzon] [Rabaey] Low-Jitter Timers for Power Control [Blaauw]
1.4 μJ/hour
IBM 130 nm CMOS
In a connected world, functionality arises
from connections of devices.
Largest efficiency gain obtained by
balancing available resources: computation, communication and energy.
The dynamic nature of the environment,
the needs and the resources dictate adaptive solutions.
No one wins by being selfish.
Cooperation and collaboration are a must.