Computing for the Masses 为人民计算 Zhiwei Xu 徐志伟 Information Science Advisory Committee,...
-
Upload
shanna-reeves -
Category
Documents
-
view
214 -
download
0
Transcript of Computing for the Masses 为人民计算 Zhiwei Xu 徐志伟 Information Science Advisory Committee,...
Computing for the Masses为人民计算
Zhiwei Xu 徐志伟Information Science Advisory Committee, NSFC
Institute of Computing Technology (ICT)Chinese Academy of Sciences
INSTITUTE OF COMPUTING
TECHNOLOGY
Contents
• Background• Goals• Problems and Approaches
Demand: China Computer Market Grows
GDP US$Trillio
n
ComputerMarket
US$Billion
InternetUsers
(Million)
ClientDevices(Million)
1995 0.69 7.4
2000 1.08 25.9 22.5 8.9
2005 2.30 59.0 111(+80) 49.5
2010 3.00 115.6 233 106
2015 4.75 217.3 411 191
2020 7.07 403.9 662 308
Sources: China NBS, CCID, CNNIC, Goldman Sachs
2007 3.38 93.1 210 78
Still has big growth space
Internet Penetration (2007)
China 16%
USA 70%
World 19%
China in 10 years = USA today?
Supply: China computer industry is weak(Forbes 2000 for year 2007 US$ billion)
Rank Company Country Sales Profi ts Assets Market ValueProfi t/SalesP/EAppl i cati on Servi ces
709 Ebay USA 7. 67 0. 35 15. 37 35 4. 56% 100740 Amazon USA 14. 84 0. 48 6. 49 26. 87 3. 23% 561565 Expedi a USA 2. 67 0. 3 8. 3 6. 55 11. 24% 221863 Al ibaba China 0.17 0.03 0.23 12.25 17.65% 408
Software & Servi ces37 I BM USA 98. 79 10. 42 120. 43 157. 62 10. 55% 1563 Mi crosof t USA 57. 9 16. 96 67. 34 253. 15 29. 29% 15213 Googl e USA 16. 59 4. 2 25. 34 147. 66 25. 32% 35319 SAP Germany 14. 96 2. 81 14. 93 57. 77 18. 78% 211040 I nfosys I ndi a 3. 21 0. 89 3. 08 22. 09 27. 73% 251905 Tencent China 0.36 0.14 0.58 11.37 38.89% 81
Hardware53 HP USA 107. 67 7. 85 88. 57 122. 04 7. 29% 16178 Appl e USA 26. 5 4. 07 30. 04 109. 88 15. 36% 27192 Del l USA 61. 13 2. 95 27. 56 44. 6 4. 83% 151053 RI M Canada 2. 95 0. 61 3. 08 58. 73 20. 68% 961338 Lenovo China 14.53 0.16 5.35 6.47 1.10% 40
Challenges to Academia
• C4M supply is seriously lacking
• Lag behind demandLag behind industry
• Lag behind international peersToo much short-term “mission”
Computing for the Masses (C4M)
• Research and applications of computer science for mass adoption– Directly benefit the masses
• Billions of people
≠ scientific computing or business computing
– Including• Parallelism for the masses• Net computing for the masses• Social computing for the masses
Contents
• Background• Goals
– Mass Adoption billions of people• No dumbing down: Value = Ω(Adoption)
– Sustainability: Value↑, resource→ • Problems and Approaches
Sustainability
1960 1970 1980 1990 2000 2010 2020 2030 2040Time
Value &Resource Total IT Value
Resource consumptionEnvironment impact
Servers electricity bill: $1.9 billion (IDC, 2007 China )
Physics
Circuits
Systems
Energy/operation(2000-2007)
μJ
pJ
C4M is not dumbing down
Personalized
Expertise
Ubiquity
Commodity
Basic
0.1 0.2 0.3 0.4 0.5 0.6 0.8 1.0 1.2Adoption(Computer Users in China, Billion)
Value
2010
2020 2030 2040
Value-Augmenting Adoption
Personalized
Expertise
Ubiquity
Commodity
Basic
0.1 0.2 0.3 0.4 0.5 0.6 0.8 1.0 1.2Adoption(Computer Users in China, Billion)
Value
2010
2020
2030
2040
PC: example of C4M• Reached more users• More value than mainframe/mini• More innovations with big ideas
– Frame buffer– GUI– OO programming– Ethernet
What’s different now?
• The Net = Three Worlds• Man-Machine Symbiosis Man-Machine Society
Computing for the Masses
Business Infrastructure
IT Infrastructure
Business Value
IT Components
Business App & Svc
Servers, NetworksStorages, Data
Sensor Networks, CPS
Utility Devices
Computer users in China: 210 million (2007); 800 million (2020)
Godson CPULenovo PC/LaptopDawning Servers
BlueWhale StorageVega Grid
Contents
• Background• Goals• Problems and Approaches
– A Science of Three Worlds– Architectural Characteristics– Personal Net
A Science of Net Computing
• Computation as a unifying theme in a new science of three worlds
• Enrich our beautiful algorithmic computing theory• Karp
– Computational lens
• Hurwicz– Mechanism design
• Science 2020
Google-Like Computing
Linux Servers and Other Resources Distributed in Wide Area
Google system softwareGoogle filesystem, resource mngt, fault tolerance, etc.
Google utilities: MapReduce & BigTable
Google application software and data Sorting, machine learning, graph computing, etc.
Google Value (Visible)Search, AdWord, Map, Earth, News, Froogle, etc.
Hosting Environment: LAMP
DatacentersServersData, MetadataCode
2006 Data ($ billion)
Revenue:10.6
Profit: 3
Cost: 7
R&D: 1.2
Resource: 2.4
O=F(I) Value = F(Resource)
Enrich Algorithmic Computing • Traditional algorithmic computing
– Turing machine decision problem– Input, output, a procedure of mechanic steps– Time complexity, space complexity
• What are “algorithms” in the tri-world?– What is the “decision problem”?
• What is Web computable?• What is Wiki computable?
– How to quantify “value” and “resource”?– What is a “step”? What is termination?– What are the complexity metrics?
System Characteristics
• C4M Workload Analytics– Time, space, information– Interaction, energy, effort
• Basic “Laws” revisited– Moore’s law– Network effect (Metcalf, Brown)– Viral market– Internet principles (E2E, REST)
• New Phenomena and Abstractions
Architecture Characterization
• Patterson & HennesseyPerformance = Program/Time
= 1/(#Instructions x CPI x CycleTime)• Need reexamination
– Program=C4M workloads– Time=?– Instruction=?
• Other important metricsTask/Energy = ?Task/Effort = ?
Architecture Characterization
Execution Single Multiple
Control
Decentralized
Centralized
Admin, Knowledge, Naming, Coding, Contribution
Salesforce.com
many web sites
GoogleAmazonTeragrid
WWWCloudsPNC environment
Virtual hosts
Virtual Machines
Number of Execution Sites (Datacenters, Machines)
Distributed Systems
DecentralizedSystems
Personal Net (PN)
• A PN for each member of the masses• A general-purpose, personal, net computing
platform – a dynamic, virtualized set of assets from the Net
(cyberinfrastructure, community, physical world)– appearing to be dedicated to a personal owner’s
use and control• People share the Net personally
The Net Now• Offering
– Traditional network services: email, ftp, BBS, messaging– Consumer web: Amazon, eBay– Business web: salesforce.com– Community Web: Wiki, MySpace, Facebook– Grid services: Nanohub– Platform: Teragrid, Amazon S3 and EC2 (clouds)
• Characteristics– Institutional, not personal– Special-purpose solutions, not a general-purpose platform
• The Net now is like the Mainframe in 1960’s
Personal Net Computing
ASP
PG Platform Provider
A, DO, PC, N, S
A, DO, PC, N, S
……
PG Platform Provider
A, DO, PC, N, S
A, DO, PC, N, S
……
DSP CSP SSP NSP ASP……
PersonalGrids
PlatformProviders
ResourceProviders
AccessingDevices
Individuals
The Net
Assets A: applications D: data O: operating sys. P: policies C: computing N: networking S: storage
SP: service provider for resources
Resources are “raw” assets (capabilities)
DISC Grids Clouds
PocketWeb
Pocket Web: battery life > 2 weeks; assets on demand; the Net in you hand
Dual-objective optimizationFairness
Success Rate
Characterizing Emergence
1
2
Qn
nR
RR
2
1
Emergencesdo appear
• Workloads (over 1 million jobs simulated)– Synthetic workloads– Real workloads: www.cs.huji.ac.il/labs/parallel/workload/
• Value For consumers: for providers:
high job success rate fair revenue and utilization
Xiao et al, “Incentive-based Scheduling for Market-like Computational Grids”, IEEE Transactions on Parallel and Distributed Systems, 2008
Clash of the Computer and the Network Approaches
• Fetching 10-byte data from a blog server: 162 ms, 52 context switchesat server side
• How much is needed to host 100 million PG’s?– Response time < 0.25 s
• Sustained = 5% Peak?
1 Network Access
2 Inter Network
3 Transport
4 Application
?
GSMLBPEL
WSRFWSDLSOAP
HTML XMLHTTP
TCP/IP Stack Web/Web Service Stacks
HW systemVMM
OS
DatabaseApp
HW (core)Thread VMM
AppThread
Summary
• CS research lags behind demand• C4M is potentially a transformative
opportunity for CS research • C4M means sustainability and value-
augmenting mass adoption• C4M research agenda
– Establish a science of three worlds– Characterize net computing architectures– Create personal net
Thank you!