Telepresence: An Umbrella Research Topic Jim Gray Microsoft Research Gray@Microsoft.com http://research.Microsoft.com/~Gray/ 1 Federal Research Support Nerve Center of Science If it’s not broke, don’t fix it. But…. US Science is the engine of progress BUT….. Best and brightest are spending increasing time fund raising Seems excessive to me. Venture capital community is THE LONG richer and BOOM more generous than Federal Support 2 Cyberspace is a New World. We have discovered a “new continent”. It is changing how we learn, work, and play. – 1 T$/y industry – 1 T$ new wealth since 1993 – 30% of US economic growth since 1993 There is a gold rush to stake out territory. THE LONG But we also need explorers: BOOM Lewis & Clark expeditions Universities to teach the next generation(s) Governments, industry, and philanthropists should fund long-term research. 3 Research Investments Pay Off CSTB –NRC Evolving the High-Performance Computing and Communications Imitative to Support the nations Information Infrastructure, NA Press, Washington DC, 1995. 1960 1970 Time-sharing 1980 1990 Government funded CTSS, Multics, SSD Unix Industrial Billion Dollar/year Industry SDS 940, 360/67 VMS Graphics Sketchpad, Utah GM/IBM, LucasFilm E&S, SGI, PIXAR,.. Networking Arpanet, Internet Ethernet, Pup, Datakit DECnet, LANs, TCP/IP Workstations Windows Lisp machine, Stanford Xerox Alto Apollo, Sun Englebart, Rochester Alto, Smalltalk 4 Star, Mac, Microsoft Research Investments Pay Off 1970 1980 Relational Data Bases 1990 2000 Berkeley, Wisc,… IBM Oracle, IBM,… Parallel DBs Tokyo,Wisconsin, UCLA ICL, IBM ICL, Teradata, Tandem Data Mining (complex queries) Wisc, Stanford, … IBM, Arbor,… IRI, Arbor, Plato, … 5 Why Can’t Industry Fund IT Research? It does: IBM (5.8%), Intel (13%), Lucent (12%), Microsoft (14.%) , Sun (12%) , ... – R&D is ~5%-15% (50 B$ of 500 B$) AD is 10% of that (5 B$) – Long-Range Research is 10% of that 500 M$ 2,500 researchers and university support – Compaq: 4.8% R&D (1.3 B$ of 27.3 B$).AOL: 3.7% D, ?R (96 M$ of 2.6 B$) – Dell:1.6% R&D EDS, MCI-WorldCom, …. (204 M$ of 12.6 B$), To be competitive, some companies cannot make large long-term research investments. The Xerox/PARC story: created Mac, Adobe, 3Com… 6 PITAC Report Presidential IT Advisory Committee http://www.ccic.gov/ac/report/ Findings: – Software construction is a mess: needs breakthroughs. – We do not know how to scale the Internet 100x Security, manageability, services, terabit per second issues. – USG needs high-performance computing (Simulation) but market is not providing vector-supers – just providing processor arrays. – Trained people are in very short supply. Recommendations: – – – – Lewis & Clark expeditions to 21st century. Increase long-term research funding by 1.4B$/y. Re-invigorate university research & teaching. Facilitate immigration of technical experts. 7 Outline (ambitious!) Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 8 Microsoft Research -- 1991 Founded in 1991 Goal: pursue strategic technologies for Microsoft Original research groups: – Natural Language Processing – Operating Systems – Programming Languages Overall size < 20 at the end of 1992 9 Microsoft Research -- 1999 400 Researchers in 25 areas – Operating systems to Statistical Physics Research lab locations: – Redmond, Cambridge, San Francisco, Beijing Internationally recognized research teams – Hundreds of publications, presentations – Leadership roles in professional societies, journals, conferences 10 MS Research Areas Operating systems, languages, compilers, virtual machines, networking, wireless computing, fault-tolerance, large scale servers, security Natural language, speech, vision, graphics, decision theory, information retrieval, UI, collaboration, statistics, signal processing Cryptography, statistical physics and discrete mathematics 11 Growing Fast Grew 20x from ‘92 to ‘99 Decided in ‘97 to grow by a 3x in 3 years – 200 in FY97 => 600 in FY00, primarily in Redmond Major impact on MS products – Virtually all MS products shipped today use technology from MS Research Key role in MS growth – Pioneering research in software that allows computers to see, hear, speak and understand 12 Microsoft Research Philosophy University organizational model – Flat structure, critical mass groups Open research environment – Aggressive publication of research results in literature and on world wide web – Frequent visitors, daily seminars – Over 100 visiting professors and interns in 1998 – Over 110 visiting researchers in 1998 13 What I Do. Work for the government! – CSTB, PITAC(software, ngi), LoC study, .... Work on scaleable systems: – 1 Billion Transactions Per Day Cluster – TerraServer – New: Sloan Digital Sky Survey 17 Outline (ambitious!) Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 18 Gordon Bell on Tele Presentations http://research.microsoft.com/barc/GBell/ 19 Motivation: Telepresentations • Presenter and/or audience telepresent NOT: meeting or collaboration settings Forget the nasty social issues! Mostly one-way 20 Telepresentation Elements Slides Audio Video Script, text comments, hyperlinks, etc. 21 Telepresentations: The Essentials Slide and audio a must Add some video (low quality) to make us feel good Storage and transmission costs low 22 Telepresentations: The Killer App Increased attendance & lower travel costs Practical and low-cost NOW e.g. ACM97 - 2,000 visitors in real space, 20,000 visitors on Internet http://research.microsoft.com/acm97 23 Today’s Experiment Would you like to pause, rewind, browse? Do you wish you could have seen this – At home? – At another time? How much does a present speaker add? How much would you pay for real presence? 24 University Lectures Online Research lectures on-line & on-demand http://murl.microsoft.com/ Will get UVC content Available to anyone anywhere – T1 good, 28.8 OK Generated by CMU, MIT, MSR, Stanford, UW, Xerox Hosted by MSR 25 Outline (ambitious!) Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 26 Changing role of computation Past: Computers for: – computing (Cray) – business data processing (IBM) – “document” creation (PC) Future: Computers for: – understanding & learning – communicating – consuming & entertaining Requires new User Interface to machines 27 Flows Making “Flows” a Reality Computer Graphics – Creating realistic looking environments, people Computer Vision – Analyzing posture, gaze, gestures Speech input/output Natural Language – Analysis, IR Implicit requests for information 29 Building life-like human characters How to fail at Tele-Conferences 1. 2. 3. 4. Eliminate gaze awareness and sense of space of a normal group setting Have long audio latencies & poor audio quality Use incompatible equipment Make it much harder to initiate the call to make a phone call 31 Gaze Awareness & Sense of Space Is anyone paying attention? Who is talking (where is sound coming from? 32 Gaze Awareness Looking at screen: the forehead shot Looking at camera: the glowering shot Looking at YOU. 33 You can’t just move the eyes Glowering Surprise Boredom Interest 34 Mona Lisa Effect Eyes and nose indicated gaze 35 Spatialized Audio & Video Pointing “nose vector” at target Map video onto wire frame Rotate frame to point in space Move (fake) eyes in frame (>30°) to point at target Project voice on that vector. 36 Recognizing gestures Live video Area of motion H flow V flow Generating life-like speech from textual data Data-driven stochastic speech – Natural sounding – Rapid, automatic customizability Examples – Synthetic voice w/ transplanted speech contours 38 Artificial singing AT&T Voder, 1962, by Homer Dudley – Daisy (Inspiration for HAL’s voice in 2001) Microsoft Research Whistler, 1997 – Scarborough Fair 39 Analyzing language Language recognition shipped in Word 97 General purpose text-critiquing, summarization, Japanese word-breaking 40 Inside The Office Grammar Checker 41 Understanding language: MindNet A huge language knowledge base Automatically created from dictionaries Words (nodes) linked by relationships Millions of links Recently added (Encarta) encyclopedia knowledge 42 MindNet -- “Going to the birds” chicken Is_a clean Is_a smooth Is_a poultry Means chatter hen Is_a gaggle Is_a Is_a beak strike Is_a bill egg bird sound Is_a goose Part_of face Locn_of feather wing Is_a claw hawk Is_a Is_a Is_a Typ_obj leg turtle mouth limb Is_a Part Typ_subj_of Is_a creature Is_a Part fly Typ_subj plant Not_is_a Is_a Is_a Typ_subj_of Means meat Is_a Is_a Typ_obj keep Typ_0bj_of Purpose animal Typ_subj make peck duck Cause quack Is_a Typ_obj Quesp Typ_obj Typ_subj preen supply Purpose catch Is_a opening arm Changing balance between user & software systems Yesterday: – Applications were single programs running in isolation – Users used to (more or less) understand systems that they used Today: – Componentized applications operate in concert – Sophisticated users understand only small percentage of systems they use 44 Tomorrow’s Systems and Applications Users will not be able to predict – where computations will be performed, – when they will be performed or – by what software components Gap between system capabilities and user understanding will grow to the point that the only way user will be able to use system is through assisting agents 45 Examples of user agents & implicit actions Lumiere (Office 97) – Monitoring user and program events to provide user help and assistance Implicit queries – Inferring information needs from browsing Lookout/SpamKiller – Monitoring mail activity to auto-categorize it 46 User Modeling Models of a user’s informational goals – User’s query (when available…) – User’s background – Acute and long-term search activity – Acute actions with objects and documents – Program data structures Explicit and implicit information access and display Outline (ambitious!) Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 48 A novel Kilo A letter Mega Library of Congress (text) LoC (sound + cinima) All Disks All Tapes Giga Tera Peta Exa A Movie LoC (image) All Photos Zetta All Information! Yotta 51 Alan Newell’s & Michael Lesk’s Points www.lesk.com/mlesk/ksg97/ksg.html Soon everything can be recorded and kept Most data will never be seen by humans Precious Resource: Human attention Auto-Summarization Auto-Search will be a key enabling technology. 52 Outline (ambitious!) Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 53 Put Everything in Future (Disk) Controllers (it’s not “if”, it’s “when?”) Acknowledgements: Dave Patterson explained this to me a year ago Kim Keeton Erik Riedel Helped me sharpen these arguments Catharine Van Ingen 54 Remember Your Roots 55 Kilo Mega Giga Tera Peta Exa Technology Drivers: Disks Disks on track 100x in 10 years 2 TB 3.5” drive Shrink to 1” is 200GB Disk replaces tape? Zetta Yotta Disk is super computer! 56 Data Gravity Processing Moves to Transducers Move Processing to data sources Move to where the power (and sheet metal) is Processor in – Modem – Display – Microphones (speech recognition) & cameras (vision) – Storage: Data storage and analysis 57 It’s Already True of Printers Peripheral = CyberBrick You buy a printer You get a – several network interfaces – A Postscript engine cpu, memory, software, a spooler (soon) – and… a print engine. 58 Basic Argument for x-Disks Future disk controller is a super-computer. – 1 bips processor – 128 MB dram – 100 GB disk plus one arm Connects to SAN via high-level protocols – RPC, HTTP, DCOM, Kerberos, Directory Services,…. – Commands are RPCs – Management, security,…. – Services file/web/db/… requests – Managed by general-purpose OS with good dev environment Apps in disk saves data movement – need programming environment in controller 60 The Slippery Slope Nothing = Sector Server If you add function to server Then you add more function to server Function gravitates to data. Everything = App Server 61 Why Not Everything? Allow Everything on Disk Server (thin client’s) Tried and true design – Mainframes, Minis, ... – Web servers,… – Encapsulates data – Minimizes data moves – Scaleable It is where everyone ends up. All the arguments against are short-term. 66 Disk = Node has magnetic storage (100 GB?) has processor & DRAM has SAN attachment has execution Applications environment Services DBMS RPC, ... File System SAN driver Disk driver OS Kernel 68 Technology Drivers: System on a Chip Integrate Processing with memory on one chip – chip is 75% memory now – 1MB cache >> 1960 supercomputers – 256 Mb memory chip is 32 MB! – IRAM, CRAM, PIM,… projects abound Integrate Networking with processing on one chip – system bus is a kind of network – ATM, FiberChannel, Ethernet,.. Logic on chip. – Direct IO (no intermediate bus) Functionally specialized cards shrink to a chip. 69 Technology Drivers: What if Networking Was as Cheap As Disk IO? Disk TCP/IP – Unix/NT 100% cpu @ 40MBps – Unix/NT 8% cpu @ 40MBps Why the Difference? Host does TCP/IP packetizing, checksum,… flow control small buffers Host Bus Adapter does SCSI packetizing, checksum,… flow control 70 DMA Technology Drivers: The Promise of SAN/VIA:10x in 2 years http://www.ViArch.org/ Today: – wires are 10 MBps (100 Mbps Ethernet) – ~20 MBps tcp/ip saturates 2 cpus – round-trip latency is ~300 us In the lab – Wires are 10x faster Myrinet, Gbps Ethernet, ServerNet,… – Fast user-level communication tcp/ip ~ 100 MBps 10% of each processor round-trip latency is 15 us 71 SAN: Standard Interconnect Gbps Ethernet: 110 MBps PCI: 70 MBps UW Scsi: 40 MBps LAN faster than memory bus? 1 GBps links in lab. 100$ port cost soon Port is computer FW scsi: 20 MBps scsi: 5 MBps 72 Technology Drivers Plug & Play Software RPC is standardizing: (DCOM, IIOP, HTTP) – Gives huge TOOL LEVERAGE – Solves the hard problems for you: naming, security, directory service, operations,... Commoditized programming environments – – – – FreeBSD, Linix, Solaris,…+ tools NetWare + tools WinCE, WinNT,…+ tools JavaOS + tools Apps gravitate to data. General purpose OS on controller runs apps. 75 Basic Argument for x-Disks Future disk controller is a super-computer. – 1 bips processor – 128 MB dram – 100 GB disk plus one arm Connects to SAN via high-level protocols – RPC, HTTP, DCOM, Kerberos, Directory Services,…. – Commands are RPCs – management, security,…. – Services file/web/db/… requests – Managed by general-purpose OS with good dev environment Move apps to disk to save data movement – need programming environment in controller 76 Summary Microsoft Research (census) Tele-Presentations (Gordon Bell, Jim Gemmell) Microsoft Research initiative on Telepresence What if you could record everything you see & hear? The architecture revolution: processing moves to transducers 77