cyberinfrastructure technologies and applications
Post on 20-Aug-2015
1.618 Views
Preview:
TRANSCRIPT
11
CyberinfrastructureTechnologies and Applications
Summit on Cyberinfrastructure: Innovation At WorkBanff Springs Hotel
Banff Canada October 11 2007
Geoffrey FoxComputer Science, Informatics, Physics
Pervasive Technology LaboratoriesIndiana University Bloomington IN 47401
http://grids.ucs.indiana.edu/ptliupages/presentations/gcf@indiana.edu http://www.infomall.org
2222
e-moreorlessanything ‘e-Science is about global collaboration in key areas of science,
and the next generation of infrastructure that will enable it.’ fromits inventor John Taylor Director General of Research CouncilsUK, Office of Science and Technology
e-Science is about developing tools and technologies that allowscientists to do ‘faster, better or different’ research
Similarly e-Business captures an emerging view of corporations asdynamic virtual organizations linking employees, customers andstakeholders across the world.
This generalizes to e-moreorlessanything including presumably e-AlbertaEnterprise and e-oilandgas, e-geoscience ….
A deluge of data of unprecedented and inevitable size must bemanaged and understood.
People (see Web 2.0), computers, data (including sensors andinstruments) must be linked.
On demand assignment of experts, computers, networks andstorage resources must be supported
3333
What is Cyberinfrastructure Cyberinfrastructure is (from NSF) infrastructure that
supports distributed science (e-Science)– data, people,computers• Clearly core concept more general than Science
Exploits Internet technology (Web2.0) adding (via Gridtechnology) management, security, supercomputers etc.
It has two aspects: parallel – low latency (microseconds)between nodes and distributed – highish latency (milliseconds)between nodes
Parallel needed to get high performance on individual largesimulations, data analysis etc.; must decompose problem
Distributed aspect integrates already distinct components –especially natural for data
Cyberinfrastructure is in general a distributed collection ofparallel systems
Cyberinfrastructure is made of services (originally Webservices) that are “just” programs or data sources packagedfor distributed access
44
Underpinnings ofCyberinfrastructure
Distributed software systems are being “revolutionized” bydevelopments from e-commerce, e-Science and the consumerInternet. There is rapid progress in technology families termed“Web services”, “Grids” and “Web 2.0”
The emerging distributed system picture is of distributed serviceswith advertised interfaces but opaque implementationscommunicating by streams of messages over a variety of protocols• Complete systems are built by combining either services or
predefined/pre-existing collections of services together toachieve new capabilities
As well as Internet/Communication revolutions (distributedsystems), multicore chips will likely be hugely important (parallelsystems)
Industry not academia is leading innovation in these technologies
55
Service or Web Service Approach One uses GML, CML etc. to define the data structure in a
system and one uses services to capture “methods” or“programs”
In eScience, important services fall in three classes• Simulations• Data access, storage, federation, discovery• Filters for data mining and manipulation
Services could use something like WSDL (Web ServiceDefinition Language) to define interoperable interfaces but Web2.0 follows old library practice: one just specifies interface
Service Interface (WSDL) establishes a “contract” independentof implementation between two services or a service and a client
Services should be loosely coupled which normally means theyare coarse grain
Services will be composed (linked together) by mashups(typically scripts) or workflow (often XML – BPEL)
Software Engineering and Interoperability/Standards are closelyrelated
SDSC
TACC
UC/ANL
NCSA
ORNL
PU
IU
PSC
NCAR
Caltech
USC/ISI
UNC/RENCI
UW
Resource Provider (RP)
Software Integration Partner
Grid InfrastructureGroup (UChicago)
Computing and Cyberinfrastructure: TeraGrid
TeraGrid resources include more than 250 teraflops of computing capability and more than 30 petabytes ofonline and archival data storage, with rapid access and retrieval over high-performance networks. TeraGridis coordinated at the University of Chicago, working with the Resource Provider sites: Indiana University,Oak Ridge National Laboratory, National Center for Supercomputing Applications, PittsburghSupercomputing Center, Purdue University, San Diego Supercomputer Center, Texas Advanced ComputingCenter, University of Chicago/Argonne National Laboratory, and the National Center for AtmosphericResearch.
77
Data and Cyberinfrastructure DIKW: Data Information Knowledge Wisdom
transformation Applies to e-Science, Distributed Business Enterprise (including
outsourcing), Military Command and Control and generaldecision support
(SOAP or just RSS) messages transport information expressedin a semantically rich fashion between sources and services thatenhance and transform information so that complete systemprovides• Semantic Web technologies like RDF and OWL might help us
to have rich expressivity but they might be too complicated We are meant to build application specific information
management/transformation systems for each domain• Each domain has Specific Services/Standards (for API’s and Information
such as KML and GML for Geographical Information Systems)• and will use Generic Services (like R for datamining) and• Generic Standards (such as RDF, WSDL)
Standards made before consensus or not observant of technologyprogress are dubious
8Database
SS
SS
SS
SS
SS
SS
SS
SS
SS
SS
FS
FS
FS
FS
FS
FS
FS
FS FS
FS
FS
FS
FS
FS
FS
FS
FS FS
FS
FS
PortalFS
OS
OS
OSOS
OS
OS
OS
OS
OS
OS
OS
OS
MD
MD
MD
MD
MD
MD
MD
MD
MD
MetaDataFilter Service
Sensor Service
OtherService
AnotherGrid
Raw Data Data Information Knowledge Wisdom
Decisions
SS
SS
AnotherService
AnotherService
SSAnother
Grid SS
AnotherGrid
SS
SS
SS
SS
SS
SS
SS
SS
FS
Inter-Service Messages
Information and Cyberinfrastructure
99
Information CyberinfrastructureArchitecture
The Party Line approach to Information Infrastructure is clear– one creates a Cyberinfrastructure consisting of distributedservices accessed by portals/gadgets/gateways/RSS feeds
Services include:• Computing• “original data”• Transformations or filters implementing DIKW (Data Information
Knowledge Wisdom) pipeline• Final “Decision Support” step converting wisdom into action• Generic services such as security, profiles etc.
Some filters could correspond to large simulations Infrastructure will be set up as a System of Systems (Grids of
Grids)• Services and/or Grids just accept some form of DIKW and produce
another form of DIKW• “Original data” has no explicit input; just output
1010
Virtual Observatory Astronomy GridIntegrate Experiments
Radio Far-Infrared Visible
Visible + X-ray
Dust Map
Galaxy Density Map
11
C Y B E R I N F R A S T R U C T U R E C E N T E R F O R P O L A R S C I E N C E ( C I C P S )
12
CReSIS PolarGrid• Important CReSIS-specific Cyberinfrastructure components include
– Managed data from sensors and satellites– Data analysis such as SAR processing – possibly with parallel
algorithms– Electromagnetic simulations (currently commercial codes) to design
instrument antennas– 3D simulations of ice-sheets (glaciers) with non-uniform meshes– GIS Geographical Information Systems
• Also need capabilities present in many Grids– Portal i.e. Science Gateway– Submitting multiple sequential or parallel jobs
• The need for three distinct types of components: Continental USA withmultiple base and field camps– Base and field camps must be power efficient– Terrible connectivity from base and field camps to Continental subGrid
CICC Chemical Informatics and CyberinfrastructureCollaboratory Web Service Infrastructure
Portal ServicesRSS FeedsUser ProfilesCollaboration as in Sakai
Core Grid ServicesService RegistryJob Submission and Management
Local ClustersIU Big Red, TeraGrid, Open Science Grid
Varuna.netQuantum Chemistry
Statistics Services Database Services
Core functionality Computation functionality 3D structures by
Fingerprints Regression CID
Similarity Classification SMARTS
Descriptors Clustering 3D Similarity
2D diagrams Sampling distributions
File format conversion
Docking scores/poses by
Applications Applications CID
Docking Predictive models SMARTS
Filtering Feature selection Protein
2D plots Docking scores
Toxicity predictions
Anti-cancer activity predictions
CID, SMARTS
Cheminformatics Services
Druglikeness
Arbitrary R code (PkCell)
Mutagenecity predictions
PubChem related data by
Pharmacokinetic parameters
OSCAR Document AnalysisInChI Generation/SearchComputational Chemistry (Gamess, Jaguar etc.)
14
Process Chemistry-Biology Interaction Datafrom HTS (High Throughput Screening)
Percent Inhibitionor IC50 data isretrieved from HTS
Question: Was thisscreen successful?
Question: What should theactive/inactive cutoffs be?
Question: What can welearn about the targetprotein or cell line from thisscreen?
Compound data submittedto PubChem
Workflows encodingdistribution analysis ofscreening results
Grids can link dataanalysis ( e.g imageprocessing developedin existing Grids),traditional Chem-informatics tools, aswell as annotationtools (Semantic Web,del.icio.us) andenhance lead ID andSAR analysis
A Grid of Grids linkingcollections of servicesatPubChemECCR centersMLSCN centers
Workflows encodingplate & control wellstatistics, distributionanalysis, etc
Workflows encodingstatistical comparison ofresults to similarscreens, docking ofcompounds into proteinsto correlate binding, withactivity, literature searchof active compounds,etc
CHEMINFORMATICSPROCESS GRIDS
Scientists at IU prefer Web 2.0 toGrid/Web Service for workflow
1515
People and Cyberinfrastructure: Web 2.0 Web 2.0 has tools (sites) and technologies
• Technologies (later) are “competition” for Grids and WebServices
• Sites (below) are the best way to integrate people intoCyberinfrastructure
Kazaa, Instant Messengers, Skype, Napster, BitTorrent for P2PCollaboration – text, audio-video conferencing, files
del.icio.us, Connotea, Citeulike, Bibsonomy, Biolicious manageshared bookmarks
MySpace, YouTube, Bebo, Hotornot, Facebook, or similar sitesallow you to create (upload) community resources and sharethem; Friendster, LinkedIn create networks• http://en.wikipedia.org/wiki/List_of_social_networking_websites
Writely, Wikis and Blogs are powerful specialized shareddocument systems
Google Scholar and Windows Live Academic Search tells you whohas cited your papers while publisher sites tell you about co-authors
16161616
“Best Web 2.0 Sites” -- 2006 Extracted from http://web2.wsj2.com/ Social Networking
Start Pages
Social Bookmarking
Peer Production News
Social Media Sharing
Online Storage(Computing)
1717
Web 2.0 Systems are Portals, Services, Resources Captures the incredible development of interactive
Web sites enabling people to create and collaborate
1818
Web 2.0 and Web Services I Web Services have clearly defined protocols (SOAP) and a well
defined mechanism (WSDL) to define service interfaces• There is good .NET and Java support• The so-called WS-* specifications provide a rich sophisticated but
complicated standard set of capabilities for security, fault tolerance, meta-data, discovery, notification etc.
“Narrow Grids” build on Web Services and provide a robustmanaged environment with growing adoption in Enterprisesystems and distributed science (so called e-Science)
Web 2.0 supports a similar architecture to Web services but hasdeveloped in a more chaotic but remarkably successful fashionwith a service architecture with a variety of protocols includingthose of Web and Grid services• Over 500 Interfaces defined at http://www.programmableweb.com/apis
Web 2.0 also has many well known capabilities with GoogleMaps and Amazon Compute/Storage services of clear generalrelevance
There are also Web 2.0 services supporting novel collaborationmodes and user interaction with the web as seen in socialnetworking sites, portals, MySpace, YouTube,
1919
Web 2.0 and Web Services II I once thought Web Services were inevitable but this is
no longer clear to me Web services are complicated, slow and non functional
• WS-Security is unnecessarily slow and pedantic(canonicalization of XML)
• WS-RM (Reliable Messaging) seems to have pooradoption and doesn’t work well in collaboration
• WSDM (distributed management) specifies a lot There are de facto standards like Google Maps and
powerful suppliers like Google which “define the rules” One can easily combine SOAP (Web Service) based
services/systems with HTTP messages but the “lowestcommon denominator” suggests additionalstructure/complexity of SOAP will not easily survive
2020
Applications, Infrastructure,Technologies
The discussion is confused by inconsistent use of terminology –this is what I mean
Multicore, Narrow and Broad Grids and Web 2.0 (Enterprise2.0) are technologies
These technologies combine and compete to build infrastructurestermed e-infrastructure or Cyberinfrastructure• Although multicore can and will support “standalone” clients probably
most important client and server applications of the future will be internetenhanced/enabled so key aspect of multicore is its role and integration ine-infrastructure
e-moreorlessanything is an emerging application area of broadimportance that is hosted on the infrastructures e-infrastructureor Cyberinfrastructure
2121
Some Web 2.0 Activities at IU Use of Blogs, RSS feeds, Wikis etc. Use of Mashups for Cheminformatics Grid workflows Moving from Portlets to Gadgets in portals (or at least
supporting both) Use of Connotea to produce tagged document
collections such as http://www.connotea.org/user/crmcfor parallel computing
Semantic Research Grid integrates multiple taggingand search systems and copes with overlappinginconsistent annotations
MSI-CIEC portal augments Connotea to tag a mix ofURL and URI’s e.g. NSF TeraGrid use, PI’s andProposals• Hopes to support collaboration (for Minority Serving
Institution faculty)
2222
Use blog tocreate posts.
Display blog RSSfeed in MediaWiki.
2323
Semantic Research Grid (SRG) Architecture
10/22/07 23
2424
MSI-CIEC Portal
MSI-CIECMinority Serving Institution CyberInfrastructure Empowerment Coalition
25252525
Mashups v Workflow? Mashup Tools are reviewed at
http://blogs.zdnet.com/Hinchcliffe/?p=63 Workflow Tools are reviewed by Gannon and Fox
http://grids.ucs.indiana.edu/ptliupages/publications/Workflow-overview.pdf Both include scripting
in PHP, Python, sh etc.as both implementdistributedprogramming at levelof services
Mashups use all typesof service interfacesand perhaps do nothave the potentialrobustness (security) ofGrid service approach
Mashups typically“pure” HTTP (REST)
26262626
Grid Workflow Datamining in Earth Science Work with Scripps Institute Grid services controlled by workflow process real time
data from ~70 GPS Sensors in Southern California
Streaming DataSupport
TransformationsData Checking
Hidden MarkovDatamining (JPL)
Display (GIS)
NASA GPS
Earthquake
Real Time
Archival
2727
Grid Workflow Data Assimilation in Earth Science Grid services triggered by abnormal events and controlled by workflow process real
time data from radar and high resolution simulations for tornado forecasts
Typicalgraphicalinterface toservicecomposition
28282828
Web 2.0 uses all types of Services Here a Gadget Mashup uses a 3 service workflow with
a JavaScript Gadget Client
2929
Web 2.0 Mashupsand APIs
http://www.programmableweb.com/apis has (Sept 122007) 2312 Mashups and511 Web 2.0 APIs and withGoogleMaps the most oftenused in Mashups
The Web 2.0 UDDI (serviceregistry)
3030
The List of Web2.0 API’s
Each site has API andits features
Divided into broadcategories
Only a few used a lot(49 API’s used in 10or more mashups)
RSS feed of new APIs Amazon S3 growing
in popularity
3131
Now to Portals3131
Grid-style portal as used in Earthquake GridThe Portal is built from portlets
– providing user interfacefragments for each servicethat are composed into thefull interface – uses OGCEtechnology as does planetaryscience VLAB portal withUniversity of Minnesota
32323232
Portlets v. Google Gadgets Portals for Grid Systems are built using portlets with
software like GridSphere integrating these on theserver-side into a single web-page
Google (at least) offers the Google sidebar and Googlehome page which support Web 2.0 services and do notuse a server side aggregator
Google is more user friendly! The many Web 2.0 competitions is an interesting model
for promoting development in the world-widedistributed collection of Web 2.0 developers
I guess Web 2.0 model will win!
Note the many competitions powering Web 2.0 Mashup Development
Typical Google Gadget Structure
… Lots of HTML and JavaScript </Content> </Module>Portlets build User Interfaces by combining fragments in a standalone Java ServerGoogle Gadgets build User Interfaces by combining fragments with JavaScript on the client
Google Gadgets are an example ofStart Page technologySee http://blogs.zdnet.com/Hinchcliffe/?p=8
3434
Web 2.0 v Narrow Grid I Web 2.0 and Grids are addressing a similar application class
although Web 2.0 has focused on user interactions• So technology has similar requirements
Web 2.0 chooses simplicity (REST rather than SOAP) to lowerbarrier to everyone participating
Web 2.0 and Parallel Computing tend to use traditional (possiblyvisual) (scripting) languages for equivalent of workflow whereasGrids use visual interface backend recorded in BPEL
Web 2.0 and Grids both use SOA Service Oriented Architectures “System of Systems”: Grids and Web 2.0 are likely to build
systems hierarchically out of smaller systems• We need to support Grids of Grids, Webs of Grids, Grids of
Services etc. i.e. systems of systems of all sorts
3434
Web 2.0 v Narrow Grid II Web 2.0 has a set of major services like GoogleMaps or Flickr
but the world is composing Mashups that make new compositeservices• End-point standards are set by end-point owners• Many different protocols covering a variety of de-facto standards
Narrow Grids have a set of major software systems like Condorand Globus and a different world is extending with customservices and linking with workflow
Popular Web 2.0 technologies are PHP, JavaScript, JSON,AJAX and REST with “Start Page” e.g. (Google Gadgets)interfaces
Popular Narrow Grid technologies are Apache Axis, BPELWSDL and SOAP with portlet interfaces
Robustness of Grids demanded by the Enterprise? Not so clear that Web 2.0 won’t eventually dominate other
application areas and with Enterprise 2.0 it’s invading GridsThe world does itself in large numbers!
3636
Web 2.0 v Narrow Grid III Narrow Grids have a strong emphasis on standards and
structure; Web 2.0 lets a 1000 flowers (protocols) and a milliondevelopers bloom and focuses on functionality, broad usabilityand simplicity• Semantic Web/Grid has structure to allow reasoning• Annotation in sites like del.icio.us and uploading to
MySpace/YouTube is unstructured and free text searchreplaces structured ontologies
Portals are likely to feature both Web and “desktop client” technologyalthough it is possible that Web approach will be adopted more or lessuniformly
Web 2.0 has a very active portal activity which has similar architecture toGrids• A page has multiple user interface fragments
Web 2.0 user interface integration is typically Client side using GadgetsAJAX and JavaScript while• Grids are in a special JSR168 portal server side using Portlets WSRP and
Java3636
3737
The Ten areas covered by the 60 core WS-*Specifications
WSRP (Remote Portlets)10: Portals and User Interfaces
WS-Policy, WS-Agreement9: Policy and Agreements
WSDM, WS-Management, WS-Transfer8: Management
WSRF, WS-MetadataExchange, WS-Context7: System Metadata and State
UDDI, WS-Discovery6: Service Discovery
WS-Security, WS-Trust, WS-Federation, SAML,WS-SecureConversation
5: Security
BPEL, WS-Choreography, WS-Coordination4: Workflow and Transactions
WS-Notification, WS-Eventing (Publish-Subscribe)
3: Notification
WS-Addressing, WS-MessageDelivery; ReliableMessaging WSRM; Efficient Messaging MOTM
2: Service Internet
XML, WSDL, SOAP1: Core Service ModelTypical Grid/Web Service ExamplesWS-* Specification Area
3838
WS-* Areas and Web 2.0
Start Pages, AJAX and Widgets(Netvibes) Gadgets10: Portals and User Interfaces
Service dependent. Processed by application9: Policy and Agreements
WS-Transfer style Protocols GET PUT etc.8: Management==Interaction
Processed by application – no system state –Microformats are a universal metadata approach
7: System Metadata and State
http://www.programmableweb.com6: Service Discovery
SSL, HTTP Authentication/Authorization,OpenID is Web 2.0 Single Sign on
5: Security
Mashups, Google MapReduceScripting with PHP JavaScript ….
4: Workflow and Transactions(no Transactions in Web 2.0)
Hard with HTTP without polling– JMS perhaps?3: NotificationNo special QoS. Use JMS or equivalent?2: Service Internet
XML becomes optional but still usefulSOAP becomes JSON RSS ATOMWSDL becomes REST with API as GET PUT etc.Axis becomes XmlHttpRequest
1: Core Service Model
Web 2.0 ApproachWS-* Specification Area
3939
Too much Computing? Historically one has tried to increase computing capabilities by
• Optimizing performance of codes• Exploiting all possible CPU’s such as Graphics co-processors and “idle
cycles”• Making central computers available such as NSF/DoE/DoD
supercomputer networks
Next Crisis in technology area will be the opposite problem –commodity chips will be 32-128way parallel in 5 years time andwe currently have no idea how to use them – especially on clients• Only 2 releases of standard software (e.g. Office) in this time span
Gaming and Generalized decision support (data mining) are twoobvious ways of using these cycles• Intel RMS analysis• Note even cell phones will be multicore
There is “Too much data” as well as “Too much computing” butunclear implications
4040
Intel’s Projection
41Pradeep K. Dubey, pradeep.dubey@intel.com
Tomorrow
What is …? What if …?Is it …?Recognition Mining Synthesis
Create a model instance
RMS: Recognition Mining Synthesis
Model-basedmultimodalrecognition
Find a modelinstanceModel
Real-time analytics ondynamic, unstructured,
multimodal datasets
Photo-realism andphysics-based
animation
TodayModel-less Real-time streaming and
transactions on static – structured datasets
Very limited realism
42Pradeep K. Dubey, pradeep.dubey@intel.com
What is a tumor? Is there a tumor here? What if the tumor progresses?
It is all about dealing efficiently with complex multimodal datasets
Recognition Mining Synthesis
Images courtesy: http://splweb.bwh.harvard.edu:8000/pages/images_movies.html
43Intel’s Application Stack
4444
Multicore SALSA at IU Service Aggregated Linked Sequential Activities
• http://www.infomall.org/multicore Aims to link parallel and distributed (Grid) computing
by developing parallel applications as services and notas programs or libraries• Improve traditionally poor parallel programming
development environments Can use messaging to link parallel and Grid services
but performance – functionality tradeoffs different• Parallelism needs few µs latency for message latency and
thread spawning• Network overheads in Grid 10-100’s µs
Developing Service (library) of multicore parallel datamining algorithms
4545
Microsoft CCR for Parallelism• Use Microsoft CCR/DSS where DSS is mash-up/workflow service
model built from CCR and CCR supports MPI or Dynamic threads• CCR Supports exchange of messages between threads using named
ports• FromHandler: Spawn threads without reading ports• Receive: Each handler reads one item from a single port• MultipleItemReceive: Each handler reads a prescribed number of
items of a given type from a given port. Note items in a port can begeneral structures but all must have same type.
• MultiplePortReceive: Each handler reads a one item of a given typefrom multiple ports.
• JoinedReceive: Each handler reads one item from each of two ports.The items can be of different type.
• Choice: Execute a choice of two or more port-handler pairings• Interleave: Consists of a set of arbiters (port -- handler pairs) of 3
types that are Concurrent, Exclusive or Teardown (called at end forclean up). Concurrent arbiters are run concurrently but exclusivehandlers are
• http://msdn.microsoft.com/robotics/
46464646
DSS "Get" (loop 1 to 10000; two services on one node)
0
50
100
150
200
250
300
350
1 10 100 1000 10000
Round trips
Avera
ge r
un
tim
e (
mic
roseco
nd
s)
Series1
Timing of HP Opteron Multicore as a function of number of simultaneous two-way service messages processed (November 2006 DSS Release)
Measurements of Axis 2 shows about 500 microseconds – DSS is 10 times better
DSS Service Measurements
474725.84ThreadCCRXPIntel4 (4 core 2.8 Ghz)
16.34ThreadCCRXP39.34ProcessMPICH299.44ProcessmpiJava1524ProcessMPJERedhat1854ProcessMPJEXPAMD4
(4 core 2.19 Ghz)
20.28ThreadCCR (C#)Vista1008ProcessmpiJavaFedora1428ProcessMPJEFedora
1708ProcessMPJEVistaIntel8b(8 core 2.66 Ghz)
64.28ProcessMPICH21118ProcessmpiJava1578ProcessMPJEFedoraIntel8c:gf20
(8 core 2.33 Ghz)
4.218ProcessNemesis39.38ProcessMPICH2: Fast40.08ProcessMPICH2 (C)
1818ProcessMPJE (Java)RedhatIntel8c:gf12(8 core 2.33 Ghz)(in 2 chips)
MPI ExchangeLatency
ParallelismGrainsRuntimeOSMachine
MPI Exchange Latency in µs (20-30 µs computation between messaging)
4848
Clustering algorithm annealing by decreasing distance scale and gradually finds moreclusters as resolution improvedHere we see 10 increasing to 30 as algorithm progresses
PC07Intro gcf@indiana.edu 49
Parallel Multicore Clustering(C# on Windows)
0
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0.4
0.45
0 0.5 1 1.5 2 2.5 3 3.5 4
Parallel Overheadon 8 Threads running on Intel 8 core
Speedup = 8/(1+Overhead)
10000/(Grain Size n = points per core)
Overhead = Constant1 + Constant2/n
Constant1 = 0.05 to 0.1 (Client Windows) due to threadruntime fluctuations
10 Clusters
20 Clusters
5050
We use DSS as Service Framework as Integratedwith CCR Supporting MPI/Threading
PC07Intro gcf@indiana.edu 51
Intel 8-core C# with 80 Clusters: Vista RunTime Fluctuations for Clustering Kernel
• 2 Quadcore Processors• This is average of standard deviation of run time of the 8 threads
between messaging synchronization points80 Cluster(ratio of std to time vs #thread)
0
0.05
0.1
0 1 2 3 4 5 6 7 8
thread
std
/ t
ime
10,000 Datpts
50,000 Datapts
500,000 Datapts
Number of Threads
Standard Deviation/Run Time
PC07Intro gcf@indiana.edu 52
80 Cluster(ratio of std to time vs #thread)
0
0.002
0.004
0.006
1 2 3 4 5 6 7 8
10,000 Datapts
50,000 Datapts
500,000 Datapts
Intel 8 core with 80 Clusters: Redhat RunTime Fluctuations for Clustering Kernel
• This is average of standard deviation of run time of the8 threads between messaging synchronization points
Number of Threads
Standard Deviation/Run Time
5353
What should one do? i.e. How does one Cyberinfrastructure enable a given area/application XYZ As computing free, focus on identifying data/information/knowledge/wisdom
needed (there is probably too much data but not so much wisdom in DIKWpipeline)• Should we care just about “original data” or also about the whole pipeline DIKW?
Scope out supercomputer/computer services needed and exploit OGFstandards
Identify services (filters, often data mining) needed by XYZ?• Will we need parallel implementations of filters – if so use multicore compatible
frameworks Identify standards for application XYZ Set up distributed XYZ Services Use Web 2.0 (as it makes things easier) not current Grids (which makes
things harder)• Build a “Programmable XYZ Web”’• Emphasize Simplicity• Is “Secrecy” important and in fact viable? Often important but hard
What are synergies of XYZ to pervasive capabilities such as Web 2.0 sites,National resources like TeraGrid, and “Personal aides in an information richworld” (future of PC) ?
top related