1 NAREGI Project Goals Establishment of a research grid infrastructure NAREGI is a collaborative research project between industry, academia, and govern- ment organizations. Our goal is to develop a new science grid that will be able to perform large- scale simulations for next-generation R&D. The Center for Grid Research and Develop- ment and the Computational Nano-science Center serve as the bases of project activities. The Center for Grid Research and Develop- ment develops grid infrastructure software and network technology. The Computational Nano-science Center evaluates the new grid system using application software and advanced nano- science simulation technology. Revitalization of the IT industry through commercialization of grid middleware and strengthened international competitiveness Dissemination of grid environments through- out industry (through cooperation with The Computational Nano-science Center ) Leadership in the standardization of grid technology Cultivation of human resources specializing in IT technology for grids
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
1
NAREGI Project Goals
Establishment of a research grid infrastructure
NAREGI is a collaborative research project between industry, academia, and govern-ment organizations. Our goal is to develop a new science grid that will be able to perform large- scale simulations for next-generation R&D.The Center for Grid Research and Develop-ment and the Computational Nano-science Center serve as the bases of project activities.The Center for Grid Research and Develop-ment develops grid infrastructure software and network technology.The Computational Nano-science Center evaluates the new grid system using application software and advanced nano-science simulation technology.
Revitalization of the IT industry through commercialization of grid middleware and strengthened international competitiveness
Dissemination of grid environments through-out industry (through cooperation with The Computational Nano-science Center )
Leadership in the standardization of grid technology
Cultivation of human resources specializing in IT technology for grids
2
Background of Science Grid R &D (1)
Present Industrial Infrastructure
Next-generation Industrial Infrastructure
Nano-science / Biotechnology
Simulation Based on Quantum Theory＋
Large-scale Computing Resources||
Design of Nano Structure
Construct Theoretical System for Heat, Structure, Fluid, and Electromagnetism
Understand Phenomenon throughObservation and Experiment
Support Product Development Power in the 21st Century
Advance Computer Simulation
Support Industry as the Theoretical Backbone to Product R&D
Computer Simulation is Essential to Understand Phenomena related to
Nano & Bio Technologies
Support Research and Development in the 21st Century
R&D-capable computer resources help establish the next-generation industrial infrastructure.
3
Background of Science Grid R &D (2)
1) Development based on experiment / measurement data
2) Development based on combiningsingle-function simulations
1) System-wide large-scale analysis2) Multi-scale analysis3) Multi-physics analysis
Conventional R & D and Product Development
Next-generation R & D and Product Development
Coupled Simulation Requirements Computing Resource Requirements
1) Shorter development periods2) Understanding new phenomena3) Optimizing designs
Required computer capacity is based on data from the National Institute of Science and Technology Policy.
Current World’s Highest
Automobile Design / Chip Design100G
2004 2020
1T
100T
10P
2000 2010
100PComputing Resources
Required for Next-Generation R&D World’s Highest
Affordable
Protein Structure Analysis /Drug Design
Organic Material Function / Reaction Prediction
Reaction Condition Optimization / Semiconductor Function Prediction
4
NAREGI R&D System
Project Leader (Dr.K.Miura, NII)
5Relationship among NAREGI Organizations and Outputs of the Project
Use in Industry（New Intellectual
Product Development)
Vitalization of Industry
e – Infrastructure
Grid Middleware for Large Computer Centers
Personnel Training (IT and Application
Engineers)
Contribution to Interna-tional Scientific Community
and Standardization
Grid Applications Environment
High-performance & Secure Grid Networking
Resource Management in the Grid Environment
Grid Programming Environment
Grid-Enabled Nano-Applications
Center for Grid Research and Development
Grid Middleware（National Institute of Informatics）
Computational Methods for Nano-science using the Latest Grid Technology
Subjects of ResearchLarge-scale Computation
High Throughput Computation
New Methodology for Computational Science
Computational Nano-science Center
（Institute of Molecular Science）
Requirement from the Industry with regard to Science Grid for Industrial Applications
Solicited Research Proposalsfrom the Industry to Evaluate
Grid System with Nano-science Applications
Consortium for Promotion ofGrid Applications in Industry（Member company: 40 companies）
Science Grid Environment
Evaluation of Grid System with Nano Applications
Progress in the Latest Research and Development
(Nano, Biotechnology)
Productization of General-purpose
Grid Middleware for Scientific Computing
6
NAREGI Server GridResource allocation on Server Grid, Automatic scheduling of executing jobs, where users can run their HPC application programs as it is or slightly modified.
Kyushu U
NII(Jinbocho)
IMR,Tohoku U
AIST,KEK (Tsukuba)ISSP (Kashiwa)
IMS(Okazaki)
SUPERSINET
Kyoto U
Seamless resource coordination across many different research organizations.
NAREGI Middlewares
Cross-Organizational Virtual Computer
7
NAREGI Middleware Stack
Computing Resources
NII IMS Research Organizations etc
（（Globus,Condor,UNICOREGlobus,Condor,UNICORE OGSAOGSA))
SuperSINET
Grid-Enabled Nano-Applications
Grid PSEGrid Programming
-Grid RPC-Grid MPI
Grid Visualization
Grid VM
Packaging
DistributedInformation Service
Grid Workflow
Super Scheduler
High-Performance & Secure Grid Networking
8
MPI
RISMJob
LocalScheduler
LocalScheduler
IMPIServer
GridVM
FMOJob
LocalScheduler
SuperScheduler
WFT
RISMsourceFMO
source
Work-flow
PSECA
Site A Site B(SMP machine)
Site C(PC cluster)
6: Co-Allocation
3: NegotiationAgreement
6: Submission
10: Accounting
10: Monitoring
4: Reservation
5: Sub-Job
3: Negotiation
1: Submissionc: Editb: Deploymenta: Registration
CA CA CA
Resource Query
GridVM GridVM
DistributedInformation
Service
GridMPI
RISMSMP
64 CPUs
FMOPC Cluster128 CPUs
Grid Visualization
Output files
Input files
IMPI
Scenario for Multi-site MPI Job Execution
9Adaptation of Nano-science Applications to Grid Environment
Site A
MPICH-G2, Globus
RISMRISM FMOFMO
Site BMPICH-G2, Globus
Data Transformationbetween Different Meshes
Electronic Structurein Solutions
Electronic StructureAnalysis
Solvent DistributionAnalysis
Grid MiddlewareGrid Middleware
RISM FMO Fragment Molecular Orbital methodReference Interaction Site Model
10
NAREGI Five-year Plan
11
NAREGI Phase 1 Testbed
～３０００ CPUs～１７Tflops
SuperSINET
Center for GRID R&D(NII)
～5 Tflops
Computational Nanoscience Center(IMS)
～10 Tflops
Osaka Univ.BioGrid
TiTechCampus Grid
AISTSuperCluster
ISSPSmall Test App Clusters
Kyoto Univ.Small Test App Clusters
Tohoku Univ.Small Test App Clusters
KEKSmall Test App Clusters
Kyushu Univ.Small Test App Clusters
AISTSmall Test App Clusters
Construction of a Testbed of HeterogeneousEnvironments for the Verification ofGrid System Development
12Computer System for Grid Software Infrastructure R & D
Center for Grid Research and Development（５Ｔflops，700GB)
File Server(PRIMEPOWER 900 ＋ETERNUS3000 ＋ ETERNUS LT160）
(SPARC64V1.3GHz)(SPARC64V1.3GHz)1node1node／8CPU
SMP type Compute Server (PRIMEPOWER HPC2500）
1node (UNIX, 1node (UNIX, SPARC64V1.3GHz/64CPU)SPARC64V1.3GHz/64CPU)
SMP type Compute Server(SGI Altix3700）
1node 1node (Itanium2 1.3GHz/32CPU)(Itanium2 1.3GHz/32CPU)
SMP type Compute Server(IBM pSeries690）
1node 1node (Power4(Power4 1.3GHz1.3GHz/32CPU)/32CPU)
InfiniBand 4X(8Gbps)
InfiniBand 4X (8Gbps)
Distributed-memory typeCompute Server(HPC LinuxNetworx ）
GbE (1Gbps)
Distributed-memory type Compute Server(Express 5800）
GbE (1Gbps)
GbE (1Gbps)
GbE (1Gbps)
SuperSINET
High Perf. Distributed-memory Type Compute Server (PRIMERGY RX200）
High Perf. Distributed-memory type Compute Server (PRIMERGY RX200）
Memory 130GBStorage 9.4TBMemory 130GBStorage 9.4TB
128CPUs128CPUs(Xeon, 3.06GHz)(Xeon, 3.06GHz)+Control Node+Control Node
Memory 65GBStorage 9.4TBMemory 65GBStorage 9.4TB
128 128 CPUsCPUs(Xeon(Xeon, 3.06GHz), 3.06GHz)+Control Node+Control Node
Memory 65GBStorage 4.7TBMemory 65GBStorage 4.7TB
Memory 65GBStorage 4.7TBMemory 65GBStorage 4.7TB
Memory 65GBStorage 4.7TBMemory 65GBStorage 4.7TB
Memory 65GBStorage 4.7TBMemory 65GBStorage 4.7TB
128 CPUs 128 CPUs (Xeon, 2.8GHz)(Xeon, 2.8GHz)+Control Node+Control Node
128 CPUs 128 CPUs (Xeon, 2.8GHz)(Xeon, 2.8GHz)+Control Node+Control Node
128 128 CPUs(XeonCPUs(Xeon, 2.8GHz)+Control Node, 2.8GHz)+Control Node
Distributed-memory type Compute Server (Express 5800）
128 CPUs 128 CPUs (Xeon, 2.8GHz)(Xeon, 2.8GHz)+Control Node+Control Node
Distributed-memory typeCompute Server(HPC LinuxNetworx ）
Ext. NW
Intra NW-AIntra NW
Intra NW-B
L3 SWL3 SW1Gbps1Gbps
((upgradableupgradableTo 10Gbps)To 10Gbps)
L3 SWL3 SW1Gbps1Gbps
((UpgradableUpgradableto 10Gbps)to 10Gbps)
Memory 16GBStorage 10TBBack-up Max.36.4TB
Memory 16GBStorage 10TBBack-up Max.36.4TB
Memory 128GBStorage 441GBMemory 128GBStorage 441GB
Memory 32GBStorage 180GBMemory 32GBStorage 180GB
Memory 64GBStorage 480GBMemory 64GBStorage 480GB
13Computer System for Nano Application R & D
Computational Nano science Center（10Ｔflops，5TB)
SMP type Computer Server
Memory 3072GBStorage 2.2TBMemory 3072GBStorage 2.2TB
Distributed-memory type Computer Server(4 units)818 CPUs(Xeon, 3.06GHz)+Control Nodes818 CPUs(Xeon, 3.06GHz)+Control NodesMyrinet2000 (2Gbps)
Memory 1.6TBStorage 1.1TB/unitMemory 1.6TBStorage 1.1TB/unit
File Server16CPUs (SPARC64 GP, 675MHz)(SPARC64 GP, 675MHz)
Memory 8GBStorage 30TBBack-up 25TB
Memory 8GBStorage 30TBBack-up 25TB
5.4 TFLOPS 5.0 TFLOPS16ways16ways××50nodes (POWER4+ 1.7GHz)50nodes (POWER4+ 1.7GHz)MultiMulti--stage Crossbar Networkstage Crossbar Network
L3 SWL3 SW1Gbps1Gbps
((UpgradableUpgradable to to 10Gbps)10Gbps)
VPN
Firewall
SuperSINETCenter for Grid R & D
Front-end ServerFront-end Server
CA/RA Server
14
Summary
１） Grid will be not only the information infrastructure, but also the R & D base and the industrial infrastructure in the 21st century.
２） Develop a grid middleware which seamlessly connects heterogeneous computer resources spanned across the nation.
３） Utilize the developed grid infrastructure by conducting research on leading-edge nano science and nano technology simulation applications on top of the infrastructure.
４） Hand down the developed grid technology to industry sector and lead to the strengthening of its international competitiveness.
５） Contribute to international standardization of grid technology
Related Documents
